JP2853638B2 - Shift control device for automatic transmission for vehicle - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

The present invention relates to a shift control device for an automatic transmission for a vehicle, and more particularly to a shift control device for an automatic transmission in which a shift control is performed based on learning.

[0002]

2. Description of the Related Art Conventionally, as a vehicle transmission, an automatic transmission in which a shift operation is automated has been frequently used. The mainstream of this automatic transmission uses a torque converter in place of a clutch. Also, in the case of large vehicles such as buses and trucks, an actuator that automatically connects and disconnects a clutch to a mechanical transmission similar to a manual transmission is provided due to the relationship with the amount of transmission of drive torque. It has been considered to construct an automatic transmission by removing the pedal.

Usually, in such a shift control device for an automatic transmission, a target shift speed is set according to a vehicle speed and an accelerator opening. However, it is difficult to sufficiently reflect the driver's intentions and preferences according to the vehicle speed and the accelerator opening in the target shift speed, and therefore, the shifts according to the intentions of all the drivers are necessarily realized satisfactorily. Not necessarily.

Therefore, in recent years, an automatic transmission has been developed which is capable of manual shifting according to the driver's preference while mainly performing automatic shifting. Is also possible.
Further, a shift control device configured to learn the driver's preference based on the details of the shift using a neural network or the like and to perform an automatic shift in accordance with the learned details is disclosed in Japanese Patent Laid-Open No. 7-980.
No. 60 and the like.

[0005]

In the transmission control device disclosed in the above-mentioned publication, not only the transmission based purely on the driver's preference, but also the transmission is required due to road conditions and the like. There is a possibility that the necessary shift information may be used as data for learning. For example, when the vehicle is traveling at a low speed on a congested road, most of the shifting is performed according to the road conditions regardless of the driver's preference, but all the shifting information at this time is used as learning data. May be used.

[0006] As described above, if data that is not suitable for learning is mixed during learning, the accuracy of learning is reduced, and as a result, it is difficult to maintain good shift control according to the driver's preference. Become. In particular, in upshifting during low-speed traveling such as in congested roads, the driver's preferences are slightly different for each driver, and learning effects are greatly expected. The shift control during traveling is unstable and is not preferable.

SUMMARY OF THE INVENTION The present invention has been made in view of the above-mentioned circumstances, and has as its object to provide an automatic vehicle control system capable of accurately and appropriately performing learning according to the driver's preference and realizing stable shift control. A transmission control device for a transmission is provided.

[0008]

In order to achieve the above-mentioned object, the present invention provides an accelerator opening detecting means for detecting an accelerator opening of an engine, and an engine speed detecting means for detecting an engine speed. Means, monitoring means for monitoring at least one of the accelerator opening and the engine speed at the time of switching the gear position of the automatic transmission, and learning data calculation for calculating learning data based on an output from the monitoring means. Means, learning means for learning so as to carry out a gear shift reflecting a driver's shift preference based on the learning data, and the automatic transmission based on an output from the learning means and a driving state of the vehicle. Shift control means for performing shift control of the vehicle, and congested road travel determination means for determining that the vehicle is traveling on a congested road. If it is determined that the vehicle is running the congested road by road travel determining means, it is characterized in that not updated training data without employing the output from the monitoring means.

Therefore, at least one of the accelerator opening and the engine speed at the time of switching the gear position of the automatic transmission is monitored and output, and learning data is calculated based on this output. Then, based on the learning data, learning is performed so as to execute the shift speed change reflecting the driver's shift preference, and the shift control of the automatic transmission is favorably performed. However, if the traffic congestion road traveling determination means determines that the vehicle is traveling on a congested road, the learning data calculation means does not use the output from the monitor means. Therefore, while the vehicle is traveling on a congested road, the learning data is not updated unnecessarily, and the accuracy of the shift control reflecting the shift preference of the driver is suitably maintained.

Further, according to the second aspect of the present invention, a vehicle connected to the engine and provided with a manual mode in which a gear is switched by a driver's operation and an automatic mode in which the gear is automatically switched according to the driving state of the vehicle. Opening control means for detecting the accelerator opening of the engine, engine speed detecting means for detecting the engine speed, and the accelerator at the time of switching the gear position of the automatic transmission. Monitoring means for monitoring at least one of the opening degree and the engine speed; learning data calculating means for calculating learning data based on an output from the monitoring means in at least one of the manual mode and the automatic mode; Speed change based on data, reflecting the driver's shift preference during the auto mode And learning means for learning in order to practice,
Target shift speed setting means for setting a target shift speed based on an output from the learning means and a driving state of the vehicle; shift control means for performing shift control of the automatic transmission based on the target shift speed; A traffic congestion road traveling determination unit that determines that the vehicle is traveling on a road, and wherein the learning data calculation unit is configured to determine whether the vehicle is traveling on the congested road by the congestion road traveling determination unit. It is characterized in that the learning data is not updated without using the output from the monitor means.

Accordingly, in a shift control device for an automatic transmission for a vehicle having a manual mode and an automatic mode,
At least one of the accelerator opening and the engine speed at the time of switching the gear position of the automatic transmission is monitored, and learning data is calculated based on the monitor output in at least one of the manual mode and the automatic mode.
Based on the learning data, learning is performed so as to execute a gear shift reflecting the driver's shift preference in the auto mode, whereby a target gear is set, and gear shift control of the automatic transmission is performed. Performed well. However, if the traffic congestion road traveling determination means determines that the vehicle is traveling on a congested road, the learning data calculation means does not use the output from the monitor means. Therefore, while the vehicle is traveling on a congested road, the learning data is not updated unnecessarily, and the accuracy of the shift control reflecting the shift preference of the driver is suitably maintained.

Further, in the invention according to claim 3, the learning data calculating means travels on the congested road when the congested road traveling determining means determines that the vehicle has left the traveling on the congested road. In this case, the calculation of the learning data is performed based on the latest output monitored by the monitoring means when the operation is being performed. Therefore, after the vehicle has departed from traveling on a congested road, the monitor output at the time of changing the gear position, which was last performed during traveling on a congested road, is effectively applied to the calculation of the learning data, and learning is continuously performed well.

Further, the invention according to claim 4 further comprises a vehicle speed detecting means for detecting a vehicle speed, wherein the congested road traveling determining means determines that the vehicle is traveling on the congested road when the vehicle speed is lower than a predetermined vehicle speed. It is characterized by determining. Therefore, whether the vehicle is traveling on a congested road can be easily determined based on whether the vehicle speed is lower than the predetermined vehicle speed.

[0014] In the invention according to claim 5, the learning data calculation means is configured to determine whether the vehicle speed is equal to or higher than the predetermined vehicle speed.
When the vehicle speed is lower than the predetermined vehicle speed, the learning data is calculated based on the latest output monitored by the monitoring means. Accordingly, it is determined that the vehicle has departed from traveling on a congested road because the vehicle speed has become equal to or higher than the predetermined vehicle speed. The monitor output at the time is effectively applied to the calculation of the learning data, and the learning is satisfactorily continued.

Further, in the invention according to claim 6, the time point for switching the gear position is a time point for upshifting. Therefore, at least one of the accelerator opening and the engine speed at the time of the shift up of the automatic transmission is monitored and output, and the calculation of the learning data is performed based on this output. Then, based on the learning data, learning is performed so as to perform a shift-up reflecting the driver's shift preference, and the shift-up control of the automatic transmission is favorably performed. However, when the vehicle is traveling on a congested road, the learning data is not unnecessarily updated, and thus the accuracy of the shift-up control, which is particularly desired to reflect the driver's shift preference, is preferable. Is maintained.

[0016]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A shift control device for an automatic transmission for a vehicle according to an embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a schematic block diagram showing the main configuration, and FIG. 2 is a schematic configuration diagram showing the entire configuration. First, the overall structure of the transmission control device of the present invention will be described with reference to FIG.

As shown in FIG. 2, the shift control device of the present invention is a diesel engine (hereinafter referred to as engine).
This is a system for automatically changing the rotational driving force of 11 using a gear type transmission (hereinafter referred to as a transmission mechanism) 17 having a clutch 15. Here, the speed change mechanism 17 has seven forward speeds in addition to the reverse speed, and can perform not only automatic shifting but also manual shifting.

The engine 11 is provided with a fuel injection pump (hereinafter, referred to as an injection pump) 21 having a pump input shaft 19 which rotates at half the rotation speed of the engine output shaft 13. An electromagnetic actuator 25 is connected to the control rack 23. Further, a rack position detection sensor 123 for detecting the position of the control rack 23 is also provided. Further, the pump input shaft 19 is provided with an engine speed sensor (engine speed detecting means) 27 for detecting a speed signal of the output shaft 13 of the engine 11 and detecting the engine speed Ne.

An exhaust pipe 12a for guiding exhaust gas extends from the engine 11 via an exhaust manifold 12, and an exhaust brake device 119, which is one of engine auxiliary brakes, is interposed in the exhaust pipe 12a. .
The clutch 15 is provided with an air cylinder 33 as a clutch actuator. This clutch 15
Is connected by bringing the clutch plate 31 into pressure contact with the flywheel 29 by well-known holding means (not shown). That is, when the air cylinder 33 shifts from the non-operation state to the operation state, the holding means operates in the release direction, whereby the clutch 15 changes from the connected state to the disconnected state.

