JP7444038B2 - temperature estimation device - Google Patents

Description

The present invention relates to a temperature estimation device.

The vehicle described in Patent Document 1 includes a motor generator as a drive source and a control device for the motor generator. The control device estimates the temperature of the motor generator rotor when the vehicle system is started. Specifically, the control device estimates the temperature of the rotor based on the temperature of the rotor when the vehicle system is stopped and the elapsed time from when the vehicle system is stopped until the next time the vehicle system is started. .

Japanese Patent Application Publication No. 2020-114167

In a motor generator such as Patent Document 1, even if the temperature of the rotor and the elapsed time are the same when the vehicle system is stopped, it is difficult to imagine that the rotor temperature always changes in the same way while the vehicle system is stopped. Not exclusively. Therefore, in the control device of Patent Document 1, there is room to improve the accuracy of estimating the temperature of the rotor, etc. in accordance with the actual temperature change of the rotor, etc.

A temperature estimation device for solving the above problems is applied to a vehicle equipped with a transaxle including a motor generator as a drive source and a power transmission mechanism that transmits the power of the motor generator, and the temperature estimation device In some cases, the temperature estimation device estimates the temperature of a specific component constituting the transaxle, and includes an execution device and a storage device, and the storage device estimates the temperature by inputting an input variable. Mapping data is stored that defines a mapping that outputs an output variable shown in FIG. The execution device includes an acquisition process that is a process of acquiring the input variable, including an elapsed time until the next activation, and a load variable indicating the load of the vehicle a certain period before the system of the vehicle stops. and a calculation process of outputting the value of the output variable by inputting the input variable acquired by the acquisition process into the mapping.

In the above configuration, the greater the load on the vehicle during a certain period before the vehicle system stops, the more difficult it is for the temperature of the specific component to decrease thereafter due to heat generation according to the load on the vehicle. According to the above configuration, by taking into consideration the load of the vehicle a certain period before the vehicle system stops, it is possible to improve the accuracy of estimating the temperature of a specific component when the vehicle system is started.

A schematic configuration diagram of a vehicle. Flowchart showing startup control.

<Mechanical configuration of vehicle>
An embodiment of the present invention will be described below with reference to FIGS. 1 and 2. First, a schematic configuration of a vehicle 100 to which a control device 90 of the present invention is applied will be described.

As shown in FIG. 1, the vehicle 100 includes an internal combustion engine 10, a transaxle 20, and a plurality of drive wheels 69 as paths through which power is transmitted. The transaxle 20 includes a first planetary gear mechanism 40 , a second planetary gear mechanism 50 , a first motor generator 61 , a second motor generator 62 , a speed reduction mechanism 66 , and a differential 67 . That is, the transaxle 20 is a so-called hybrid transaxle. Further, in this embodiment, the second motor generator 62 is a motor generator as a drive source. Furthermore, the first planetary gear mechanism 40, the second planetary gear mechanism 50, the speed reduction mechanism 66, and the differential 67 are power transmission mechanisms that transmit the power of the motor generator.

The internal combustion engine 10 includes a crankshaft 11 as an output shaft. The crankshaft 11 is connected to a first planetary gear mechanism 40 . The first planetary gear mechanism 40 includes a sun gear 41, a carrier 42, a plurality of pinion gears 43, a ring gear 44, and a ring gear shaft 45. The sun gear 41, which is an external gear, and the ring gear 44, which is an internal gear, are coaxially located. Sun gear 41 is connected to ring gear 44 via a plurality of pinion gears 43. The carrier 42 supports the pinion gear 43 in a rotatable state. Further, the carrier 42 supports the pinion gear 43 so as to be able to revolve. That is, the pinion gear 43 revolves as the carrier 42 rotates. The carrier 42 is connected to the crankshaft 11. Sun gear 41 is connected to first motor generator 61 .

The first motor generator 61 includes a rotor 61A and a stator 61B. The rotor 61A is rotatable relative to the stator 61B. Rotor 61A is connected to sun gear 41.

When the torque of the internal combustion engine 10 is input to the carrier 42, the torque of the internal combustion engine 10 is distributed between the sun gear 41 side and the ring gear 44 side. Then, when the torque of the internal combustion engine 10 transmitted via the sun gear 41 is input to the rotor 61A of the first motor generator 61, the first motor generator 61 functions as a generator.

