JP2843576B2 - Fire alarm - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION [Industrial Application Field] The present invention detects a physical quantity such as heat, smoke, or gas based on a fire phenomenon, and detects the detected physical quantity and the physical quantity of the physical quantity.
The present invention relates to a fire alarm device that performs fire monitoring by determining a temporal change amount such as a differential value, an integral value, a difference value, and a duration.

[Prior Art] A sensor level from a fire detector for detecting a physical quantity such as heat, smoke or gas based on a fire phenomenon, and a differential value (that is, a slope per unit time) and an integral value of the sensor level It has been proposed to make a fire determination based on (or an integrated value), a difference value, and a temporal transition amount such as a continuation time.

For example, when a differential value is used as a temporal transition amount, when the sensor level exceeds a certain predetermined level, the rate of increase is also measured, and when the sensor level is equal to or higher than a certain level, it is determined that a fire has occurred. What has been proposed. In the specification attached to Japanese Patent Application No. 62-155341 entitled "Fire Alarm System" filed by the applicant on June 22, 1987, the case where an integral value is used as a temporal transition amount is described. When the sensor level exceeds a predetermined level, a portion of the sensor level that is higher than the predetermined level is integrated, and when the integrated value reaches a certain value, it is determined that a fire has occurred. Things have been suggested. In addition, the same "fire alarm device" filed on March 1, 1988 by the present applicant.
The specification attached to Japanese Patent Application No. 63-45955 named
When the difference value is used as the temporal transition amount, a certain rising function is generated when the sensor level exceeds a certain predetermined level, and the rise of the sensor level exceeds the degree of increase of the rising function, and a predetermined rising function is generated. It has been proposed that a fire is determined when a difference between the rising function and a certain value or more is opened within the time period. Also, the specification attached to Japanese Patent Application No. 63-63433, also filed on March 18, 1988, filed with the present application and entitled "Fire Alarm System," describes the duration as a temporal transition amount. When used, it has been proposed to measure a duration in which the sensor level continuously exceeds a certain predetermined level and determine that a fire has occurred when the duration has reached a certain value. ing.

[Problems to be Solved by the Invention] In any of the above-described methods, only the determination as to whether or not there is a fire is made based on the detected sensor level at the present time. It is highly desirable to be able to closely monitor the possibility of a fire, that is, the degree of fire, the degree of danger, and even from a smoldering fire to a flaming fire.

Therefore, the first object of the present invention is not only to judge whether or not there is a fire, but also the fire accuracy and danger, including the situation leading up to the fire, and the entire range from smoked fire to flaming fire. An object of the present invention is to provide a fire alarm device capable of performing detailed and detailed monitoring.

As a method for achieving such an object, first, a relationship between input information such as a sensor level and output information such as a fire accuracy is defined by a function or a table stored in a ROM or the like. And so on. However, in the case of defining in a table, when the number of input points is increased, the number of combinations of inputs explosively increases. Therefore, describing all the combinations requires a great deal of labor and a large ROM table. In addition, there is a limit in expressing a complicated relationship in describing a relationship between input and output by a function.

Accordingly, a second object of the present invention is to provide a fire alarm apparatus having a signal processing structure suitable for achieving the first object.

[Means for Solving the Problems] To achieve these objects, according to the present invention, fire information is obtained by performing signal processing on detection information output from fire phenomenon detection means, and various types of fire information are obtained based on the fire information. In a fire alarm device configured to make a fire determination, a specific set of the detection information and information on a temporal transition amount of the detection information, and a set of fire information to be obtained when the specific set is given. When the detection information and the information on the temporal transition amount are input, the table corresponding to each of the input detection information and the temporal transition amount information according to the degree of contribution to the fire information. Weighting, based on the weighted information, a signal processing network configured to calculate the fire information, and a specific set of detection information and temporal transition amount information in the table. processing Adjusting means for adjusting the weight so as to approximate the fire information calculated when given to the net to the set of the fire information in the table; anda fire alarm device comprising: Provided.

In a specific embodiment, it is preferable that a storage area for storing the adjusted weights is provided. In this case, the signal processing network stores the storage information for the detection information and the temporal transition amount information. The above calculation is performed by weighting the values read from the area.

Also, the signal processing network does not directly calculate fire information from the input detection information and temporal transition amount information, but once calculates intermediate information from the input information and calculates fire information from the intermediate information. It is preferable that the calculation is performed hierarchically. The hierarchy can have a plurality of stages, and the number of intermediate information to be calculated in each intermediate hierarchy is arbitrarily set. For example, if the hierarchy has two stages, input-intermediate and intermediate-output, first, each of the input information is individually weighted first, and each intermediate information is calculated. , And output information, that is, fire information is calculated. The value of each piece of intermediate information is not important, and the signal processing network firstly adjusts the first and second weighting values by the adjusting means so that the relationship between the input information and the output information approximates the contents of the definition table. Adjusted for.