The clutch 15 is provided with a clutch stroke sensor 35 for detecting disconnection and connection information based on the clutch stroke amount. Note that a clutch touch sensor 37 may be used in place of the clutch stroke sensor 35. Transmission mechanism 1
7, a clutch rotation sensor 41 for detecting the rotation speed of the input shaft 39, that is, the rotation speed NCL of the clutch 15.
Is attached.

An air passage 43 is connected to the air cylinder 33. The air cylinder 33 is connected via a check valve 45 to a pair of air tanks 47 as an air source.
49. In the middle of the air passage 43, there are solenoid valves X1, X2 which are duty-controlled to supply working air and function as opening / closing means, and solenoid valves Y1, Y2 which are duty-controlled to open the air cylinder 33 to the atmosphere.
And a three-way solenoid valve W is provided upstream of the solenoid valves X1 and X2.

As shown in FIG.
X2 are connected in parallel with each other and are normally closed. The solenoid valves Y1 and Y2 are also connected in parallel to each other, and are normally open. These solenoid valves X1, X2 and solenoid valves Y1, Y2 are used alternately. The solenoid valve W is controlled to connect the air tanks 47 and 49 to the air passage when the air cylinder 33 is on, and is controlled to open the air passage to the atmosphere when the air cylinder 33 is off.

Here, of the pair of air tanks 47, 49, the air tank 49 is an emergency tank. If the air in the main air tank 47 runs out for some reason, the solenoid valve 55 is opened to release the air from the emergency air tank 49. Supply. For this reason, air sensors 57, 59 that output an ON signal when the internal air pressure falls below a specified value are attached to each of the air tanks 47, 49.

In the air tank 47, an air passage 43 is provided.
A different air passage is connected to the air passage that branches into two systems on the downstream side. The front end of this air passage is connected to a pair of air masters 10 in a braking system (air overhydraulic type) via a pair of solenoid valves MVQ111, 111 that operate in response to a signal from a brake sensor 87 described later.
9, 109.

These air masters 109, 109 include:
A strong brake pedal force sensor (BPS sensor) 106 is attached. The BPS sensor 106 is configured as a diaphragm open / close switch that is turned on when receiving strong brake depression force information corresponding to air pressure when a strong braking force exceeding a set value is required. The change lever 61 is a select lever as a shift operation means for the transmission mechanism 17, and can be moved in a select direction and a direction orthogonal to the select direction, as shown in FIG. It can be moved in a shift direction parallel to the select direction from the position moved in the direction.

The select pattern and shift pattern in each of these directions will be described. First, in the select direction, an N (neutral) range and an R (reverse)
Range and D equivalent to automatic shift mode (auto mode)
Each range of (drive) range is set. In the shift direction, that is, in the M (manual) range corresponding to the manual shift mode (manual mode), the D
A reference position set at a position where the change lever 61 is moved in the orthogonal direction from the (drive) range, that is, a HOLD (hold) range (indicated by HOLD in FIG. 3) is sandwiched between the (drive) range and the UP (shift up) position. DOW
An I-type shift pattern including an N (shift down) position is set.

In such a select pattern and a shift pattern, the change lever 61 located in the N range, the R range, and the D range is held at the position even if the driver's hand leaves after the select operation to the position. On the other hand, if the driver shifts to the UP position or the DOWN position after the M range is selected after the operation is stopped, the change lever 61 automatically returns to the HOLD range when the driver's hand is released after the operation. It is held in that position. The detection of each range and position of the change lever 61 is performed by a gear position selection switch 63, and this detection signal is supplied to a control unit 71 as a shift control means. Then, the gear shift unit 65 is operated according to the detection signal, and the gear in the transmission mechanism 17 is switched according to the select range and the shift position.

The gear shift unit 65 includes a plurality of solenoid valves (only one is shown in FIG. 2) 73 operated by an operation signal from the control unit 71, a select fork and a shift fork in the speed change mechanism 17 (both shown in FIG. 2). And a pair of power cylinders (not shown) for operating the power cylinders (not shown). The power cylinder operates when high-pressure operating air is supplied from the above-described air tanks 47 and 49 via the electromagnetic valve 73. That is, the solenoid valve 7
Each power cylinder is operated by the operation signal given to 3, and the meshing state of the gears of the gear type transmission mechanism 17 is changed in the order of select and shift.

Further, the gear shift unit 65 is provided with a gear position switch 75 as a gear position sensor for detecting each gear position, and a gear position signal from the gear position switch 75 is output to the control unit 71. A vehicle speed sensor 79 for detecting a vehicle speed is attached to an output shaft 77 of the transmission mechanism 17, and an accelerator pedal 81 for detecting an amount of depression (accelerator opening VA) as engine load information. A sensor (accelerator opening detecting means) 85 is provided. The accelerator opening sensor 85 detects a change in resistance according to the amount of depression of the accelerator pedal 81 as a voltage value (VA), and converts this into a digital signal by the A / D converter 83 and outputs the digital signal. FIG. 4 shows a map showing the relationship between the accelerator opening and the voltage value (VA), and the accelerator opening VA is set based on this map.

A brake sensor 87 that outputs a high-level brake signal to the control unit 71 when the brake pedal 69 is depressed is attached to the brake pedal 69. A starter 89 that is engaged with the engine 11 at appropriate times and starts the engine 11 is attached. Starter 8
9 is provided with a starter relay 91, which is also connected to the control unit 71.

Reference numerals 120 and 121 in the figure denote exhaust brake devices 119 which are engine auxiliary brakes, respectively.
An exhaust brake on / off switch and an engine brake auxiliary device on / off switch for switching a compression-release type engine auxiliary brake device (not shown) as an engine brake auxiliary device between an operation standby state and a non-operating state. It is arranged near.

The reference numeral 93 in FIG. 2 indicates an engine control unit provided separately from the control unit 71. This engine control unit 93
Is based on the accelerator opening information VA from the control unit 71 based on information from each sensor.
1 controls the electronic governor 25. That is, when the electronic governor 25 receives a command signal from the engine control unit 93, the control rack 23 operates to perform a fuel increase / decrease operation.
1 is performed to control the increase or decrease of the rotation speed of the output shaft 13.

The control unit 71 comprises a microcomputer (CPU) 95, a memory 97, and an interface 99 as an input / output signal processing circuit. The input port (input interface) 101 of the interface 99 includes the above-mentioned gear position selection switch 63, brake sensor 87, accelerator sensor 85, engine rotation sensor 27, clutch rotation sensor 41, gear position switch 75, vehicle speed sensor 79, clutch. Stroke sensor 35, clutch touch sensor 37 (clutch 1
5 is used in place of the clutch stroke 35 instead of the clutch stroke 35), the air sensors 57 and 59, the BRS sensor 106 that outputs strong brake pedal force information, the exhaust brake on / off switch 120, the engine brake auxiliary device on / off switch 121, and the rack. Position detection sensor 123
Also, a slope start switch 103 described later is connected, and detection information is input to the control unit 71 from each of these sensors.

The hill start switch 103 is for operating a system (hereinafter referred to as AUS) for preventing the vehicle from moving backward when the vehicle starts on an uphill. This AUS is
Air master 1 for a plurality of wheel brakes 107
The supply of air to the valves 09 and 109 is controlled by a pair of solenoid valves MVQ.
This is a system in which a vehicle is started while being controlled via 111,111.

On the other hand, the output port (output interface) 113 is provided with the above-described engine control unit 93, starter relay 91, solenoid valves X1, X2, Y.
1, Y2, W and the solenoid valves 55, 73, 111, etc. are connected respectively. Reference numeral 115 in the figure denotes an air warning lamp which is turned on in response to a detection signal from the air sensors 57, 59 when the air pressure in the air tanks 47, 49 has not reached the set value. Reference numeral 117 denotes wear of the clutch 15. Reference numeral 116 denotes a stop lamp switch that is turned on when the brake pedal 69 is depressed, the clutch warning lamp being turned on in response to a detection signal when the amount exceeds a specified value.

The memory 97 is composed of a read-only ROM in which various flowcharts are written as programs and data, and a writable RAM. In the ROM, in addition to the control program, the duty ratios of the solenoid valves X1, X2, Y1, and Y2 corresponding to the accelerator opening information VA are stored in advance as a map.
Read out appropriate values from this map as appropriate.

Then, the above-mentioned shift speed selection switch 63
Outputs a select signal and a shift signal as a shift signal in response to the operation of the change lever 61. In the ROM, the shift position corresponding to a paired combination of the two signals is stored in advance as a plurality of data maps. ing. Therefore, when the control unit 71 receives the select signal and the shift signal, the CPU 95 selects a predetermined map from the plurality of data maps, calculates an output signal from the map, and furthermore, the output signal is transmitted to the gear shift unit 65.
And the gear is set to the target shift speed corresponding to the shift signal. The gear position signal from the gear position switch 75 is output when the shift is completed, and it is determined whether all the gear position signals corresponding to the select signal and the shift signal have been output. That is, the gear position signal is mainly used to generate a signal indicating whether the meshing is normal.