On the other hand, when the first motor generator 61 is made to function as an electric motor, the torque of the first motor generator 61 is input to the sun gear 41 as the rotor 61A rotates with respect to the stator 61B. Then, the torque of the first motor generator 61 input to the sun gear 41 is distributed between the carrier 42 side and the ring gear 44 side. Then, when the torque of the first motor generator 61 transmitted via the carrier 42 is input to the crankshaft 11 of the internal combustion engine 10, the crankshaft 11 of the internal combustion engine 10 rotates. That is, the first motor generator 61 can apply torque to the internal combustion engine 10 .

Ring gear 44 is connected to ring gear shaft 45. The ring gear shaft 45 rotates together with the ring gear 44. The ring gear shaft 45 is connected to a speed reduction mechanism 66. The speed reduction mechanism 66 is, for example, a speed reduction gear mechanism. The speed reduction mechanism 66 is connected to drive wheels 69 via a differential 67. The differential 67 allows a difference in rotational speed to occur between the left and right drive wheels 69.

Further, the ring gear shaft 45 is connected to a second planetary gear mechanism 50. The second planetary gear mechanism 50 includes a sun gear 51, a carrier 52, a plurality of pinion gears 53, a ring gear 54, and a case 55. The sun gear 51, which is an external gear, and the ring gear 54, which is an internal gear, are coaxially located. Sun gear 51 is connected to ring gear 54 via a plurality of pinion gears 53. The carrier 52 supports the pinion gear 53 in a rotatable state. The carrier 52 is fixed to a case 55 of the second planetary gear mechanism 50. That is, the carrier 52 cannot rotate, and the pinion gear 53 cannot revolve due to the carrier 52. Ring gear 54 is connected to ring gear shaft 45. Sun gear 51 is connected to second motor generator 62 .

The second motor generator 62 includes a rotor 62A and a stator 62B. The rotor 62A is rotatable relative to the stator 62B. Rotor 62A is connected to sun gear 51.

By functioning as a generator when decelerating vehicle 100, second motor generator 62 can generate regenerative braking force in vehicle 100 according to the amount of power generated by second motor generator 62.

On the other hand, when the second motor generator 62 is made to function as an electric motor, the rotor 62A rotates with respect to the stator 62B. The torque of the second motor generator 62 is input to the drive wheels 69 via the second planetary gear mechanism 50 , the ring gear shaft 45 , the reduction mechanism 66 , and the differential 67 . Then, the drive wheel 69 rotates due to the torque of the second motor generator 62.

Vehicle 100 includes a first inverter 71, a second inverter 72, and a battery 73 as devices for transmitting and receiving electric power. The first inverter 71 adjusts the amount of power exchanged between the first motor generator 61 and the battery 73. The second inverter 72 adjusts the amount of power exchanged between the second motor generator 62 and the battery 73.

As shown in FIG. 1, the vehicle 100 includes a supply passage 76, an oil pump 77, an oil pan 78, and a discharge passage 79 as a mechanism for supplying oil. The oil pan 78 stores oil. The oil pump 77 is mechanically connected to the differential 67 and is driven by torque transmitted from the differential 67. Therefore, the oil pump 77 is a so-called mechanical oil pump. Oil pump 77 supplies oil stored in oil pan 78 to various parts of transaxle 20 via supply passage 76 . Further, the discharge passage 79 allows the oil that has circulated through various parts of the transaxle 20 to flow back to the oil pan 78.

<Vehicle electrical configuration>
Next, the electrical configuration of vehicle 100 will be explained.
As shown in FIG. 1, the vehicle 100 includes a vehicle speed sensor 81, an accelerator opening sensor 82, an outside temperature sensor 83, an oil temperature sensor 84, a start switch 86, a mode selection switch 87, a timer 88, and an accelerator pedal 89. There is.

Vehicle speed sensor 81 detects vehicle speed SP, which is the speed of vehicle 100. The accelerator opening sensor 82 detects the accelerator opening ACC, which is the operation amount of the accelerator pedal 89 operated by the driver. Outside temperature sensor 83 detects outside temperature TA, which is the outside temperature of vehicle 100. Oil temperature sensor 84 detects oil temperature TB, which is the temperature of oil flowing through supply passage 76.