[Operation] First, the adjusting unit weights the input / output values shown in the definition table so as to minimize the error, thereby informing the signal processing network of the contents of the definition table. Once a signal processing network is formed in this way, the signal processing network can output a desired output value for all input values, and therefore, the detection processing that is not defined in the definition table is performed. Information and temporal transition amount information (differential value of detection information, ie, slope per unit time,
It can also handle combinations of integrated values or integrated values, difference values, and durations after detection information exceeds a predetermined value, etc., and desired fire information (fire accuracy, danger, smoked fire accuracy) Etc.). This allows the sensor
Detailed fire judgment can be performed based on the level and the amount of change over time.

As described above, when defining the input / output relationship, it is not necessary to define all the combinations, and it is sufficient to define each important point. Also, especially when it is necessary to describe in detail the singular point where the output value changes significantly due to a slight deviation of the input value, or the minimum point, the vicinity of the maximum point, define the surroundings in detail, and However, it can be roughly defined.

Also, if you want to change the relationship between input and output, there are cases where a different output value is defined for the input value defined so far, and a case where the definition is made for an undefined area so far. The definition can be easily changed by running the adjusting means (net structure creation program). That is, by changing the definition, accurate fire judgment, danger judgment, and the like can be performed.

[Example] Hereinafter, an example of the present invention will be described.

FIG. 1 shows a sensor level of an analog physical quantity based on a fire phenomenon detected by each fire sensor, which is sent to a receiving means such as a receiver or a repeater, and the receiving means based on the collected sensor level. FIG. 2 is a block circuit diagram in a case where the present invention is applied to a so-called analog fire alarm device that makes a fire judgment. Of course, the present invention is also applicable to an on / off type fire alarm device in which each fire detector makes a fire judgment and sends only the result to the receiving means.

In Figure 1, RE is the fire receiver, DE ₁ ～DE _N, for example fire of N analog which is connected to the fire receiver RE through a transmission line L such as a pair of power supply and signal lines And the internal circuit of only one of them is shown in detail.

In the fire receiver RE, the MPU 1 is a microprocessor, the ROM 11 is a program storage area storing programs related to the operation of the present invention described later, and the ROM 12 is a table for various constants such as fire discrimination criteria for all fire detectors. Various constant table storage areas for storage, ROM 13 is a terminal address table storage area that stores the address of each fire sensor, RAM 11 is a work area, and RAM 12 is a definition table described later for all fire sensors. RAM 13 is a storage area for weight values for storing signal line weight values, which will be described later, for all fire detectors. RAM 14 is only used in the second embodiment described later. Used to store sensor level / duration table for all fire detectors, sensor level / duration Inter-table storage area, TRX1 is a signal transmission / reception unit composed of a serial / parallel converter, a parallel / serial converter, etc., DP is a display such as a CRT, KY is a numeric keypad for learning data input described later, IF11, IF
12 and IF13 are interfaces.

In the fire detector DE ₁ , MPU2 is a microprocessor, ROM21 is a program storage area, ROM22 is a self-address storage area, RAM21 is a work area, and FS is heat, smoke, Alternatively, it is a fire phenomenon detecting means for detecting a physical quantity of gas or the like, and includes an amplifier, a sample and hold circuit, an analog / digital converter, etc., although not shown.

 TRX2 is a signal transmitting / receiving unit similar to TRX1, and IF21 and IF22 are interfaces.

Subsequently, the operation according to the embodiment of the present invention will be specifically described. Prior to that, the operation will be described first.

The present invention is intended to quickly and correctly perform various fire judgments such as fire accuracy and danger based on a signal from a sensor unit that detects a physical quantity based on a fire phenomenon and a temporal transition amount of the signal. In the first embodiment, a sensor level as a signal from the sensor unit and a differential value of the sensor level, that is, a sensor
Inputting the slope of the level per unit time and obtaining the fire accuracy as an output, the effect in this case is
This will be described with reference to FIGS. 2A and 3A. In the second embodiment, a sensor level and a duration after the sensor level exceeds a predetermined level are input as time-varying amounts, and fire accuracy and danger are obtained as outputs. The operation in this case will be described with reference to FIGS. 2B and 3B.

FIG. 2A shows a true or fairly accurate fire probability table for 16 combinations or patterns of two pieces of information: sensor level and slope of the sensor level. Also, FIG. 2B shows that
Represents a true or fairly accurate fire accuracy and danger table for 10 combinations or patterns of two pieces of information: sensor level and duration since the sensor level exceeded a predetermined level. Things. In both cases of FIGS. 2A and 2B, such a table is provided for each of the characteristics of the fire detector, the installation location, etc.
It can be created accurately by experiments and the like. However, 2
It is practically impossible to create such a table by experiment or the like for all patterns, not only for 16 or 10 patterns of one information. According to the operation of the present invention described below, it is possible to obtain accurate fire accuracy and danger for all patterns based on two pieces of information.

In FIG. 2A of the first embodiment, the two columns on the left side respectively show the sensor level at the fire phenomenon detecting means FS and the slope of the sensor level per unit time,
In one column on the right side, the fire accuracy T1 corresponding to the sensor level and the inclination shown in the two columns on the left side is indicated by 0 to ₁ . The values of the sensor level and the slope shown in the two columns on the left are also converted to values of 0 to 1 and -1 to +1. In this case, as an example, the sensor levels of 0 to 1
If the fire phenomenon detecting means FS is, for example, a smoke sensor, it corresponds to a smoke concentration of 0 to 20% / m detected by the smoke sensor. The slopes -1 to +1 are
If the current sensor level is x% / m and the sensor level a predetermined time (predetermined number of times) before is y% / m, it corresponds to the next value of x.