When a target gear position in the D range exists in the ROM, a shift map for determining an optimum gear position based on the vehicle speed V, the accelerator opening VA, and the engine speed Ne is also provided. A plurality is stored. The shift map is roughly divided into # 1, # 2, and # 3 as shown in the selection map in Table 1 according to the on / off state of the foot brake signal and the exhaust brake signal from the brake sensor 87 and the exhaust brake on / off switch 120. 3
The type has been set. The three types are set in order to improve the running feeling on a downhill. Normally, when no braking is performed, the selection map # 1 is applied.

[0039]

[Table 1]

In general, the required driving torque of a bus or truck changes according to the loading situation or driving situation, and so the ROM stores the loading situation (for example, a vehicle load degree αVL described later), the driving situation, and the like. A plurality of shift maps that are switched automatically according to the situation and the driver's preference, which will be described later, or based on the driver's intention are also stored. For example, there are three types of shift maps according to the loading status and the driving status, such as a fuel economy-oriented economy mode, a normal mode, and an acceleration-oriented power mode. These are the above-described # 1, # 2, and #, respectively. 3 is provided for each shift map. That is, the ROM stores, for example, nine types of shift maps in terms of the relationship between the vehicle speed V and the accelerator opening VA. FIGS. 5 to 13 show these nine types of shift maps, and FIGS.
FIGS. 8 to 10 show shift maps # 1, # 2, and # 3 in the economy mode. FIGS.
2 and 3 are shown in FIGS.
Shows shift maps of # 1, # 2, and # 3 in the power mode. That is, the CPU 95 appropriately selects a shift map according to the situation from the shift map group. In these shift maps, shift-up shift characteristics are indicated by solid lines, and shift-down shift characteristics are indicated by broken lines.

By the way, the basic operation of the above-mentioned automatic transmission is known, and the detailed description thereof is omitted here.
This automatic transmission operates, for example, in the same manner as that disclosed in Japanese Utility Model Laid-Open No. 2-49663. Next, control contents in the control unit 71 as a main part of the present invention will be described.

Referring to FIG. 1, the control unit 71 of the automatic transmission selects a suitable shift map from the above-mentioned shift map group, and outputs the vehicle speed information V from the vehicle speed sensor 79 and the accelerator pedal from the accelerator opening sensor 89. A target gear position setting means 3 for setting a target gear position from the selected map based on the opening degree information VA, and an optimum gear position determining means 1 capable of correcting the target gear position by reflecting the driver's intention are provided. ing.

Further, the target gear position setting means 3 includes a storage means 3A for storing a shift map and a learning expression selecting means 3B.
In addition to the nine shift map groups shown in FIG. 5 to FIG.
The downshift restriction map (see FIG. 24) for restricting the -4 downshift and the 4-3 downshift is selected with each selection map #.
It is stored for each mode of # 1, # 2, and # 3. Therefore,
The target shift speed setting means 3 is configured as a map-type storage means.

The learning expression selecting means 3B of the target gear position setting means 3 determines the driver's speed based on the vehicle speed information V, the engine speed information Ne, the detection signal from the gear position selection switch 63, the accelerator opening information VA, and the like. It has a function of performing learning that reflects driving preferences and selecting an optimal shift map from the above modes according to the learning result.
The driver's driving preference refers to, for example, a driving method of whether the driver desires an early shift-up with an emphasis on fuel efficiency or a driving with an emphasis on acceleration. Therefore, the learning expression selecting means 3B learns the driving operation of the driver by using the driving operation information by the driver as input information, and optimally selects from the plurality of shift maps in the storage means 3A according to the driver's preference and personality. The shift map of the mode (the economy mode emphasizing fuel efficiency, the normal mode, or the power mode emphasizing acceleration) is selected.

More specifically, the learning expression selecting means 3B is provided with the function shown in FIG.
21 is provided with a plurality of neural networks as shown in FIG. 21. When various kinds of driving operation information are input to these neural networks, arithmetic processing including learning is performed in the neural networks, and thereby the driver An output signal (judgment output) optimal for the user's preference is output. Then, a shift map of a mode corresponding to an output signal from each neural network is selected, and a target shift speed corresponding to the vehicle speed V and the accelerator opening VA is set based on the shift map.

The optimum gear position determining means 1 determines the driving state of the vehicle and the driver's intention by using fuzzy logic, and corrects the target gear position set by the target gear position setting means 3. It is constituted as a gear position determining means. The fuzzy type optimal gear position determining means 1 estimates the traveling state of the vehicle based on fuzzy rules set in advance by experiments and the like using vehicle information having vehicle load information as a parameter, thereby inferring the intention of the driver. However, the vehicle load information includes a difference between the acceleration α0 when the vehicle accelerates on a straight flat road with the vehicle empty and the actual acceleration α when the vehicle actually accelerates (= vehicle load αVL).
Is used as a parameter.

For this reason, as shown in FIG. 1, the control unit 71 is provided with a vehicle load degree calculating means 2 for calculating the vehicle load degree αVL. The vehicle load degree calculating means 2 is provided with an engine torque calculating means 4, a driving force calculating means 5, an air resistance calculating means 6, an acceleration calculating means 7 equivalent to a straight flat road vehicle, and a subtracting means 8. The engine torque calculation means 4 calculates the engine torque Te from the position information SRC of the control rack 23 supplied from the rack position detection sensor 123 and the engine speed information Ne. As in the case of No. 3, it is configured as a storage means of a map format.

As described above, the engine torque Te is obtained from the position information SRC of the control rack 23 and the engine speed information Ne based on a preset map (not shown). Since it differs depending on the use of the compression-release type engine auxiliary brake, in a situation where the exhaust brake or the compression-release type engine auxiliary brake is used, a map (not shown) separately set according to this situation is used.

The driving force calculating means 5 is provided with the engine torque information Te obtained by the engine torque calculating means 4.
Is calculated on the basis of the driving force F. The calculation of the driving force F is performed by, for example, the following equation. F = (Te · it · if · η) / R where it is the gear ratio of the shift speed, if is the final reduction gear ratio (differential gear ratio), η is the power transmission efficiency, and R is the tire radius.

The air resistance calculating means 6 calculates the air resistance Rl as the running resistance of the vehicle from the actual vehicle speed information V, and calculates it by the following equation. Rl = λ · A · V ² where λ is the air resistance coefficient, A is the front projected area of the vehicle, V
Is the actual vehicle speed. Next, the acceleration calculating means 7 (hereinafter, referred to as acceleration calculating means) 7 equivalent to a straight flat road vehicle will be described. The acceleration calculating means 7 includes the driving force information F calculated by the driving force calculating means 5 and the air resistance. Based on the air resistance coefficient information Rl calculated by the calculation means 6, the acceleration α0 when the vehicle accelerates on a straight flat road in an empty state, that is, the acceleration equivalent to a straight flat road empty vehicle is calculated. The acceleration α0 corresponding to the straight flat road vehicle is calculated by the following equation using the driving force F of the vehicle.

Α0 = g · {F− (μW0 + R1)} / (W0 + Wr) where g is the gravitational acceleration, μ is the road surface friction coefficient, W0 is the weight of the empty vehicle, and Wr is the weight of the rotating part. Then, the subtraction means 8 calculates the vehicle load degree information αVL by the following equation based on the acceleration information α0 corresponding to the straight flat road vehicle calculated by the acceleration calculation means 7 and the actual acceleration information α from the clutch rotation sensor 41. The vehicle load information αVL corresponds to the weight of the vehicle and the gradient resistance of the vehicle.

ΑVL = α0−α That is, if αVL> 0, the vehicle load is heavy, and if αVL <0, the vehicle load is light. Then, it is determined from the magnitude of the value of αVL how heavy (or light) the vehicle load is. FIG. 14 shows an example in which, for example, a vehicle load degree αVL is calculated by simulation on a flat road. Here, the horizontal axis represents the total vehicle weight gvw (gross vehicle weight), and the vertical axis represents the vehicle load αVL.

When the vehicle load degree αVL is calculated by the vehicle load degree calculation means 2 in this manner, the fuzzy type optimum gear position determination means 1 adds the accelerator opening information VA and the accelerator opening information VA to the vehicle load degree αVL. The target shift speed setting means 3 fetches each information such as the opening degree change information ΔVA, the vehicle speed information V, the engine speed Ne, the brake information, and the current shift speed information.
Correction is performed for the target gear set by. As the brake information, in addition to the operation information of the foot brake input from the brake sensor 87, the operation information of the exhaust brake, the compression-release type engine auxiliary brake, and the like is also input. Is corrected in consideration of the above information.

More specifically, the optimum gear position determining means 1 quantifies each information by a fuzzy inference method using the min-max composite centroid method, and quantifies these quantified values into a predetermined plurality of predetermined fuzzy values. The target shift speed is corrected in light of the rules. Note that the content of the fuzzy inference has no direct relation to the present invention, and a detailed description thereof will be omitted here.

As described above, in the shift control device for an automatic transmission for a vehicle according to one embodiment of the present invention, the target shift speed according to the driver's preference set using the neural network is finally determined by fuzzy operation. The optimum gear is determined by the control, and the optimum gear is determined by the control unit 71 in FIG.
The determination is made according to the flowchart of the main routine as shown in FIG. Hereinafter, the procedure for determining the automatic shift speed, that is, the optimum shift speed in the D range will be described in detail with reference to FIG.