Start switch 86 is a switch for starting and stopping the system of vehicle 100. Mode selection switch 87 is a switch that selects driving mode DM, which is the mode in which vehicle 100 travels. In this embodiment, the mode selection switch 87 allows one of the eco mode, normal mode, and power mode to be selected as the driving mode DM. Note that the operation of vehicle 100 according to driving mode DM will be described later. The timer 88 measures time. The timer 88 is always driven by a built-in battery regardless of whether the system of the vehicle 100 is activated or not.

Vehicle 100 includes a control device 90. A signal indicating the vehicle speed SP is input to the control device 90 from the vehicle speed sensor 81. A signal indicating the accelerator opening degree ACC is inputted to the control device 90 from the accelerator opening sensor 82 . A signal indicating the outside temperature TA is input to the control device 90 from the outside temperature sensor 83. A signal indicating the oil temperature TB is input to the control device 90 from the oil temperature sensor 84. A signal for starting and stopping the system of vehicle 100 is input to control device 90 from start switch 86 . A signal for selecting the driving mode DM is inputted to the control device 90 from the mode selection switch 87. A signal indicating time is input to the control device 90 from the timer 88 .

The control device 90 includes a CPU 91, a peripheral circuit 92, a ROM 93, a storage device 94, and a bus 95. The bus 95 connects the CPU 91, the peripheral circuit 92, the ROM 93, and the storage device 94 so that they can communicate with each other. The ROM 93 stores various programs in advance for the CPU 91 to execute various controls. The storage device 94 stores mapping data 94A in advance. The mapping M defined by the mapping data 94A outputs an output variable indicating the temperature of the rotor 62A of the second motor generator 62 by inputting the input variable. That is, the rotor 62A is an example of a specific component. Note that a specific explanation of the mapping M will be given later.

The storage device 94 stores data including vehicle speed SP, accelerator opening ACC, outside air temperature TA, oil temperature TB, driving mode DM, and time from the current time to a predetermined period of time before. The peripheral circuit 92 includes a circuit that generates a clock signal that defines internal operations, a power supply circuit, a reset circuit, and the like. In this embodiment, the CPU 91 and ROM 93 are execution devices. Further, the storage device 94 is a storage device. Control device 90 functions as a temperature estimation device that estimates the temperature of rotor 62A.

<Various processing>
The CPU 91 controls the internal combustion engine 10, the first motor generator 61, the second motor generator 62, etc. by executing various programs stored in the ROM 93. Specifically, the CPU 91 calculates a required vehicle output, which is a required value of the output necessary for the vehicle 100 to travel, based on the accelerator opening degree ACC and the vehicle speed SP. Further, the CPU 91 corrects the vehicle required output according to the driving mode DM. For example, when the eco mode is selected as the driving mode DM, the CPU 91 corrects the vehicle required output to be smaller than that in the normal mode. Further, for example, when the power mode is selected as the driving mode DM, the CPU 91 corrects the vehicle required output to be larger than that in the normal mode. Therefore, even if the accelerator opening degree ACC is the same, the required vehicle output corrected by the CPU 91 increases in the order of eco mode, normal mode, and power mode. CPU 91 determines torque distribution among internal combustion engine 10, first motor generator 61, and second motor generator 62 based on the vehicle required output. The CPU 91 adjusts the output of the internal combustion engine 10 and the power running and regeneration of the first motor generator 61 and the second motor generator 62 based on the torque distribution of the internal combustion engine 10 , the first motor generator 61 , and the second motor generator 62 . Control.

Further, the CPU 91 repeatedly executes the following processes at predetermined intervals by executing various programs stored in the ROM 93. Specifically, CPU 91 calculates a total travel distance TD, which is the total distance traveled by vehicle 100 since oil was stored in oil pan 78, based on the integrated value of vehicle speed SP. Here, if oil has not been replaced with new oil since oil was stored in the oil pan 78 when the vehicle 100 was manufactured, the total mileage TD is the total distance traveled by the vehicle 100 from the time the vehicle 100 was manufactured to the present time. This is the total distance traveled. Further, when the oil in the oil pan 78 has been replaced with new oil, the total mileage TD is the total distance traveled by the vehicle 100 from the time the oil was replaced with the new oil until the present time. The storage device 94 stores the total travel distance TD at every predetermined period. In this embodiment, the total mileage TD is an example of a variable that indicates the degree of deterioration of the vehicle 100.