−1 to 0 → x = (y−10)% / m to y% / m 0 → x = y% / m 0 to + 1 → x = Y% / m to (y + 10)% / m In FIG. 2B, the two columns on the left show the sensor level at the fire event detection means FS and the duration from when the sensor level exceeds a predetermined level, respectively, and the two columns on the right show Is the fire accuracy T ₁ according to the sensor level and duration shown in the two columns on the left.
And risk T ₂ are indicated by 0-1. The values of the sensor level and the duration shown in the two columns on the left are also 0 to 1.
In this case, as an example, if the fire level detecting means FS is a smoke sensor, for example, the sensor level of 0 to 1 is 0 to 20% of the smoke density detected by the smoke sensor. / m, and the duration 0-1 is
It is assumed that it corresponds to 0 to 60 seconds.

Now, to explain the operation according to the present invention, assume a net structure as shown in FIG. 3A for the first embodiment and as shown in FIG. 3B for the second embodiment. The purpose of these net structure, if the FIGURE 3A of the first embodiment gives converted into the input layer IN ₁ and IN ₂ respectively 0-1 and -1 to +1 the sensor level and the slope, an output It is intended to obtain the accurate fire accuracy converted from 0 to ₁ from the layer OT1, and the input layer is used in the case of FIG. 3B of the second embodiment.
Giving IN ₁ and IN ₂ to be converted to 0-1, respectively the sensor level and duration, the exact fire accuracy and risk which is converted again into 0-1 respectively from the output layer OT ₁ and OT ₂ It is what we are trying to get. This net structure assumes that either the first embodiment or the second embodiment exists in the fire receiver for each fire detector.

In the net structure of the first embodiment shown in FIG. 3A, two IN ₁ and IN ₂ on the left side are input layers IN, and one OT ₁ on the right side is output layer O
T, when it is assumed that the intermediate eight IM ₁ to IM ₈ is referred to as an intermediate layer IM, with each intermediate layer IM ₁ to IM ₈ receives a signal from each input layer IN ₁ and IN _2, the output layer OT ₁ In this case, a signal is output. It is assumed that the signal always travels from the input layer to the output layer, that there is no signal coupling in the reverse direction or between the same layers, and that there is no direct signal coupling from the input layer to the output layer. Therefore, as shown in FIG. 3A, there are 16 signal lines from the input layer to the intermediate layer, and 8 signal lines from the intermediate layer to the output layer.

In the net structure of FIG. 3B of the second embodiment, two IN ₁ and IN ₂ on the left side are connected to the input layer IN ′, and two OT ₁ and O 2 on the right side.
T ₂ output layer OT ', four IM ₁ to IM ₄ middle intermediate layer IM' is referred to as a signal line between the layers, upon shall be coupled in a manner similar to Figure 3A, an input layer From 8 to the middle layer
There are eight signal lines, and eight signal lines are similarly provided from the intermediate layer to the output layer.

These signal lines shown in FIGS. 3A and 3B have weight values or coupling degrees that are changed by values to be output from an output layer in accordance with signals input from each input layer,
The larger the weight, the better the signal on the signal line. The weights of the signal lines between the input layer and the intermediate layer and between the intermediate layer and the output layer are first adjusted according to the relationship between the input and output, and the weight value storage area shown in FIG. It is stored in each area for the fire detector in the RAM 13. The content of the weight value stored in this manner is used for the subsequent fire monitoring operation.

Specifically, by the net creation program described later,
In the case of the first embodiment, the sensor level and the inclination in the two columns on the left side of the table in FIG. 2A are respectively set to the input layer IN _{1 in} FIG. 3A.
And IN ₂ as inputs, and based on those inputs, compare the value output from the output layer OT ₁ with the value of the fire accuracy T ₁ as a teacher signal or learning data shown in the right column of FIG. 2A. The weighting value of each signal line is changed so that the error is minimized. In this way, it is possible to tell the net structure of FIG. 3A a very close approximation to the entire function of the table of FIG. 2A, which is only shown in 16 patterns.

Similarly, in the case of the second embodiment, the sensor level and the duration in the two columns on the left side of the table in FIG. 2B are given as inputs to the input layers IN ₁ and IN ₂ in FIG. Output layers OT ₁ and OT ₂ based on those inputs
The value output from, compared to the respective values of the fire probability T ₁ and risk T ₂ of the as a teacher signal or learning data shown in the right column of FIG. 2B, the signal lines so as to minimize an error Change the weight value of. In this way, it is possible to instruct the net structure of FIG. 3B, which is very close to the entire function of the table of FIG. 2B, shown only in ten patterns, to be taught.