First, in step S10 of FIG.
As described above, the engine torque Te is calculated by the engine torque calculating means 4. Then, step S12
Then, the driving force F of the vehicle is calculated by the driving force calculation means 5,
In the next step S14, the air resistance calculating means 6 calculates the air resistance Rl of the vehicle. In step S16, the straight flat road empty vehicle equivalent acceleration calculating means 7 calculates the straight flat road empty vehicle equivalent acceleration α0 from the driving force information F calculated in step S12 and the air resistance information Rl calculated in step S14.

Then, in step S18, step S
The vehicle load level information αVL is calculated based on the acceleration α0 corresponding to the straight flat road empty vehicle calculated in step 16 and the actual acceleration information α from the clutch rotation sensor 41. Next step S19
Then, the learning type selection means 3B of the target gear position setting means 3 performs the learning control of the shift according to the driver's preference, and selects the optimum shift map from the storage means 3A. Hereinafter, the shift learning control according to the driver's preference will be described in detail with reference to the flowchart of FIG. Here, since the effect of the learning is great, the learning of upshifting is 2-3 upshifting,
Four upshifts are targeted for learning, and are also targeted for driving on a flat road where the driver's preference is easily dispersed.

First, in step S50 in FIG. 16, data necessary for learning the shift according to the driver's preference is calculated (learning data calculation means). The learning data includes the following. (1) 2-3 accelerator opening average AVA (23) (2) 2-3 standard deviation SVA (23) (3) 3-4 accelerator opening average AVA (34) (4) 3-4 standard deviation SVA ( 34) (5) 2-3 Engine rotation average ANe (23) (6) 3-4 Engine rotation average ANe (34) (7) HOLD range use frequency FH during deceleration (8) M range use frequency FMD during deceleration Referring to FIG. 17, there is shown a flowchart showing a routine for calculating the average accelerator opening AVA, the standard deviation SVA, and the average engine speed ANe, and AVA (23) and AVA () listed in the above (1) to (6). 34), SVA (23),
SVA (34), ANe (23), and ANe (34) are calculated based on the flowchart of FIG. Hereinafter, based on FIG. 17, AVA (23), AVA (34), SVA (23),
The calculation procedure of SVA (34), ANe (23), ANe (34) will be described.

First, in step S70 in FIG. 17, the vehicle speed V is equal to or higher than a predetermined vehicle speed V2 (for example, 20 km / h) (V ≧ V
2) is determined (congested road traveling determination means). This means that the vehicle is traveling on a congested road at a low vehicle speed less than the predetermined vehicle speed V2. Here, a threshold value adopted as the predetermined vehicle speed V2 (for example, 2
0 km / h) is the minimum vehicle speed at which the vehicle can normally be regarded as not traveling on a congested road. The judgment result is true (Yes)
If the vehicle speed V is equal to or higher than the predetermined vehicle speed V2, it can be determined that the vehicle is not traveling on a congested road, and in this case, the process proceeds to step S71.

In step S71, the vehicle speed V becomes equal to the predetermined vehicle speed V.
It is determined whether or not it is immediately after two or more. If the determination result is false, the process proceeds to step S78, where AVA (23), A
VA (34), SVA (23), SVA (34), ANe (23), ANe
The calculation of (34) is performed. AVA (23), AVA (34), SVA (2
The calculation procedure of 3), SVA (34), ANe (23), ANe (34) is as follows, and will be described in order. 1) 2-3 accelerator opening average AVA (23): The 2-3 accelerator opening average AVA (23) is monitored by the control unit 71 (monitoring means) from the second gear to the third gear in the D range. This is the average value of the accelerator opening VA at the start of the shift (change of the gear position), and the average of the past 10 times on a flat road is obtained from the following equation so as to obtain sufficient accuracy.

AVA (23) = (VA (23) 0 + VA (23) 1 + ·
+ VA (23) 9) / 10 2) 2-3 standard deviation SVA (23): 2-3 standard deviation SVA
(23) is a standard deviation (3σ) of the accelerator opening VA at the time of shifting from the second gear to the third gear in the D range, and the standard deviation of the past 10 times on a flat road is obtained from the following equation. .

SVA (23) = 3 · ((1/10) · Σ (VA
(23) i-AVA (23)) ² ) ^1/2 , i = 0 to 9 However, in this case, in order to facilitate the calculation processing in the CPU 95, the actual value is replaced with SVA (23) instead of (SVA (23)). SVA
The square of (23)), that is, the following equation is used for convenience.

(SVA (23)) ² = 9 · (1/10) · Σ (V
A (23) i-AVA (23)) ² , i = 0 to 9 3) 3-4 accelerator opening average AVA (34): 3-4 accelerator opening average AVA (34) is also control unit 7
This is the average value of the accelerator opening VA at the start of shifting from the third gear to the fourth gear in the D range monitored by 1. The average of the past 10 times on a flat road is obtained from the following equation.

AVA (34) = (VA (34) 0 + VA (34) 1 + ·
+ VA (34) 9) / 10 4) 3-4 standard deviation SVA (34): 3-4 standard deviation SVA
(34) is a standard deviation (3σ) of the accelerator opening VA at the time of shifting from the third gear to the fourth gear in the D range, and the standard deviation of the past 10 times on a flat road is obtained from the following equation. .

SVA (34) = 3 · ((1/10) · Σ (VA
(34) i-AVA (34)) ² ) ^1/2 , i = 0 to 9 However, as in the case of the above-mentioned SVA (23), the actual value is (SVA) instead of SVA (23). The square of (34)), that is, the following equation is used for convenience. (SVA (34)) ² = 9 · (1/10) · Σ (VA (34) i−A
VA (34)) ² , i = 0 to 9 5) 2-3 engine rotation average ANe (23): 2-3 engine rotation average ANe (23) is also the control unit 7
The average value of the engine speed at the time of shifting from the 2nd gear to the 3rd gear by manual operation in the M range monitored by 1 is obtained. Specifically, the engine speed Ne immediately before the start of the shift
From the average value of

ANe (23) = (Ne (23) 0 + Ne (23) 1+...
+ Ne (23) 4) / 5 6) 3-4 engine rotation average ANe (34): 3-4 engine rotation average ANe (34) is also the control unit 7
The average value of the engine speed at the time of shifting from the third gear to the fourth gear by manual operation in the M range monitored by 1 is also obtained. Similarly to the above, it is obtained from the average value of the engine speed Ne immediately before the start of the shift.

ANe (34) = (Ne (34) 0 + Ne (34) 1+...
+ Ne (34) 4) / 5 The result of determination in step S71 is true, and the vehicle speed V is equal to the predetermined vehicle speed V
If it is immediately after the number becomes 2 or more, then step S7
Proceed to 2. In step S72, it is determined whether or not upshifting in the D range has been performed at a stage where the determination result in step S70 is true and the vehicle speed V is lower than the predetermined vehicle speed V2 (V <V2) before the vehicle speed V becomes equal to or higher than the predetermined vehicle speed V2. Determine. If the determination result is true, the process proceeds to step S73.

In step S73, the vehicle speed V becomes equal to the predetermined vehicle speed V
The accelerator opening VA at the time of the latest shift-up in the D range that was last executed in a stage less than 2 is adopted as effective learning data. Then, the process proceeds to step S78. On the other hand, if the determination result in step S72 is false (No), and the shift-up in the D range is not performed at a stage lower than the predetermined vehicle speed V2, the process proceeds to step S74.

In step S74, the vehicle speed V becomes equal to the predetermined vehicle speed V
At a stage where the vehicle speed is lower than the predetermined vehicle speed V2 before reaching 2 or more, it is determined whether or not the manual upshift in the M range has been performed. If the determination result is true, then step S
Proceed to 76. In step S76, the vehicle speed V becomes the predetermined vehicle speed V
The engine speed Ne at the time of the latest manual shift-up in the M range last performed in the stage less than 2 is adopted as effective learning data. And step S7
Proceed to 8.

If the decision result in the step S74 is false, that is, if the vehicle speed V is lower than the predetermined vehicle speed V2, the upshift is not performed in the D range (step S7).
2) In the case where the manual shift-up in the M range is not performed (step S74), for example, after the vehicle starts, the vehicle speed V reaches the predetermined vehicle speed V2 or more at a stretch while keeping the second gear. In such a case, the routine is terminated without doing anything. That is, in this case, the calculation of the learning data as performed in step S78 is not performed.

Incidentally, the result of the determination in step S70 is false, that is, the vehicle speed V is still the predetermined vehicle speed V2 (for example,
Even if the speed has not reached 20 km / h), the routine is terminated without doing anything. That is, in a situation where the vehicle speed V has not yet reached the predetermined vehicle speed V2 and it can be considered that the vehicle is traveling on a congested road, learning of the driver's preference is not performed. Normally, when a vehicle is traveling on a congested road, upshifting and downshifting are often performed according to the traffic situation rather than the driver's preference and intention, and thus the driver's preference is good. In the situation where the learning data is not reflected, the adoption of the learning data is canceled.