Based on the driving modes DM selected from the current time to before the specified period, the CPU 91 determines the driving mode DM selected for the longest time during that period as the average driving mode DMA. Note that an example of the prescribed period is several seconds to several tens of seconds. The storage device 94 stores the average driving mode DMA at every predetermined cycle. In this embodiment, the average driving mode DMA is an example of a variable that indicates the load on the vehicle 100. Further, the certain period before the system of the vehicle 100 stops is a point in time that is half of the specified period from when the system of the vehicle 100 stops. Note that when the system of the vehicle 100 is stopped, it is when the control device 90 is stopped by operating the start switch 86.

Based on the vehicle speed SP from the current time to before the specified period, the CPU 91 calculates the average value of the vehicle speed SP during that period as the average vehicle speed SPA. The storage device 94 stores the average vehicle speed SPA at predetermined intervals. In this embodiment, the average vehicle speed SPA is an example of a variable indicating the load on the vehicle 100. Further, the fixed period before the system of the vehicle 100 stops is a point in time that is half of the specified period from when the system of the vehicle 100 stops.

The CPU 91 calculates the average value of the accelerator opening degrees ACC for that period as the average accelerator opening degree ACCA, based on the accelerator opening degrees ACC from the current time to before the predetermined period. The storage device 94 stores the average accelerator opening degree ACCA every predetermined cycle. In this embodiment, the average accelerator opening degree ACCA is an example of a variable indicating the load on the vehicle 100. Further, the certain period before the system of the vehicle 100 stops is a point in time that is half of the specified period from when the system of the vehicle 100 stops.

<Estimated temperature calculation process>
Next, control for calculating the estimated temperature ET, which is the estimated value of the temperature of the rotor 62A of the second motor generator 62, will be explained. The CPU 91 calculates the estimated temperature ET through startup control and normal control. Note that this estimated temperature ET can be used, for example, when limiting the output of the second motor generator 62 so that the second motor generator 62 can be driven within the heat-resistant temperature.

The CPU 91 calculates the initial value of the estimated temperature ET by executing startup control once when the system of the vehicle 100 is started. This startup control will be described later. Note that the time when the system of the vehicle 100 is started is the time when the control device 90 is started by operating the start switch 86.

Further, after the startup control, the CPU 91 calculates the estimated temperature ET by repeatedly executing the normal control at predetermined intervals. Specifically, during normal control, the CPU 91 estimates the estimated temperature ET based on the initial value of the estimated temperature ET, the vehicle required output, the torque distribution, the outside air temperature TA, the oil temperature TB, and the like. Note that the above torque distribution is a torque distribution among the internal combustion engine 10, the first motor generator 61, and the second motor generator 62. The storage device 94 stores the estimated temperature ET at predetermined intervals.

Based on the estimated temperature ET from the current time to before the predetermined period, the CPU 91 calculates a temperature increase gradient TRG indicating a tendency of change in the estimated temperature ET per unit time during that period at every predetermined period. For example, assume that 1 second is set as the unit time, and the estimated temperature ET increases by 1° C. in 10 seconds. In this case, the estimated temperature ET increases by 0.1° C. per second. Therefore, the temperature increase gradient TRG is 0.1°C. The storage device 94 stores the temperature increase gradient TRG at predetermined intervals. In this embodiment, the temperature increase gradient TRG is an example of a variable indicating the load on the vehicle 100. Further, the certain period before the system of the vehicle 100 stops is a point in time that is half of the specified period from when the system of the vehicle 100 stops.

<Start-up control>
Next, startup control executed by the CPU 91 will be described. The ROM 93 stores in advance a startup program which is a program for executing startup control. Each time the system of the vehicle 100 is started, the CPU 91 performs startup control once by executing a startup program.

As shown in FIG. 2, when startup control is started, the CPU 91 executes step S11. In step S11, the CPU 91 calculates the elapsed time PE from when the system of the vehicle 100 is stopped until it is started next time based on the time obtained from the timer 88. Specifically, the CPU 91 calculates the elapsed time PE based on the time obtained from the timer 88 immediately before the system of the vehicle 100 stops and the time obtained from the timer 88 immediately after the system of the vehicle 100 starts. do. The storage device 94 stores the elapsed time PE. After that, the CPU 91 advances the process to step S12.