Now, in both the first embodiment and the second embodiment, the weight between the input layer INi and the intermediate layer IMj is defined as And the weight between the intermediate layer IMj and the output layer OTk is (I = 1 to I, j = 1 to J, k = 1 to
K, where I = 2, J = 8, K =
1, and in the case of the second embodiment I = 2, J = 4, K =
2), Has positive, zero, and negative values, respectively. If the input values in the input layer INi are represented by INi, the total sum NET ₁ (j) of the inputs to the hidden layer IMj is This value NET _i (j) is converted to a value of 0 to 1 by, for example, a sigmoid function, and is converted to IMj
If it is expressed by Becomes Similarly, the sum NET of inputs to the output layer OTk
₂ (k) When this value NET ₂ (k) is converted to a value of 0 to 1 by a sigmoid function and expressed as OTk, Becomes Thus, the net structure of Figure 3A and Figure 3B, the input values IN ₁ to IN _I, the relationship between the output values OT ₁ ~OT _K, as equations 1 to 4 using a heavy bid Is represented by
Here, gamma ₁ and gamma ₂ are adjustment factor sigmoidal curve, in this embodiment is selected properly in _{γ 1 = 1.0, γ 2 =} 1.2.

In the net creation program, in the case of the first (second) embodiment, FIG. 2A (FIG. 2B) stored in the storage area RAM 12
16 ways to define the table in FIG.) (In the case of the second embodiment the tilt sensor level IN ₁ of Street 10) is shown (duration in the case of the second embodiment) of the pattern combinations with IN ₂ When one of them is given to the input layer of FIG. 3A (FIG. 3B), the actual output OT ₁ (the second embodiment) calculated by the above-described equations 1 to 4 and output from the output layer For OT ₁ and OT ₂ )
Is the teacher signal output T ₁ shown on the right side of FIG. 2A (FIG. 2B).
(T ₁ and T _{2 in} the case of the second embodiment), and the sum of the errors Em (m = 1 to M, where
M = 16 in the case of the embodiment and M = 10 in the case of the second embodiment) are represented by the following equations.

Here, OTk is a value obtained by the above equation 4. The value E obtained by summing the sum of errors Em for all 16 combinations (10 patterns in the case of the second embodiment) in the table of FIG. 2A (FIG. 2B) is Becomes

Finally, an operation is performed to adjust the weights of the signal lines one by one so that the value E in Equation 6 is minimized. The weight value stored in each fire detector area in the storage area RAM 13 is updated with these adjusted new weight values, and is used in a normal fire monitoring operation. Such adjustment of the weight of the signal line is performed for all the fire sensors in the fire alarm device.

When the education of the table of FIG. 2A (FIG. 2B) for the net structure conceptually shown in FIG. 3A (FIG. 3B) is completed, that is, when the adjustment of the weight value of each one is completed, the actual At the time of fire monitoring, the network calculation program described later
In the case of the first embodiment, the input values of the sensor level and the slope are
Further, in the case of the second embodiment, the input values of the sensor level and the duration are given to the net structure, the values obtained from the respective output layers are calculated by using the above-mentioned equations 1 to 4, and the calculated values are calculated. In the case of the first embodiment, the fire judgment is made by comparing with the reference values of the fire accuracy, and in the case of the second embodiment, the fire judgment is made by comparing with the reference values of the fire accuracy and the risk, respectively.

Hereinafter, FIG. 4A, FIG. 4B, FIG. 6, FIG. 7, FIG.
The operation of the first embodiment of the present invention will be described with reference to FIG. 8C, and FIG. 5A, FIG. 5B, FIG. 5C, FIG. 6, FIG. 7, FIG. 9A to FIG. The operation of the second embodiment will be described.

First, the first embodiment will be described. In FIG. 4A, first, for each of the N fire detectors shown in FIG. 1, the net structure creation program is executed in order from the first fire detector. .

The operation of the net structure creation program in the n-th fire detector (n = 1 to N) will be described. First, the sensor level and inclination in the left column of the definition table described in FIG. The input is given as a teacher input or learning input from the learning data input numeric keypad KY (step 404). The definition table is prepared for each fire detector because the installation environment and the individual characteristics of the fire detector itself are different for each fire detector, but if the environmental conditions and characteristic conditions are the same, Of course, the same definition table can be used for the same condition.

The content of the definition table for nth fire detector is numeric keypad KY
Is stored in the n-th fire detector area in the definition table storage area RAM 12 (Y in step 403), the net structure creation program shown in FIG.
Move on to run 600.

First, a total of 24 signals, 16 signals between the input layer and the intermediate layer and 8 signals between the intermediate layer and the output layer described in FIG. 3A, stored in the n-th fire detector area of the storage area RAM13 Line Is set to a certain value (step 601). next,
Equations (1) to (6) based on the fixed weight value
The actual output values for all M combinations (M = 16 in the first embodiment) of the definition table in FIG. 2A according to
Sum of squares of error between OT and teacher output value T (E in Equation 6)
And set it as E ₀ (step 602).