Table 2 briefly shows, for example, the relationship between the time change of the vehicle speed V in the 2-3 upshift in the D range and the adoption / non-use of learning data (here, the accelerator opening VA is shown as an example). It is. As shown in the table, when the vehicle speed V has not yet reached the predetermined vehicle speed V2 (for example, 20 km / h), the learning data is rejected, and the vehicle speed V becomes the predetermined vehicle speed V2.
2 (for example, 20km / h)
It is determined that the traffic congestion traveling has ended and the vehicle has shifted to the normal traveling, and the learning data at the time of the immediately preceding shift-up is adopted as valid data.

As described above, the reason why the learning data at the time of upshifting immediately before the vehicle speed V becomes equal to or higher than the predetermined vehicle speed V2 is adopted as valid data is that the shift from the second gear to the third gear has already been performed. This is because the driver's shift preference at the time of acceleration appears in the accelerator opening VA at the time. As for the M range, similarly to the case of the D range, when the vehicle speed V becomes equal to or higher than the predetermined vehicle speed V2, the learning data at the time of immediately preceding upshifting is adopted as effective data.
At this time, the driver's preference for shifting during acceleration has already appeared in the engine speed Ne during shifting from the second gear to the third gear.

[0074]

[Table 2]

That is, in this learning, when the vehicle is traveling on a congested road where the vehicle speed V has not yet reached the predetermined vehicle speed V2 (for example, 20 km / h), the upshift or downshift is not actually performed. Even if it has been performed, these shifts are processed as if they were not performed, and the learning data is not updated. Also, the HOLD of (7)
Range use frequency FH and M range use frequency FMD of (8)
Is calculated based on the flowchart of the FH and FMD calculation routine shown in FIG. Hereinafter, the calculation procedure of the HOLD range use frequency FH and the M range use frequency FMD will be described with reference to FIG.

The HOLD range use frequency FH and the M range use frequency FMD are defined as the average values of the HOLD range use frequency FHi and the M range use frequency FMDi, respectively. Therefore, first, in step S80 of FIG.
The OLD range use frequency FHi and the M range use frequency FMDi are calculated. When the vehicle is performing a predetermined deceleration operation, the HOLD range use frequency FHi is set such that the change lever 61 moves from the D range or the UP position or the DOWN position to the target shift speed switching information in the normal D range shift down mode. The calculation is performed based on the frequency of the number of times the gear is switched to the HOLD range and the gear is held at the current gear.

More specifically, the HOLD range usage frequency FHi
When the vehicle speed V is equal to or higher than a predetermined vehicle speed V1 (for example, 30 km / h), the accelerator pedal 81 is released and the accelerator opening V
The vehicle speed V gradually decreases after A is set to 0%, and is performed during a predetermined operation state until the engine speed Ne becomes the predetermined engine speed Ne1 and the clutch 15 is automatically disengaged. The number of downshifts NSi and H
It is calculated from the following equation based on the number NHi of times when the downshift is canceled using the OLD range. The shift-down mode in the normal D range indicates a mode using a map other than the above-described shift-down restriction map (hereinafter, referred to as a shift-down enabled mode).

FHi = (number of cancellations NHi) / (total number of downshifts NSi of the fifth speed or lower gear NSi), i = 0 to 4 where the predetermined engine speed Ne1 is
9 is operated and the foot brake is used, for example, 600 rpm (Ne1 = 600 rpm). When the foot brake is not used, the value is smaller than 600 rpm, for example, 450 rpm (Ne1 = 450 rpm). . At this time, the vehicle speed V corresponding to Ne1 = 600 rpm is:
For each shift speed, for example, the speed is 20 km / h at the fifth speed, 14 km / h at the fourth speed, and 8.5 km / h at the third speed.

On the other hand, the M-range use frequency FMDi at the time of downshifting is such that the accelerator pedal 81 is released when the vehicle speed V is equal to or higher than a predetermined vehicle speed V1 (for example, 30 km / h), and the accelerator opening VA is set to 0%. The vehicle speed V gradually decreases,
The total number of downshifts NDi (the above total shift) at the fifth gear and lower is actually performed during a predetermined operation state until the engine speed Ne reaches the predetermined engine speed Ne1 and the clutch 15 is automatically disengaged. This is calculated from the following equation based on the number of downshifts NSi and including the manual operation using the M range and the number of times NMDi in which manual downshifts are performed using the M range. Here, the calculation of the M range use frequency FMDi is based on the total number of downshifts and the number of NDi NMDi
Is set on the basis of the detection signal from the speed selection switch 63, so that there is no other way to determine the output frequency of the shift state switching signal.

FMDi = NMDi / NDi, i = 0 to 4 In the next step S82, it is determined whether or not the downshift mode is a mode using the downshift restriction map (hereinafter referred to as a downshift no mode). . If the result of the determination is true and the downshift mode is the downshift no mode, the process proceeds to step S84.

In step S84, step S80 is performed.
The value 1 is set to the HOLD range use frequency FHi calculated in step irrespective of the above calculation result. Details will be described later,
In the case where the downshift mode is the downshift no mode, 5-4 downshifts of the fifth gear or lower,
Since the three downshifts are canceled in the region of low vehicle speed and small accelerator opening (see FIG. 24), the use frequency FHi becomes extremely close to the value 1 in light of the above equation. Therefore, in this step S84, the value 1 is set again to the HOLD range use frequency FHi to clarify that the HOLD range use frequency is high. Thereby, the learning by the learning expression selecting means 3B, that is, the learning of the driver's preference is made more suitable and accurate.

On the other hand, if the decision result in the step S82 is false,
If the downshift mode is not the downshift non-permission mode but the normal downshift mode, the process proceeds to step S86. In step S86, it is determined whether or not the shift-down mode has been performed by manual operation in the M range in the shift-down enabled mode. If the result of the determination is true and it is determined that the downshift by manual operation has been performed, the process proceeds to step S88, and the HOLD range use frequency FHi
Is set to the value 0. In other words, in the case where the downshift of the fifth gear or less in the M range by manual operation has been performed even once, the driver uses the HOLD range in order to cancel the downshift in the D range. In this case, it can be determined that the manual operation is actively performed. Therefore, here, the value 0 is set to the HOLD range use frequency FHi, and this is not used as an input parameter, and it is made clear that the driver intends to perform a manual operation.

By the way, the determination result in step S86 is false, and in step S82, it is determined that the downshift mode is the downshift enabled mode, and that it is determined that the downshift by the manual operation at the fifth gear or lower has not been performed. In this case, the value of the HOLD range use frequency FHi calculated in step S80 is applied as it is, and the process proceeds to step S90.

In step S90, the determination result in step S82 is true, and the execution of step S84 causes the HO
Whether the LD range use frequency FHi is the value 1, or whether the determination result in step S82 is false and the determination result in step S86 is false, and there is no downshift by manual operation of the fifth gear or lower. Is determined. If the result of the determination is true, that is, if it is determined in step S88 that the value 0 has not been set for the use frequency FHi, the process proceeds to step S92.

In step S92, the value 0 is set to the M range use frequency FMDi this time. That is, step S90
Is true and the use frequency FHi is not the value 0, the driver wants to cancel the downshift using the HOLD range and can judge that he is reluctant to shift by manual operation. Therefore, with respect to one M range use frequency FMDi, the learning result in the learning formula selection means 3B is set to a value 0 so as to make the result clearer and more accurate, and this is not used as an input parameter.

On the other hand, if the result of the determination in step S90 is false, the value of the use frequency FMDi calculated in step S80 is applied as it is, and the flow advances to step S94. In step S94, the HO is finally determined based on the use frequency FHi and the use frequency FMDi set as described above.
The LD range use frequency FH and the M range use frequency FMD are obtained. More specifically, the frequency of use FH and frequency of use FMD are calculated from the following equations, respectively, using the past 5 of frequency of use FHi and frequency of use FMDi.
Determine by taking the average of the times.

FH = (FH0 + FH1 +... + FH4) / 5 FMD = (FMD0 + FMD1 +... + FMD4) / 5 By taking the HOLD range use frequency FH and the M range use frequency FMD finally, the learning can be stabilized.

Returning to FIG. 16, in the next step S52,
For the reason described above, it is determined whether or not the vehicle is traveling on a flat road. Here, it is determined whether or not the vehicle load degree αVL is within a predetermined range (near 0 value) set for each gear. By determining whether or not the vehicle is traveling on a flat road as described above, learning can be performed only on a flat road on which the driver's preference is conspicuous.

If the decision result in the step S52 is false (No),
That is, when it is determined that the vehicle load degree αVL is out of the predetermined range and the vehicle is not traveling on a flat road, the process proceeds to step S64 without learning about upshifting. On the other hand, if the determination result of step S52 is true (Ye
s), that is, when it is determined that the vehicle load αVL is within the predetermined range and the vehicle is traveling on a flat road, the process proceeds to step S54.

In step S54, it is determined whether or not 2-3 upshifts or 3-4 upshifts have been performed 10 times continuously in the D range. If the determination result is true, it can be determined that almost only the D range is used at the time of upshifting and the use frequency of the M range is extremely low. In this case, the process proceeds to step S56. In step S56, the upshift preference is learned based on the upshift by the D range operation, and an output necessary for selecting the shift map, that is, a judgment output is set. That is,
Here, since the use frequency of the M range is low, the learning based on the automatic shift is performed without learning the preference based on the use of the M range. More specifically, the learning based on the back propagation learning method and the calculation of the judgment output are performed by the first neural network shown in FIG. Hereinafter, processing in the first neural network will be described.