In step S12, the CPU 91 determines whether the elapsed time PE is greater than a predetermined threshold A. An example of the threshold value A is several hours to several tens of hours. In step S12, if the CPU 91 determines that the elapsed time PE is greater than the threshold A (S12: YES), the CPU 91 advances the process to step S13.

In step S13, the CPU 91 sets the outside air temperature TA at the time of processing in step S13 as the initial value of the estimated temperature ET. After that, the CPU 91 ends the current startup control. Note that after that, the CPU 91 repeatedly executes the normal control.

On the other hand, in step S12, if the CPU 91 determines that the elapsed time PE is equal to or less than the threshold value A (S12: NO), the CPU 91 advances the process to step S21.
In step S21, the CPU 91 obtains various values by accessing the storage device 94. Specifically, the CPU 91 stores the estimated temperature ET, total travel distance TD, average driving mode DMA, average vehicle speed SPA, average accelerator opening ACCA, temperature increase gradient TRG, which were stored immediately before the system of the vehicle 100 stopped. Obtain outside air temperature TA and oil temperature TB. Further, the CPU 91 acquires the elapsed time PE stored in step S11. Note that in this embodiment, the process in step S21 is an acquisition process. After that, the CPU 91 advances the process to step S22.

In step S22, the CPU 91 generates the various values obtained in the process of step S21 as input variables x(1) to x(9) to the mapping M. Specifically, the CPU 91 substitutes the estimated temperature ET into the input variable x(1). The CPU 91 assigns the elapsed time PE to the input variable x(2). The CPU 91 assigns the total mileage TD to the input variable x(3). The CPU 91 assigns a numerical value indicating the average driving mode DMA to the input variable x(4). For example, the CPU 91 sets, as the input variable x(4), a numerical value such as "1" when the average driving mode DMA is the eco mode, "2" when the average driving mode is the normal mode, and "3" when the average driving mode is the power mode. substitute. The CPU 91 assigns the average vehicle speed SPA to the input variable x(5). The CPU 91 assigns a numerical value indicating the average accelerator opening degree ACCA to the input variable x(6). For example, the CPU 91 substitutes a larger numerical value in the range of "0" to "1" as the input variable x(6), the larger the average accelerator opening degree ACCA. The CPU 91 assigns the temperature rise gradient TRG to the input variable x(7). The CPU 91 assigns the outside temperature TA to the input variable x(8). The CPU 91 assigns the oil temperature TB to the input variable x(9). In this embodiment, input variables x(4) to input variables x(7) are load variables that indicate the load on the vehicle 100 a certain period before the system of the vehicle 100 stops. Furthermore, the input variable x(3) is a deterioration degree variable that indicates the deterioration degree of the vehicle 100 when the system of the vehicle 100 is stopped. After that, the CPU 91 advances the process to step S23.

In step S23, the CPU 91 applies the input variables x(1) to x(9) and bias parameters generated in the process of step S22 to the mapping M defined by the mapping data 94A stored in advance in the storage device 94. By inputting the input variable x(0), the value of the output variable y(i) is calculated. Thereafter, the CPU 91 advances the process to step S24.

An example of the mapping M defined by the mapping data 94A is a function approximator, which is a fully connected forward propagation neural network with one intermediate layer. Specifically, in the mapping M defined by the mapping data 94A, the input variables x(1) to x(9) and the input variable x(0) as a bias parameter are , k=0 to 9) are substituted into the activation function f, thereby determining the value of the node in the intermediate layer. Furthermore, the output variable y(1) is determined by substituting each of the values obtained by converting the values of the intermediate layer nodes into the activation function g by the linear mapping defined by the coefficient wSij (i=1). The output variable y(1) is a numerical value indicating the initial value of the estimated temperature ET, that is, the estimated temperature ET when the system of the vehicle 100 is started.

In this embodiment, the processing in step S22 and step S23 is calculation processing. In this embodiment, an example of the activation function f is the ReLU function. Further, an example of the activation function g is a sigmoid function.