Next, the weights of the eight signal lines between the intermediate layer and the output layer are reduced by one so that the total value E ₀ of the errors becomes minimum when the same definition table input is given. The operation of adjusting one is performed (N in step 603). Since the weighting value is adjusted only between the intermediate layer and the output layer, there is no change in the values of Expressions 1 and 2 described above. First of all, the first one signal line (Step 604), and perform the same calculations of Equations 3 to 6 to obtain the final total error value E obtained by Equation 6. (Step 605). And the Is compared with the total error value E ₀ before changing the weight value (step 606).

Then (N in step 606), Is set as a new E ₀ (step 609) and changed Is stored in an appropriate position in the work area.

Also, If (Y in step 606), the direction in which the weight value is changed is incorrect, so the original Change the weight value to the other side based on Using the values of Equations 3 to 6 in the same manner as described above. Calculate (steps 607, 608), this calculated _Is set as a new E ₀ (step 60).
9), changed Is stored in an appropriate position in the work area.

here, Is a coefficient proportional to.

In steps 604-609, When the change adjustment for is completed, next, the remaining seven signal lines are Are sequentially adjusted in steps 604 to 609 in the same manner.

In this way, all signal lines between the intermediate layer and the output layer Is adjusted (Y in step 603), then the signal line between the input layer and the intermediate layer is Are also adjusted in steps 610 to 616 so that errors are similarly reduced based on all of the equations (1) to (6).

When the weights of all the signal lines have been adjusted (Y in step 610), E ₀ thus reduced is reduced.
Is compared to a predetermined value C, and if still greater than C (N in step 617), return to step 603 to further reduce the error, and remove the intermediate layer in steps 604-609.
The above-described process from adjusting the weight value between the output layers is repeated again. When E ₀ becomes equal to or less than the predetermined value C (Y in step 617), the process proceeds to step 406 in FIG. 4A, where the 24 changed signal lines are adjusted. Are stored at the corresponding addresses of the n-th fire sensor area in the storage area RAM 13.

In the above operation, the values of S, α, β, C, etc. are stored in the storage area ROM 12 of the various constant tables.

Since the final error of E ₀ does not become 0, the adjustment of the weight of the signal line is terminated at an appropriate place, but when the value becomes equal to or less than the predetermined value C as shown in step 617. In addition to terminating the adjustment, the number of adjustments of the weighting value may be determined in advance and automatically terminated when the number of adjustments is reached.

In FIG. 8A, the adjustment of steps 603 to 616 is repeated 1232 times to create the net structure of FIG. 3A, and the sensor level and the inclination are given as input IN to the net structure thus created. An example of the fire accuracy output as OT at this time is shown. Each pattern number corresponds to the pattern number in the definition table in FIG. 2A, and the data in the top row in each pattern number corresponds to the values of the sensor level IN ₁ and the slope IN _{2 in} FIG. 2A, respectively. The data in the middle row corresponds to the value of the fire accuracy T ₁ as the teacher signal output in FIG. 2A, and the data in the bottom row is the fire accuracy OT ₁ output by the net structure. is there. Further, the calculated value of the value of Expression 6 is shown at the upper right. FIG. 8B shows the weights obtained when the measured values in FIG. 8A are obtained.

FIG. 8C shows not only the discrete values of the definition table shown in FIG. 2A but also all the values output from the net structure when the sensor level is plotted on the X axis and the sensor level is plotted on the Y axis. fire probability OT ₁ is a diagram illustrating the Z-axis.

In this way, by defining two pieces of input information of the sensor level and the slope and the fire accuracy as 16 patterns, even if the combination of the input information is not in the definition table, the net structure is filled in between them to optimize Output as the answer. In this embodiment, the case where the number of inputs to the net structure is two and the number of outputs is one is shown.
It is easily understood by those skilled in the art that the number of outputs can be increased or decreased arbitrarily. As the output, various combinations such as a non-fire probability, a line-of-sight distance, a traveling speed, and a fire extinguishing probability are possible.

If the weighting of the signal line is adjusted for all N fire sensors in the fire alarm device (Y in step 407), and it is determined that there is no need for relearning ( Step 408 N) Then, as shown in the flowchart of FIG. 4B, the fire monitoring operation is performed sequentially from the first fire detector.

The fire monitoring operation for the n-th fire detector DEn will be described. First, a data return command is sent from the signal transmitting / receiving unit TRX1 to the n-th fire detector DEn via the interface IF11 on the signal line L (step 411). .

When the nth fire detector DEn receives the data return command,
The fire detector DEn is detected by the sensor unit, that is, the fire phenomenon detection means, and converted into a digital value by the built-in analog / digital converter according to the program stored in the program storage area ROM21 (smoke related to the fire phenomenon,
The sensor level (based on a physical quantity such as heat or gas) is read via the interface IF21, and is returned from the signal transmission / reception signal unit TRX2 via the interface IF22.

If there is a return from the sensor unit of the n-th fire detector DEn (Y in step 412), the returned sensor level is stored in the work area RAM 11 (step 413).

In order to determine the inclination, an area for storing a plurality of sensor levels for each fire sensor is allocated to the work area RAM 11, and the sensor level returned from each fire sensor at each polling is The data is stored for a predetermined time, and the oldest data, that is, the sensor level is discarded. For example, in one polling cycle is 3 seconds for the fire detector DE ₁ ~DE _N of the fire receiver RE, if 30 seconds for a predetermined time, the sensor 11 times of polling for each fire detector
The level is always stored.