The input layer of the first neural network shown in FIG.
-3 average accelerator opening AVA (23), 2-3 standard deviation SV
A (23), 3-4 accelerator opening average AVA (34) and 3-4
Each input value I1, I2, I3, I4, I of the standard deviation SVA (34)
5 is entered. Here, the shift map information selected last time, that is, the previous determination output, has a character as a reference value for the current learning. The input values of I1 to I5 are normalized by the following equation to obtain Ii '.
Are input to the three intermediate layers.

Ii '= (Ii-Iimin) / (Iimax-Iimi
n), i = 1 to 5 Here, Iimin is the minimum value of Ii, that is, the minimum value of each input value of I1 to I5, and Iimax is the maximum value of Ii, that is, I1
To I5 are the maximum values of the input values. Then, upon input to the three intermediate layers, different coupling coefficients Wij (i = 1 to 5, j = 1 to 3) are added to the respective intermediate layer input values Ii '. That is, each of the input values Ii ′ input from the five input layers to the three intermediate layers is set to 1 by an experiment or the like in advance.
Five coupling coefficients Wij (W11, W12, W13, W2)
1, W22... W53) are integrated.

Then, output values O1, O2, and O3 calculated by the following sigmoid function are output from the three intermediate layers. Oj = 1 / (1 + exp (-Xj)), j = 1 to 3, where Xj = W1j.I1 '+ W2j.I2' +... + W5j.
I5'-θj, j = 1 to 3 Here, θj (j = 1 to 3) is a predetermined threshold value set in advance by an experiment or the like.

The output values O1, O2, and O3 are also integrated with a predetermined coupling coefficient Wj4 (j = 1 to 3) and input to the output layer. Output O4 is output. O4 = (1 / (1 + exp (-Y4))). (Omax-Om
in) + Omin where Y4 = W14.O1 + W24.O2 + W34.O3-.theta.4 where Omax is the maximum value of the judgment output O4 and Omin is the minimum value of the judgment output O4. Θ4 is a predetermined threshold value set in advance by an experiment or the like.

The above Iimin, Iimax, Omin, Om
Detailed descriptions of ax, Wij, Wj4, θj, and θ4 are omitted here. However, among the input values Ii, the input value I1 and the judgment output value O4 corresponding to the previously selected shift map information take values between the values 1 to 3 as described later. The value I1min and the minimum value Omin of the output value O4 become the value 1, while the maximum value I1max of the input value I1 and the maximum value Omax of the output value O4 become the value 3
Becomes

In this way, when the frequency of using the M range at the time of shifting up by the driver is small, learning is performed based on the shifting up by the automatic shifting in the D range, instead of the shifting up by the manual operation in the M range. Thus, the output for selecting the shift map, that is, the judgment output O4 is set satisfactorily and stably. On the other hand, if the result of the determination in step S54 is false, the frequency of use of the M range is relatively high at the time of upshifting, and the driver is not satisfied with only the D range but frequently uses the manual shift in the M range. In this case, the process proceeds to step S58.

In this step S58, it is determined whether or not 2-3 upshifts or 3-4 upshifts by manual operation in the M range have been performed five times in succession. If the determination result is true, the process proceeds to step S60. In step S60, the preference of the upshift is learned based on the M range operation, that is, the upshift by the manual operation, and the output for selecting the shift map, that is, the judgment output is set. More specifically, the learning and the calculation of the judgment output are performed by a second neural network provided separately from the first neural network as shown in FIG. Hereinafter, processing in the second neural network will be described.

The input layer of the second neural network shown in FIG.
The input values I′1, I′2, I′3 of the −3 engine rotation average ANe (23) and the 3-4 engine rotation average ANe (34) are input. Here, similarly to the above, the shift map information selected last time is the previous determination output, and has the character as the reference value for the current learning. Then, the input values of I1 to I5 are normalized by the following equation to be I'i ', and are input to three intermediate layers.

Then, the output values O'1,
O'2 and O'3 are obtained, and the judgment output O'4 is finally derived. The arithmetic processing in the second neural network is the same as the arithmetic processing in the first neural network. Here, detailed description is omitted. In this way, if the frequency of using the M range at the time of upshifting is high, learning is performed based on manual upshifting by operating the M range, and the shift map according to the driver's preference is determined. The output O'4 will be set appropriately.
In other words, according to the operating condition of the M range by the driver,
The output for selecting which of the shift maps of the economy mode, the standard mode, and the power mode is set.

As described above, when the judgment outputs O4 and O'4 relating to the upshift are set by the processing of the first neural network or the second neural network, the process proceeds to step S62. Step S5
If the determination result of No. 8 is false, the process proceeds to step S62 without going through the first and second neural networks.

In step S62, the judgment outputs O4,
A shift map is selected according to O'4. That is, here, any one of the shift map among the economy mode, the standard mode, and the power mode is selected. In particular,
The shift map is selected based on a graph showing the relationship between the judgment outputs O4, O'4 and the selection map as shown in FIG. For example, when the judgment output O4, O'4 value from the first neural network or the second neural network is 1 or more and less than 1.5 (1≤O4, O'4 <1.5), the shift map of the economy mode is Selected, and the judgment output O4, O'4 values are 1.5 or more and less than 2.5 (1.5 ≦ O
(4, O'4 <2.5), the standard mode shift map is selected, and the value of the judgment output O4, O'4 is 2.5 or more and 3
If less than (2.5 ≦ O4, O′4 <3), the power mode shift map is selected.

Here, the selection map of the economy mode is as follows.
As described above, in the shift map focusing on fuel economy, the shift timing at each shift speed is set to the lower vehicle speed side in the standard mode having the same shift timing as the normal D range. The power mode selection map is a shift map that emphasizes acceleration, and the shift-up timing of each gear is set to the higher vehicle speed side in the standard mode. That is, when the judgment outputs O4 and O'4 change due to the learning, the shift pattern in the D range which is the automatic shift range is appropriately switched to the shift pattern according to the driver's preference.

When the result of the determination in step S58 is false, the previous values are applied as they are because the determination outputs O4 and O'4 are not newly set. That is,
In this case, the currently adopted shift map is continuously used. After the next step S64,
This is a step of learning the driver's preference at the time of downshifting.

In step S64, the vehicle speed V becomes equal to the predetermined vehicle speed V.
1 (for example, 30 km / h)
1 is released (OFF) and the accelerator opening VA is 0
%, The vehicle speed V gradually decreases, the engine speed Ne becomes the predetermined engine speed Ne1, and the clutch 1
It is determined whether or not 5 has been automatically disengaged. In addition,
The details of the value of the predetermined engine speed Ne1 are as described above, and the description is omitted here.

If the result of the determination in step S64 is true, and it is determined that the clutch 15 has been automatically disengaged after the accelerator opening VA has been set to 0%, that is, if the shift has been determined to be in the downshift mode, Is the next step S6
Proceed to 6. In step S66, the shift down preference is determined. That is, the learning of the downshift preference is performed according to the driver's use condition of the M range, and the judgment output necessary for selecting the shift map is set. More specifically, learning and calculation of the judgment output are performed by the third neural network shown in FIG. Hereinafter, processing in the third neural network will be described.

The input layer of the third neural network shown in FIG.
The input values I "1, I" 2, I "3 of the OLD range use frequency FH and the M range use frequency FMD are input, and the shift map information selected last time is the reference value of the current learning. And these I "1,
The input values of I "2 and I" 3 are normalized by the following equation to obtain I "i '
Are input to the three intermediate layers.

Then, the output values O "1, O" 2,
O "3 is obtained, and the decision output O" 4 is finally derived. The arithmetic processing in the third neural network is the same as the arithmetic processing in the first and second neural networks. Here, the description is omitted. However, here, the input value I "1 and the judgment output value O" 4 corresponding to the previously selected shift map information among the input values I "i are values between values 0 and 1 as described later. Therefore, the minimum value I "1min of the input value I" 1 and the output value O "
The minimum value O "min of 4 has a value of 0, while the maximum value I" 1max of the input value I "1 and the maximum value O" max of the output value O "4 have a value of 1.

In this manner, the learning concerning the downshift is performed based on the use condition of the M range at the time of the downshift, and the judgment output O "4 for selecting the shift map according to the driver's preference is set. That is, here, 5-4 downshift and 4-3
The output is set as to whether or not to select the downshift restriction map corresponding to the downshift non-permission mode for restricting downshifting. Here, as described above, the shift-down regulation map is provided for each of the economy mode, standard mode, and power mode selection maps # 1, # 2, and # 3.

FIG. 24 exemplifies a downshift restriction map corresponding to the selection map # 1 in the economy mode as a representative example. As shown in FIG. 24, in the downshift restriction map, the accelerator opening VA is small. In the case of, the shift timing of the 5-4 downshift and the 4-3 downshift below the fifth gear shift to the lower vehicle speed side.
That is, the timing of the 5-4 downshift and the timing of the 4-3 downshift are the same as the timing of the 3-2 downshift. Therefore, in this downshift restriction map, the fifth gear or the fourth gear unless the vehicle speed V becomes extremely small.
The gear is maintained, and the 5-4 downshift and the 4-3 downshift are not performed.