Note that the mapping M defined by the mapping data 94A is generated, for example, as follows. First, a plurality of different transaxles 20 with different degrees of deterioration over time are prepared, such as transaxles 20 that have just been manufactured and transaxles 20 that have been used to some extent. These test transaxles 20 are then mounted on vehicles 100 of the same model and used under various conditions. At this time, the elapsed time PE, total mileage TD, average driving mode DMA, average vehicle speed SPA, average accelerator opening ACCA, temperature increase gradient TRG, outside air temperature TA, and oil temperature TB are acquired. Furthermore, the temperature of the rotor 62A of the second motor generator 62 is obtained through actual measurement. Then, the temperature of the rotor 62A, the total mileage TD, the average driving mode DMA, the average vehicle speed SPA, the average accelerator opening ACCA, the temperature increase gradient TRG, the outside air temperature TA, which were acquired immediately before the system of the vehicle 100 stopped, and Let oil temperature TB and elapsed time PE be input variables x(1) to x(9) as training data. In addition, among the measured temperatures of the rotor 62A, a value obtained by converting the temperature of the rotor 62A when the system of the vehicle 100 is started in the range of "0" to "1" that can be taken by a sigmoid function is output as training data. Let the variable be y(1). The input variables x(1) to x(9) as training data and the output variable y(1) as teacher data are input to the mapping M, and the mapping M is learned by machine learning.

In step S24, the CPU 91 sets an initial value of the estimated temperature ET based on the output variable y(1). After that, the CPU 91 ends the current startup control. Note that after that, the CPU 91 repeatedly executes the normal control.

<Action of this embodiment>
In the vehicle 100, even if the temperature of the rotor 62A immediately before the system of the vehicle 100 stops and the elapsed time PE are the same, the temperature of the rotor 62A after that depends on the load of the vehicle 100 immediately before the system of the vehicle 100 stops. The temperature change trends are different. Specifically, the load on vehicle 100 tends to be larger as the average driving mode DMA shifts to eco mode, normal mode, and power mode. Further, the higher the average vehicle speed SPA, the larger the average accelerator opening ACCA, and the larger the temperature increase gradient TRG, the larger the load on the vehicle 100 tends to be. In this way, the greater the load on the vehicle 100 immediately before the system of the vehicle 100 stops, the greater the heat generated in accordance with the load on the vehicle 100. Therefore, after the system of vehicle 100 is stopped, the temperature of rotor 62A tends to be difficult to decrease. As a result, the temperature of rotor 62A when the system of vehicle 100 is started changes depending on the load of vehicle 100 immediately before the system of vehicle 100 is stopped.

<Effects of this embodiment>
(1) In this embodiment, variables indicating the load of the vehicle 100 immediately before the system of the vehicle 100 stops, that is, variables indicating the average driving mode DMA, average vehicle speed SPA, average accelerator opening ACCA, and temperature increase gradient TRG are used. As an input variable, an output variable y(1) indicating the estimated temperature ET when the system of the vehicle 100 is started can be obtained. According to this configuration, by taking into account the load of the vehicle 100 immediately before the system of the vehicle 100 stops, the output variable y(1) that reflects the load of the vehicle 100 is output. As a result, the accuracy of estimating the output variable y(1) indicating the estimated temperature ET when the system of the vehicle 100 is started can be improved.

(2) In the vehicle 100, as the total mileage TD becomes longer, the period in which the oil in the oil pan 78 is used becomes longer, and thus the oil deteriorates. When the oil deteriorates in this manner, the temperature of the rotor 62A becomes difficult to decrease due to heat exchange with the oil supplied from the oil pan 78 to various parts of the transaxle 20. Therefore, the cooling performance of the transaxle 20 tends to decrease depending on the total traveling distance TD.

In this embodiment, a variable indicating the total travel distance TD immediately before the system of the vehicle 100 stops is used as an input variable to the mapping M. According to this configuration, it is possible to obtain an output variable y(1) that takes into account the cooling performance of the transaxle 20 in the vehicle 100. As a result, an improvement in the accuracy of estimating the estimated temperature ET when the system of the vehicle 100 is started can be expected.

(3) In this embodiment, a variable indicating the outside temperature TA immediately before the system of the vehicle 100 is stopped is used as an input variable to the mapping M. According to this configuration, it is possible to obtain an output variable y(1) that takes into account the ease with which the temperature of the rotor 62A decreases due to heat exchange between the air outside the vehicle 100 and the rotor 62A.