When the sensor level returned from the n-th fire sensor DEn is stored in the n-th fire sensor area of the work area RAM 11 and the oldest data is discarded (step 413), then the sensor area is returned. The slope is obtained from the sensor level for a predetermined time of the above, and is set as SLOPE (step 414).
Various methods can be applied here to determine the slope, for example, a method of dividing the difference between the latest read sensor level and the sensor level read immediately before by one polling period. And the like.

In this way, the latest sensor level and slope SLOP
When E is determined, these information are respectively values of 0 to 1 IN
i, i.e., is converted to a value IN ₂ values IN ₁ and the inclination of 0-1 of the sensor level 0-1, it is placed in the net structure calculation program (step 415), shown thereby in Figure 7 Is executed.

In the net structure calculation program 700, NET ₁ (j) is calculated according to the above equation 1 (step 703), and is converted into the value of IMj according to equation 2 (step 704).
IM ₁ the value of all the IMj up to IM ₈ is determined (step 705 Y), then Equation 3 above using the values of those IMj
NET ₂ (k) is calculated according to the following equation (step 708), and is converted to the value of OTk according to equation 4 (step 709). OTk
That is, when the value of OT ₁ is determined (Y in step 710),
Returning to the flowchart of FIG. 4B. The value of OT ₁ represents the actual value of the fire accuracy.

Accordingly, in FIG. 4B, first, the value of OT ₁ is displayed as it is as the fire accuracy (step 416), and the value of OT ₁ is compared with the reference value A of the fire accuracy read from the various constant table storage area ROM12. Is performed (step 417), and if OT ₁ ≧ A, a fire display is performed (step 418).

Thus, the fire monitoring operation for the nth fire sensor is completed, and the same fire monitoring operation for the next fire sensor is performed.

Next, FIG. 5A, FIG. 5B, FIG. 5C, FIG. 6, FIG.
The operation of the second embodiment of the present invention will be described with reference to FIGS. 9A to 9D.

The flowchart in FIG. 5A is to create the net structure shown in FIG. 3B by using the net structure creating program 600 shown in FIG. 6, as in the case of the first embodiment. In step 504, data input from the numeric keypad, i.e., sensor level and duration,
4 and the fire accuracy and danger are different from the data input from the numeric keypad in step 404 of FIG. 4A.
-I (= 2), J (= 4), K (= 2), M
Except that the value of (= 10) is different from that of the first embodiment,
The operation is essentially the same as that of FIG. 4A.

9A and 9B show the same tables as FIGS. 8A and 8B, respectively, and FIG. 9A shows the adjustment of steps 603 to 616 in the net structure creation program 600 in FIG. 5A. When the net structure of FIG. 3B is created by repeating 334 times, the difference between the created input / output relationship in the net structure of FIG. 3B and the contents of the definition table in FIG. 2B is shown. is there. FIG. 9B shows the weighting values when the results of FIG. 9A were obtained.

9C and 9D show a diagram similar to FIG. 8C, where the sensor level is taken on the X-axis and the duration when the sensor level is above a predetermined level is taken on the Y-axis. ,
Not only discrete values of definition table shown in FIG. 2B, the 3B all output from the net structure of Figure fire probability OT ₁ (FIG. 9C) that is created and risk OT ₂ (first 9D view)
Are respectively shown on the Z axis.

The flowchart of FIG. 5B shows an operation of monitoring the fire of N fire sensors using the net structure of FIG. 3B created by the flowchart of FIG. 5A.

The fire monitoring operation for the n-th fire detector DEn will be described. A data return command is sent to the n-th fire detector DEn (step 511), and if there is a return from the n-th fire detector DEn ( In step 512 (Y), the returned data, that is, the sensor level is stored in the work area RAM 11 (step 513).

When the sensor level exceeds a predetermined level B,
In order to determine a duration that is equal to or higher than the predetermined level B,
In the work area RAM 11, an area for storing a plurality of sensor levels over a continuous time is allocated for each fire sensor. As a result, the sensor level returned from each fire detector at each polling is stored for a predetermined period of time longer than the duration, and the oldest sensor level is discarded. For example, in one polling cycle is 3 seconds for the fire detector DE ₁ ~DE _N of the fire receiver RE, if intended to save the sensor level over 1 minute, 21 times of polling for each fire detector Are stored at all times.

The latest sensor returned from the nth fire detector DEn
The level is compared with a predetermined level B. If the level is equal to or higher than the predetermined level B (Y in step 514), the work area RAM 11
An operation is performed to update the sensor level / duration table for the nth fire detector DEn in the storage area RAM 14 based on the sensor level in the storage area RAM 14 (step 51).
Five).