In step S68, it is determined whether downshifting is possible or not according to the determination output O "4. In the case of the downshiftable mode, the normal economy mode, the standard mode, and the normal mode selected in step S62 are selected.
Each of the selection maps # 1, # 2, and # 3 in the power mode is applied as it is.
One of the downshift restriction maps provided for each mode is selected and applied. More specifically, the shift down availability is set in accordance with the determination output O "4 based on a graph showing the relationship between the determination output O" 4 and the shift down availability as shown in FIG. A map is appropriately selected. That is, if the value of the judgment output O "4 is equal to or more than 0 and less than 0.5 (0≤O" 4 <0.5), it is determined that there is no downshift, and the downshift restriction map is selected. If the four values are 0.5 or more and 1 or less (0.5 ≦ O ”4 ≦ 1), the shift down is possible, and the shift map of the normal economy mode, the standard mode, and the power mode is selected. Become.

For example, when the driver does not use the exhaust brake during deceleration and frequently shifts down manually in the M mode, that is, when the M range use frequency FMD is large, The shift map of the normal economy mode, the standard mode, and the power mode selected by the upshift learning, that is, the selection map # 1 as the downshiftable mode is applied as it is. At this time, in the D range, the 5-4 and 4-3 downshifts are sequentially performed as the vehicle decelerates, whereby the engine brake suitably operates.

On the other hand, during deceleration, the driver dislikes downshifting and often uses the HOLD range.
When the HOLD range use frequency FH is large, that is, when the driver does not like the downshift shock or the like, the downshift restriction map is selected as the downshift no mode. At this time, in the D range, the fifth speed or the fourth speed is maintained irrespective of the decrease in the vehicle speed V, whereby discomfort such as a shift shock is suitably prevented.

When the result of the determination in step S64 is false and the vehicle speed V is equal to or higher than the predetermined vehicle speed V1 (for example, 30 km / h), the accelerator pedal 81 is released (OFF), and thereafter the engine speed Ne is reduced. In a situation in which the clutch 15 does not automatically disengage due to the predetermined engine speed Ne1, it can be determined that there is no need to learn the downshift preference, and in this case, the routine exits without performing anything. .

As described above, the selection of the shift map is completed based on the learning according to the driver's preference, and the process returns to FIG. 15 and proceeds to step S22. Step S22 and subsequent steps show a routine for setting an optimal gear position based on the driving state of the vehicle. In step S22, based on the vehicle speed V and the accelerator opening VA, which are factors that determine the driving state of the vehicle, the target gear position setting means 3 sets a target suitable for the traveling state from the shift map selected as described above. Find the gear.

Then, in step S24, step S
10 based on the vehicle load degree αVL obtained in step S18, the information from each sensor and the target shift speed, the running state of the vehicle is estimated in accordance with the fuzzy rule described above, and the driver's driving intention is inferred accordingly. I do. In the next step S30, the shift command supplied to the target shift speed is corrected based on the driver's intention estimated in step S24. In addition to the correction based on the fuzzy rule, the correction includes, for example, a correction content that regulates continuous execution of the shift immediately after the end of the shift and immediately after on / off of the exhaust brake and the auxiliary brake. Detailed description is omitted.

As described above in detail, in the shift control device for an automatic transmission for a vehicle according to the present invention, learning is performed based on a back propagation learning method using a neural network, so that each driver can be delicate. An optimum shift map according to the driver's preference is selected from a plurality of shift maps in consideration of different driver's preferences, and a target shift speed determined by the shift map is further converted to a desired fuzzy speed using the vehicle load degree αVL as a parameter. Correction can be made by a rule or the like, and the optimum gear position can be suitably determined by reflecting the driver's intention as well as the driver's preference. Therefore, the shift control device for the automatic transmission for a vehicle can perform shift control that is very close to shift-up or shift-down of a manual transmission mainly performed by a manual operation while being an automatic transmission,
Drivability can be greatly improved regardless of the driver.

Further, among the learning data for performing the learning control of the driver's preference, 2-3 accelerator opening average AVA
(23) 2-3 standard deviation SVA (23), 3-4 accelerator opening average AVA (34), 3-4 standard deviation SVA (34), 2-3 engine rotation average ANe (23), 3-4 Engine rotation average A
Regarding Ne (34), in calculating each data, when the vehicle speed V is lower than the predetermined vehicle speed V2 (for example, 20 km / h), the calculation of each learning value is not performed until the vehicle speed V exceeds the predetermined vehicle speed V2. Vehicle speed V is equal to the predetermined vehicle speed V2
When driving on a congested road that does not reach the limit, it is possible to prevent the adoption of shift-up data, which is performed regardless of the driver's preference, as a learning value, thereby preventing unnecessary shift map switching during congested road driving. Thus, the learning of the driver's preference can be performed better.

Of the learning data, the HOLD range use frequency FH at the time of deceleration and the M range use frequency FMD at the time of deceleration are calculated by the driver, at least once by manual operation. If the frequency of use of the M range FMDi is not 0, the driver determines that the HOLD range is not being used merely for the purpose of canceling the shift in the D range and uses the HOLD range. The frequency FHi is set to a value of 0. On the other hand, when there is no manual downshift, the driver sets HOL to cancel the shift in the D range.
It is determined that the D range is used, and the M range use frequency FMDi is set to a value of 0. Therefore, when learning the downshift preference, the HOLD range use frequency FHi and M The magnitude relation of the range use frequency FMDi is made clear. Hence, their respective average value, H
The OLD range use frequency FH and the M range use frequency FMD are also set to clear values that reflect the driver's preference, thereby improving the learning accuracy and appropriately and reliably performing the shift down mode and the shift down mode. Is done.

In learning the downshift, when the vehicle speed V is equal to or higher than a predetermined vehicle speed V1 (for example, 30 km / h), the vehicle speed V is reduced after the driver releases the accelerator pedal 81, and the clutch 15 is automatically turned off. When the clutch is disengaged, it is determined that the vehicle is in a deceleration state, and learning regarding downshifting is performed. Therefore, it is accurately detected that the vehicle is in a deceleration state, and learning of a preference at the time of downshifting is in progress. Is implemented without interruption. Here, the vehicle speed V is equal to the predetermined vehicle speed V1 (for example,
A condition of 30 km / h or more is set, because if the vehicle speed V is equal to or more than the predetermined vehicle speed V1 (for example, 30 km / h), at least one shift down is expected.

In the learning of the downshift, the shift to be learned is a 5-4 downshift of the fifth speed or lower,
4-3 downshift, 3-2 downshift, etc., which are often performed by other factors such as traffic conditions rather than the driver's preference, that is, 6 shifts larger than the fifth gear
Since learning is not performed for the -5 downshift and the 7-6 downshift, it is possible to prevent the CPU 95 from performing unnecessary calculations and avoid shortage of the capacity of the memory 97, thereby reducing the load on the control unit 71. It is possible to always carry out good learning continuously.

In the above-described embodiment, the learning of the driver's preference is performed using the gear type transmission 17 capable of performing not only the automatic transmission but also the manual transmission. However, the present invention is not limited to this. Even if the learning is applied to an automatic transmission that can be implemented, a sufficient effect can be obtained. Further, in the above-described embodiment, as described with reference to FIG. 17, the fact that the vehicle is traveling on a congested road indicates that the vehicle speed V is equal to the predetermined vehicle speed V2.
(For example, 20 km / h) or less, but the present invention is not limited thereto. The vehicle may be provided with a means capable of recognizing and grasping the road condition, thereby determining that the vehicle is traveling on a congested road.

[0122]

As described above, according to the shift control device for an automatic transmission for a vehicle of the first aspect, the accelerator opening detecting means for detecting the accelerator opening of the engine, and the engine for detecting the engine speed. Rotation speed detection means, monitoring means for monitoring at least one of the accelerator opening and the engine speed at the time of shifting the gear position of the automatic transmission, and learning data calculation for calculating learning data based on the output from the monitoring means Means, learning means for learning so as to carry out gear changeover reflecting the driver's shift preference based on the learning data, and shift control of the automatic transmission based on an output from the learning means and a driving state of the vehicle. And a congestion road traveling determination unit that determines that the vehicle is traveling on a congested road. If it is determined that both vehicles are traveling on a congested road, the learning data is not updated without using the output from the monitoring means, so that the accelerator opening at the time of shifting the gear position of the automatic transmission is performed. At least one of the degree and the engine speed is monitored and output, and learning data is calculated based on the output, and learning is performed so that the gear change reflecting the driver's shift preference is performed, and the learning is performed automatically. While the shift control of the transmission can be performed satisfactorily, while the vehicle is traveling on a congested road where the driver's shift preference is unlikely to appear, the learning data calculation means does not use the output from the monitor means, Thus, it is possible to prevent the learning data in consideration of the driver's shift preference from being unnecessarily updated, and therefore it is possible to preferably maintain the accuracy of the shift control reflecting the driver's shift preference.