(4) In this embodiment, a variable indicating the oil temperature TB immediately before the system of the vehicle 100 is stopped is used as an input variable to the mapping M. According to this configuration, it is possible to obtain an output variable y(1) that takes into account the ease with which the temperature of the rotor 62A decreases due to heat exchange between the oil supplied to the transaxle 20 and the rotor 62A.

(5) In this embodiment, the learned mapping M is used to obtain the output variable y(1) indicating the estimated temperature ET when the system of the vehicle 100 is started. Therefore, the relationship between variables indicating the average driving mode DMA, average vehicle speed SPA, average accelerator opening ACCA, temperature increase gradient TRG, etc. and the estimated temperature ET when the system of the vehicle 100 is started is expressed by a function or the like. Even with complex relationships that are difficult to understand, an appropriate output variable y(1) can be obtained by learning the mapping M.

(6) When the system of vehicle 100 is stopped, the temperature of rotor 62A decreases as elapsed time PE increases. Finally, the temperature of the rotor 62A substantially matches the outside air temperature TA. Therefore, in this embodiment, when the elapsed time PE is larger than the threshold value A, the outside air temperature TA is set as the initial value of the estimated temperature ET. Thereby, it is possible to suppress an increase in the calculation load on the CPU 91 due to the calculation of the output variable y(1) using the mapping M.

<Example of change>
This embodiment can be modified and implemented as follows. This embodiment and the following modified examples can be implemented in combination with each other within a technically consistent range.

"About input variables"
- In the above embodiment, the input variables input to the mapping M are not limited to the examples in the above embodiment. For example, the degradation variable can be changed. Specifically, the oil stored in the oil pan 78 tends to deteriorate depending on the travel time, which is the total time that the vehicle 100 has traveled since the oil was stored in the oil pan 78. Therefore, the above-mentioned travel time may be used as the deterioration degree variable instead of or in addition to the total travel distance TD.

- For example, the deterioration degree variable as an input variable of the mapping M may be omitted. Specifically, depending on the configuration of the transaxle 20, the type of oil stored in the oil pan 78, etc., it may be difficult for the oil to deteriorate. In this case, even if the deterioration degree variable is omitted as an input variable of the mapping M, the effect is small.

- For example, load variables can be changed. As a specific example, it is not necessary to employ four of the load variables: average driving mode DMA, average vehicle speed SPA, average accelerator opening ACCA, and temperature increase gradient TRG; it is sufficient to employ at least one of them.

- For example, if a deterioration degree variable is employed as an input variable of the mapping M, the load variable may be omitted. In the vehicle 100, the greater the degree of deterioration of the vehicle 100 when the system of the vehicle 100 is stopped, the more difficult it is for the temperature of specific parts to decrease thereafter due to a decrease in cooling performance according to the degree of deterioration of the vehicle 100. be. According to the above configuration, by taking into consideration the degree of deterioration of the vehicle 100 when the system of the vehicle 100 is stopped, it is possible to improve the accuracy of estimating the temperature of a specific component when the system of the vehicle 100 is started. Specifically, in a configuration in which the estimated temperature ET immediately before the system of the vehicle 100 stops, the elapsed time PE, and the total mileage TD are used as input variables of the mapping M, the system of the vehicle 100 stops. Compared to a configuration that employs only the estimated temperature ET immediately before the activation and the elapsed time PE, the estimation accuracy of the estimated temperature ET when the system of the vehicle 100 is started can be improved.

"About output variables"
- In the above embodiment, the number of output variables of the mapping M may not be one, but may be plural.

- In the above embodiment, the specific component that is the target of the output variable of the mapping M is not limited to the example of the above embodiment. Specifically, the specific component targeted by the output variable y(1) of the mapping M is not limited to the rotor 62A, but may be the stator 62B of the second motor generator 62, for example. Further, for example, it may be a part of the first motor generator 61. Furthermore, for example, not only the first motor generator 61 and the second motor generator 62, but any part in the transaxle 20 may correspond to the specific part.

"About startup control"
- In the above embodiment, the startup control is not limited to the example of the above embodiment. As a specific example, after step S11, the CPU 91 may proceed to step S21 without executing the determination process of step S12. In this case, the processes of step S12 and step S13 can be omitted.

"About mapping"
- In the above embodiment, a neural network with one intermediate layer is illustrated as the neural network, but the number of intermediate layers may be two or more.