FIG. 5C conceptually shows a sensor level / duration table created in the area allocated to each fire detector in the storage area RAM 14, and the left column of the table shows the sensor section. That is, the sensor level detected by the fire detecting means FS and converted into a digital value by the built-in analog / digital converter is shown. Sensor unit FS
If, for example, a smoke sensor unit for detecting smoke density, the sensor level is proportional to the value of the detected smoke efficiency, the predetermined level B is set to, for example, the sensor level 10, and the sensor level 10 is Assuming a smoke density of 2.5% / m, a sensor level of 50 would correspond to a smoke density of 12.5% / m. Therefore, the smoke concentration at which a fire
% / M corresponds to the sensor level 80, which corresponds to the conversion value 1.0 shown in the above definition table.

In the right column of the table in FIG. 5C, the duration when a sensor level higher than the sensor level shown in the left column is input is written. That is, the duration 36 seconds in the right column at the sensor level 10 in the left column is
The sensor level read at each poll is continuously higher than a predetermined level B for 36 seconds, that is, during one poll, and a count of 3 seconds is performed at each poll.
Although it is shown that the sensor level has been increased, the sensor level is cleared if the sensor level once read falls below a predetermined level B. Similarly, sensor level 11 in the left column
33 seconds in the right column indicates that the sensor level read at each polling is 33 seconds.
Although the level is equal to or higher than level 11 and the count is incremented, it is immediately cleared when the read sensor level is lower than 11. Similarly,
The duration of each right column up to the sensor level 50 in the left column is counted up or cleared in the same manner.

If the sensor level / duration table of the area for the nth fire detector DEn in the storage area RAM 14 is updated based on the data read into the work area RAM 11, then the storage area RAM 14 Based on the above data, the net structure calculation program 700 also shown in FIG. 7 is executed. In order to execute the net structure calculation program 700,
Each of these data has a value INi of 0 to ₁ , that is, a value IN1 of 0 to _{1 for the} sensor level and a value I1 of 0 to _{1 for the} duration.
It is converted to N _2.

When the value of INi is determined, the net structure calculation program 700 is executed for all the uncleared durations. That is, in the case of FIG. 5C, the sensor level 15
Since the durations corresponding to .about.50 have been cleared, the net structure calculation program is executed for the five sensor levels 10-14.

First, as IN _1, and 0-1 conversion value of the sensor level 10 in the left column of the FIG. 5C, as IN _2, the sensor level 10
The net structure calculation program 700 is executed using the 0-1 conversion value of the duration in the right-hand column corresponding to. That is, NET ₁ (j) is calculated according to the above equation 1 (step 703), and is converted to an IMj value according to equation 2 (step 704). When the value of all the IMj to IM ₁ to IM ₄ are determined (Y of step 705), then, NET ₂ (k) of was calculated according to the formula 3 above using the values of those IMj (Step 70
8), convert it to OTk value according to equation 4 (step
709). When the value of all the OTk of OT ₁ and OT ₂ are determined (Y of step 710), returns to the flowchart of Figure 5B. The values of these OT ₁ and OT ₂ is that each represent the measured values of the fire probability F and the degree of risk D.

The fire accuracy F and the risk D are compared with the initial values F ₀ and D ₀ , respectively (steps 517 and 519), and the larger one is left as the fire accuracy F ₀ and the risk D ₀ (steps 518 and 52).
0).

When the fire accuracy and the risk are determined based on the sensor level 10 and the corresponding duration in the left column in this manner, the process returns to step 516, and all the processes have not been completed yet. Similarly, the network structure calculation program 700 is executed based on the sensor level 11 in the left column as IN ₁ and the duration corresponding to the sensor level 11 as IN ₂ to obtain the fire accuracy F and the risk D. ,
The larger one is left as compared with the previously determined F ₀ and D ₀ respectively. The same operation is repeated up to the sensor level 14 in the left column, and ultimately the highest fire accuracy and risk are left.

In this way, it is determined that the processing of the sensor level / duration table for the n-th fire sensor in the storage area RAM 14 has been completed (Y in step 516).
When the largest fire accuracy F ₀ and the highest risk D ₀ are finally determined, the fire accuracy F ₀ is compared with the reference value A of the fire accuracy read from the various constant table storage area ROM 12. , F ₀ ≧ A (Y in step 521), a fire display is performed (step 522), and the degree of danger is notified by displaying D _{0 as} it is (step 52).
3).

Thus, the fire monitoring operation for the nth fire sensor is completed, and the same fire monitoring operation for the next fire sensor is performed.

Returning to step 514, if it is determined by polling that the sensor level stored in the work area RAM 11 is lower than the predetermined level B (N in step 514), the sensor level / duration table Storage area RA
The n-th fire detector area in M14 is cleared (step 525), and the operation goes to the fire monitoring operation for the next fire detector.

In the above embodiment, the storage area RAM1 of the definition table is used.
Data is input to the storage area RAM 13 based on the data, and the weight value is stored in the storage area RAM 13 based on the data.
In the production stage at a factory or the like, a weighting value is obtained using a net structure creation program and stored in a ROM such as an EPROM, and this ROM is used. Can also.