According to the shift control device for an automatic transmission for a vehicle of the second aspect, the shift mode is switched to a manual mode in which the shift speed is switched by an operation of a driver by a driver's operation, and the speed is automatically changed according to the driving state of the vehicle. In a shift control device for a vehicle automatic transmission having an automatic mode for switching gears, an accelerator opening detecting means for detecting an accelerator opening of an engine, an engine speed detecting means for detecting an engine speed, Monitoring means for monitoring at least one of the accelerator opening and the engine speed at the time of switching of the gear position of the machine, and learning data calculation for calculating learning data based on an output from the monitoring means in at least one of the manual mode and the automatic mode. Means and gear shift switching reflecting the driver's shift preference during the auto mode based on the learning data Learning means for performing learning, a target gear position setting means for setting a target gear position based on an output from the learning device and a driving state of the vehicle, and performing shift control of the automatic transmission based on the target gear position. Shift control means,
And a learning data calculation means for determining that the vehicle is traveling on a congested road when the vehicle is traveling on a congested road. Since the learning data is not updated without employing the output from the monitor means, the shift control of the automatic transmission in the vehicle automatic transmission having the manual mode and the automatic mode can be switched. At least one of the accelerator opening and the engine speed at the time is monitored, and learning data is calculated based on the monitor output in at least one of the manual mode and the auto mode. It is possible to perform learning so as to execute the gear shift reflecting the gear shift preference, thereby setting the target gear and automatically setting the target gear. The shift control of the transmission can be satisfactorily performed. However, when the vehicle is traveling on a congested road where the driver's shift preference is unlikely to appear, the learning data calculation means does not use the output from the monitor means, and learning data in consideration of the driver's shift preference is generated. Unnecessary updating can be prevented, and therefore, the accuracy of the shift control reflecting the driver's shift preference can be suitably maintained.

Further, according to the shift control device for an automatic transmission for a vehicle of the present invention, the learning data calculating means determines whether the vehicle has escaped from traveling on a congested road by the congested road traveling determining means. Calculates the learning data based on the latest output monitored by the monitoring means when traveling on a congested road. The shift preference can be effectively reflected in the calculation of the learning data, and therefore, the shift control in which the driver's shift preference is reflected can be favorably performed.

Further, according to the shift control device for an automatic transmission for a vehicle of the present invention, the vehicle further comprises a vehicle speed detecting means for detecting a vehicle speed. Since it is determined that the vehicle is traveling on a road, it can be easily determined that the vehicle is traveling on a congested road based on whether the vehicle speed is lower than a predetermined vehicle speed. Claim 5
According to the shift control device for an automatic transmission for a vehicle, when the vehicle speed is equal to or higher than the predetermined vehicle speed, the learning data calculating unit determines whether the vehicle speed is lower than the predetermined vehicle speed based on the latest output monitored by the monitor unit. Since the calculation of the learning data is performed,
When the vehicle speed exceeds the predetermined vehicle speed, it can be determined that the vehicle has departed from congested road traveling, and the driver's shift preference when accelerating from low vehicle speed such as congested road to normal traveling is effective for calculating learning data Therefore, the shift control reflecting the driver's shift preference can be favorably performed.

Further, according to the shift control device for an automatic transmission for a vehicle of the present invention, the point of time when the gear is switched is the point of upshifting, so that it is particularly desirable to reflect the driver's shift preference. The accuracy of the up control can be suitably maintained.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a main configuration of a shift control device for an automatic transmission for a vehicle according to an embodiment of the present invention.

FIG. 2 is a configuration diagram showing an overall configuration of a shift control device for an automatic transmission for a vehicle as one embodiment of the present invention.

FIG. 3 is a diagram showing a select pattern of a change lever.

FIG. 4 is a graph showing a relationship between an accelerator opening and VA.

FIG. 5 is a graph showing a shift map # 1 in the economy mode.

FIG. 6 is a graph showing a shift map # 2 in the economy mode.

FIG. 7 is a graph showing a shift map # 3 in the economy mode.

FIG. 8 is a graph showing a shift map # 1 in a normal mode.

FIG. 9 is a graph showing a shift map # 2 in a normal mode.

FIG. 10 is a graph showing a shift map # 3 in a normal mode.

FIG. 11 is a graph showing a shift map # 1 in a power mode.

FIG. 12 is a graph showing a shift map # 2 in the power mode.

FIG. 13 is a graph showing a shift map # 3 in the power mode.

FIG. 14 is a diagram showing characteristics of a vehicle load degree as a shift control parameter on a flat road.

FIG. 15 is a flowchart illustrating a main routine of a shift control.

FIG. 16 is a flowchart showing a learning control routine in FIG. 15;

FIG. 17 shows AVA, SVA, and ANe of the learning data.
9 is a flowchart illustrating a calculation routine.

FIG. 18 is a flowchart showing a routine for calculating FH and FMD of learning data.

FIG. 19 is a diagram showing a first neural network.

FIG. 20 is a diagram showing a second neural network.

FIG. 21 is a diagram showing a third neural network.

FIG. 22 is a graph showing a relationship between judgment outputs O4 and O'4 and a selection map.

FIG. 23 is a graph showing a relationship between a judgment output O ″ 4 and downshiftability.

FIG. 24 is a graph showing a downshift regulation map corresponding to shift map # 1 in the economy mode.

[Explanation of symbols]

 REFERENCE SIGNS LIST 1 optimal shift speed determining means 2 vehicle load degree calculating means 3 target shift speed setting means 3A storage means 3B learning formula selecting means (learning means) 4 engine torque calculating means 5 driving force calculating means 6 air resistance calculating means 7 straight flat road vehicle Equivalent acceleration calculation means 8 Subtraction means 11 Diesel engine (engine) 17 Gear transmission (transmission mechanism) 27 Engine rotation sensor (engine speed detection means) 61 Change lever 63 Shift stage selection switch 65 Gear shift unit 71 Control unit (Shift control means ) 79 Vehicle speed sensor 81 Accelerator pedal 85 Accelerator opening sensor (accelerator opening detecting means) 87 Brake sensor

──────────────────────────────────────────────────続 き Continuation of the front page (51) Int.Cl. ⁶ identification code FI F16H 59:66 (58) Investigated field (Int.Cl. ⁶ , DB name) F16H 59/00-61/12 F16H 61/16 -61/24 F16H 63/40-63/48

Claims (6)

(57) [Claims] 1. An accelerator opening detecting means for detecting an accelerator opening of an engine; an engine speed detecting means for detecting an engine speed; and the accelerator opening and the engine at the time of shifting gear positions of an automatic transmission. Monitoring means for monitoring at least one of the rotation speeds; learning data calculating means for calculating learning data based on an output from the monitoring means; and a gear position reflecting a shift preference of a driver based on the learning data. Learning means for learning to perform switching; shift control means for performing shift control of the automatic transmission based on an output from the learning means and a driving state of the vehicle; and that the vehicle is traveling on a congested road. And the learning data calculating means determines that the vehicle is traveling on the congested road by the congested road running determining means. Been the case, the shift control apparatus for a vehicular automatic transmission, characterized in that does not update the learning data without employing the output from the monitoring means. 2. A shift control of an automatic transmission for a vehicle, which is connected to an engine and has a manual mode in which a shift speed is switched by a driver's operation and an auto mode in which a shift speed is automatically switched in accordance with a driving state of the vehicle. An accelerator opening detecting means for detecting an accelerator opening of the engine; an engine speed detecting means for detecting an engine speed; and the accelerator opening and the engine speed at the time of shifting the gear position of the automatic transmission. Monitoring means for monitoring at least one of the following: learning data calculation means for calculating learning data based on an output from the monitoring means in at least one of the manual mode and the auto mode; and the automatic mode based on the learning data. Learning to carry out gear shifting that reflects the driver's shifting preferences at times Learning means; target shift speed setting means for setting a target shift speed based on an output from the learning means and a driving state of the vehicle; shift control means for performing shift control of the automatic transmission based on the target shift speed. A traffic congestion road traveling determining means for determining that the vehicle is traveling on a congested road, wherein the learning data calculating means determines that the vehicle is traveling on the congested road by the congested road traveling determining means. A transmission control device for an automatic transmission for a vehicle, wherein the learning data is not updated without using the output from the monitor means when the output from the monitoring means is adopted. 3. The learning data calculation means, when the traffic congestion road traveling determination means determines that the vehicle has left the traffic congestion road, monitors the monitor while traveling on the traffic congestion road. 3. The shift control device for an automatic transmission for a vehicle according to claim 1, wherein calculation of learning data is performed based on the latest output monitored by the means. 4. A vehicle speed detecting means for detecting a vehicle speed, wherein the congested road traveling determining means determines that the vehicle is traveling on the congested road when the vehicle speed is lower than a predetermined vehicle speed. The shift control device for an automatic transmission for a vehicle according to claim 1 or 2. 5. The learning data calculation means calculates learning data based on the latest output monitored by the monitoring means when the vehicle speed is equal to or higher than the predetermined vehicle speed and when the vehicle speed is lower than the predetermined vehicle speed. Characterized by doing
The shift control device for an automatic transmission for a vehicle according to claim 4. 6. The shift control device for an automatic transmission for a vehicle according to claim 1, wherein the shift speed switching point is a shift-up point.