- In the above embodiment, a fully connected forward propagation neural network is illustrated as the neural network, but the neural network is not limited to this. For example, a regression combination neural network may be employed as the neural network.

- In the above embodiment, the function approximator as the mapping M is not limited to a neural network. For example, a regression equation without an intermediate layer may be used.
- In the above embodiment, the activation function of mapping M is an example, and is not limited to the example of the above embodiment. For example, a sigmoid function or the like may be used as the activation function f of the mapping M, or a ReLU function or the like may be used as the activation function g.

"About the execution device"
- In the above embodiment, the execution device is not limited to one that includes the CPU 91 and the ROM 93 and executes software processing. As a specific example, a dedicated hardware circuit such as an ASIC may be provided to perform hardware processing for at least a part of what was processed by software in the above embodiments. That is, the execution device may have any of the following configurations (a) to (c). (a) It includes a processing device that executes all of the above processing according to a program, and a program storage device such as a ROM that stores the program. (b) It includes a processing device and a program storage device that execute part of the above processing according to a program, and a dedicated hardware circuit that executes the remaining processing. (c) A dedicated hardware circuit is provided to execute all of the above processing. Here, there may be a plurality of software execution devices including a processing device and a program storage device, and a plurality of dedicated hardware circuits.

"About the transaxle"
- In the above embodiment, the transaxle 20 is not limited to the example of the above embodiment. For example, the transaxle 20 does not necessarily need to include a plurality of motor generators, but only needs to include at least one motor generator as a drive source. Further, the transaxle 20 does not necessarily have to include all of the first planetary gear mechanism 40, the second planetary gear mechanism 50, the reduction mechanism 66, and the differential 67, and at least transmits the power of the motor generator as a drive source. It is sufficient to have a mechanism to do so. In this case, a mechanism that transmits the power of the motor generator as a drive source is a power transmission mechanism.

"About the vehicle"
- In the above embodiment, the vehicle is a so-called series/parallel hybrid vehicle, but the vehicle is not limited to this. For example, the vehicle may be a series hybrid vehicle or a parallel hybrid vehicle.

<Other technical ideas>
The technical ideas that can be understood from the above embodiment and modification examples will be described.
- Applied to a vehicle equipped with a transaxle that includes a motor generator as a drive source and a power transmission mechanism that transmits the power of the motor generator, and when the system of the vehicle is started, specific parts that constitute the transaxle A temperature estimating device for estimating the temperature of a temperature, comprising an execution device and a storage device, wherein the storage device defines a mapping that outputs an output variable indicative of the temperature when an input variable is input. data is stored, and the mapping includes, as the input variables, the temperature when the vehicle system is stopped, and the elapsed time from when the vehicle system is stopped until the next time it is started; a deterioration degree variable indicating the degree of deterioration of the vehicle when the system of the vehicle is stopped; A temperature estimating device that performs a calculation process of outputting a value of the output variable by inputting the value into a mapping.

ET... Estimated temperature M... Mapping PE... Elapsed time 10... Internal combustion engine 20... Transaxle 40... First planetary gear mechanism 50... Second planetary gear mechanism 61... First motor generator 61A... Rotor 61B... Stator 62... Second motor Generator 62A...Rotor 62B...Stator 66...Reduction mechanism 67...Differential 69...Drive wheel 90...Control device 91...CPU
92...Peripheral circuit 93...ROM
94...Storage device 94A...Mapping data 95...Bus 100...Vehicle

Claims (1)

Applied to a vehicle equipped with a transaxle including a motor generator as a drive source and a power transmission mechanism that transmits the power of the motor generator, when the system of the vehicle is started, specific parts constituting the transaxle are activated. A temperature estimation device for estimating temperature,
comprising an execution device and a storage device,
The storage device stores mapping data that defines a mapping that outputs an output variable indicating the temperature by inputting an input variable,
The mapping includes, as the input variables, the temperature when the vehicle's system is stopped, the elapsed time from when the vehicle's system is stopped until the next activation, and when the vehicle's system is stopped. a load variable indicating the load on the vehicle a certain period of time ago;
The execution device executes an acquisition process that is a process of acquiring the input variable, and a calculation process that outputs the value of the output variable by inputting the input variable acquired by the acquisition process into the mapping. Temperature estimation device.