Further, instead of the analog fire alarm device of the above embodiment, the present invention makes a fire judgment on each fire detector side, and sends only the result to a receiving means such as a fire receiver or a repeater. It can also be applied to an off-type fire alarm device, but in that case, the RO
M11, ROM12 and RAM14 were relocated to each fire detector side, and instead of RAM12 and RAM13, weighting values were stored in the above-mentioned production stages at factories etc.
Advantageously, a ROM is provided for each fire detector. This is because there is no space in the fire detector for providing a numeric keypad or the like as shown in FIG.

[Effects of the Invention] As described above, according to the present invention, a net structure, that is, a signal processing network is formed by weighting the combination of input / output values shown in the definition table so as to reduce the error, and At the time of monitoring, the combination of the sensor level and the amount of temporal transition is provided as input information to this net structure, so that accurate and detailed fire information corresponding to any given combination of input information can be obtained. Therefore, there is an effect that a highly accurate fire judgment can be made.

[Brief description of the drawings]

FIG. 1 is a block circuit diagram showing a fire alarm device according to an embodiment of the present invention. FIGS. 2A and 2B are diagrams showing definition tables used in the first and second embodiments of the present invention, respectively. 3A and 3B are diagrams for conceptually explaining a signal processing network used in the first and second embodiments of the present invention, respectively, and FIGS. 4A and 4B are diagrams for explaining the operation of FIG. FIG. 5A is a flowchart for explaining according to the first embodiment.
FIGS. 5B and 5C are flowcharts and explanatory diagrams for explaining the operation of FIG. 1 according to the second embodiment, and FIG.
4A and 5A are flowcharts for explaining the net structure creation program (weighting value adjusting means) shown in FIGS. 4A and 5A. FIG. 7 is a diagram for explaining the net structure calculation program shown in FIGS. 4B and 5B. Flow chart, 8A
FIG. 8 is a diagram showing actual output data values of the net structure obtained by the net structure creating program of FIG. 6 according to the first embodiment. FIG. 8B is a diagram showing each data output value obtained when the data output value of FIG. FIG. 8C shows a weight value, and FIG. 8C shows a sensor level (X axis) and a gradient of the sensor level (Y axis) in the case of the first embodiment.
9A is a diagram showing the fire accuracy on the Z-axis, FIG. 9A is a diagram showing actual output data values of the net structure obtained by the net structure creating program of FIG. 6 according to the second embodiment, and FIG. 9A and 9D show the respective weight values when the data output values of FIG. 9A are obtained. FIGS. 9C and 9D show the sensor level (X-axis) and the duration (Y-axis) in the case of the second embodiment. FIG. 7 is a diagram showing the fire accuracy and the danger level on the Z-axis, respectively. In the figure, RE is a fire detector, ROM 11 is a program storage area, RAM 12 is a definition table storage area, RAM 13 is a weight value storage area, RAM 14 is a sensor level / duration table storage area, and KY is learning data. Input numeric keypad, DE
_{1 ~DE N} fire detector, FS sensor unit (fire phenomenon detecting means), Heavy bid, IN ₁ and IN ₂ are input information (each detection information and time shift amount information), OT ₁ and OT ₃ is fire information (each fire probability and risk), and.

Claims (3)

(57) [Claims] 1. A fire alarm device which performs signal processing on detection information output from a fire phenomenon detection means to obtain one or more fire information, and makes various fire judgments based on the fire information. A table storing information and a specific set of information relating to a temporal transition amount of the detection information, and a set of fire information to be obtained when the specific set is given; and the detection information and the temporal transition. When the information on the amount is input, the corresponding detection information and the temporal transition amount information are weighted in accordance with the degree of contribution to each of the fire information, and based on the weighted information, A signal processing network configured to calculate the fire information; and the fire information calculated when a specific set of detection information and temporal transition amount information in the table is given to the signal processing network. And the Fire alarm device, characterized in that it and a adjusting means for adjusting the weighting so as to approximate the set of fire information in the table. 2. A fire alarm apparatus, wherein signal processing is performed on detection information output from fire phenomenon detection means to obtain one or more fire information, and various judgments are made based on the fire information. And, when the information regarding the temporal transition amount of the detection information is input, according to the degree of contributing to each of the fire information, perform the corresponding weighting to each input detection information and the temporal transition amount information, A signal processing network configured to calculate the fire information based on the weighted information; detection information; information on a temporal transition amount of the detection information; and desired fire information to be obtained based on the information. And a plurality of specific sets each of which is defined, and the fire information obtained when the detection information and the temporal transition amount information of each specific set of the plurality of defined sets are given to the signal processing network, respectively. Pair of said Storage means for storing a weighting value which is set so as to approximate desired fire information, and wherein the obtained plurality of fire information as a whole is approximated to the plurality of desired fire information, The fire alarm device, wherein the signal processing network performs the corresponding weighting using a weighting value stored in the storage means. 3. The signal processing network comprises: a plurality of input layers; a plurality of intermediate layers each connected to the plurality of input layers;
At least one each connected to the plurality of intermediate layers;
Having two output layers, the weighting value, the input layer and each intermediate layer, the degree of coupling between each intermediate layer and each output layer, or the output value from each input layer to each intermediate layer, The fire alarm device according to claim 1 or 2, wherein an output value from each intermediate layer to each output layer is adjusted.