JP7691389B2 - Fault sign diagnostic device and fault sign diagnostic method - Google Patents

Description

The present invention relates to a failure sign diagnostic device and a failure sign diagnostic method, and is suitable for use in a failure sign diagnostic device and a failure sign diagnostic method for diagnosing signs of failure in air compressors used in railway vehicles or in related equipment that uses compressed air.

From the perspective of improving the efficiency and labor-saving of maintenance work, there is a demand for the development of technology to diagnose signs of failures using data obtained from on-board equipment. Among on-board equipment, air compressors that generate compressed air used in air brakes and air springs affect the operation of other equipment such as air brakes when they fail, so there is a strong demand for the development of technology to detect and diagnose signs of failure before they occur.

For example, Patent Document 1 discloses an anomaly detection method that uses equipment monitoring data from railway vehicles to detect the occurrence of compressor abnormalities with high accuracy. According to the anomaly detection method of Patent Document 1, data is extracted when the compressor (air compressor) is operating and the brakes are not operating, and from the data divided by a certain time period, the data with the largest pressure rise in the pressure accumulator system is extracted. The amount of pressure rise is then calculated by multiple regression analysis using the pressure displacement of the air spring at that time, the occupancy rate calculated from the vehicle weight, the running speed, and the outside air temperature as explanatory variables. Anomalies are then detected by comparing the extracted amount of pressure rise in the pressure accumulator system with the amount of pressure rise calculated by multiple regression analysis.

JP 2018-137967 A

However, in the anomaly detection method of Patent Document 1, the data on the amount of pressure rise used to determine anomaly detection is extracted from the time when the air compressor is operating and the equipment using compressed air (e.g., brakes) is not operating. Therefore, depending on the operation and linear conditions of the vehicle on which the equipment is installed, the period corresponding to the data extraction conditions may be short, and there is a risk that data used for failure sign diagnosis may not be obtained sufficiently. Specifically, for example, when the equipment is a brake of a railway vehicle, the railway vehicle decelerates by braking just before the station and stops at the station, so if the distance between stations is short, data on the amount of pressure rise cannot be obtained. Also, if there is a steep downward gradient between stations, the brakes continue to operate for a long time, so data on the amount of pressure rise cannot be obtained. Thus, in the anomaly detection method of Patent Document 1, in a situation where related equipment using compressed air is almost always operating while the air compressor is operating, data used to determine anomaly detection may not be obtained sufficiently, and as a result, there may be a period during which anomaly detection cannot be performed in the air compressor or its related equipment.

The present invention has been made in consideration of the above points, and aims to propose a failure sign diagnostic device and failure sign diagnostic method that can diagnose signs of failure in air compressors or related equipment that uses compressed air, regardless of the vehicle's operation and linear conditions.

In order to solve this problem, the present invention provides a failure sign diagnosis device that diagnoses failure signs in an air compressor or related equipment that uses compressed air generated by the air compressor, the failure sign diagnosis device comprising: a data input unit that inputs operation data of the air compressor and pressure data of the related equipment; an operation time calculation unit that calculates the actual operation time of the air compressor based on the operation data input to the data input unit; an integrated pressure displacement calculation unit that calculates, for each of the related equipment, an integrated pressure displacement indicating the amount of compressed air used by the related equipment for the operation of the air compressor based on the operation data and the pressure data input to the data input unit; an operation time prediction model unit that uses the integrated pressure displacement of each of the related equipment calculated by the integrated pressure displacement calculation unit as a feature and calculates a predicted operation time of the air compressor from a prediction model that uses the feature; and a failure sign diagnosis unit that diagnoses the presence or absence of a failure sign in at least one of the air compressor or the related equipment based on a comparison result between the actual operation time calculated by the operation time calculation unit and the predicted operation time calculated by the operation time prediction model unit.

In addition, in order to solve the above problem, the present invention provides a failure sign diagnosis method by a failure sign diagnosis device that diagnoses a failure sign in an air compressor or related equipment that uses compressed air generated by the air compressor, the method comprising: a data input step in which the failure sign diagnosis device inputs operation data of the air compressor and pressure data of the related equipment; an operation time calculation step in which the failure sign diagnosis device calculates an actual operation time of the air compressor based on the operation data input in the data input step; and an operation time calculation step in which the failure sign diagnosis device calculates an actual operation time of the air compressor for each of the related equipment based on the operation data and the pressure data input in the data input step. the failure sign diagnosis device uses the integrated pressure displacement amount of each related device calculated in the integrated pressure displacement amount calculation step as a feature amount and calculates a predicted operating time of the air compressor from a prediction model using the feature amount; and the failure sign diagnosis step of diagnosing the presence or absence of a failure sign in at least one of the air compressor or the related device based on a comparison result between the actual operating time calculated in the operating time calculation step and the predicted operating time calculated in the operating time prediction step.

The present invention makes it possible to diagnose signs of failure in an air compressor or related equipment, regardless of the vehicle's operating and linear conditions.

1 is a block diagram showing an example of the configuration of a failure sign diagnosis device 100 according to a first embodiment of the present invention. 13 is a flowchart showing an example of a processing procedure of a process performed by an operating time calculation unit 120; 10 is a flowchart showing an example of a processing procedure of a process performed by an integrated pressure displacement amount calculation unit 130; 13 is a flowchart showing an example of a processing procedure of a process performed by an operating time prediction model unit 140. 11 is a diagram for explaining an example of a method for determining an influence degree α _n of a related device. FIG. 10 is a flowchart showing an example of a processing procedure of a failure sign diagnosing unit 150; FIG. 11 is a block diagram showing an example of the configuration of a failure sign diagnosis device 100 according to a second embodiment of the present invention. 13 is a flowchart showing an example of a processing procedure of a process performed by an integrated pressure displacement amount calculation unit 130 according to the second embodiment. FIG. 11 is a block diagram showing an example of the configuration of a failure sign diagnosis device 300 according to a third embodiment of the present invention. 13 is a flowchart showing an example of a processing procedure of a process performed by an operating time prediction model unit 340. 13 is a flowchart showing an example of a processing procedure of a failure sign diagnosing unit 350; 13 is a flowchart showing an example of a processing procedure of a model update unit 360.

The following describes an embodiment of the present invention in detail with reference to the drawings.

(1) First embodiment (1-1) configuration Fig. 1 is a block diagram showing an example of the configuration of a failure sign diagnosis device 100 according to a first embodiment of the present invention. As shown in Fig. 1, the failure sign diagnosis device 100 includes a data input unit 110, an operation time calculation unit 120, an integrated pressure displacement amount calculation unit 130, an operation time prediction model unit 140, and a failure sign diagnosis unit 150.

In addition, an air compressor 210, a brake device 220, and an air spring 230 are connected to the failure sign diagnosis device 100 as devices to be diagnosed for failure signs. The air compressor 210 is a device that generates and supplies compressed air. The brake device 220 and the air spring 230 are examples of related devices that use the compressed air generated by the air compressor 210. There may be one or more related devices for the air compressor 210.

The data input unit 110 inputs operation data of the air compressor 210 from the air compressor 210, and inputs pressure data from the brake device 220 and the air spring 230 that use the compressed air generated by the air compressor 210. Furthermore, the data input unit 110 outputs operation data of the air compressor 210 to the operation time calculation unit 120 and the accumulated pressure displacement calculation unit 130, and outputs pressure data of the brake device 220 and the air spring 230 to the accumulated pressure displacement calculation unit 130.

In this embodiment, the pressure data of related equipment that uses compressed air will be described using as examples the brake cylinder (BC) pressure value of the brake device 220, which is often installed in general railway vehicles, and the air suspension (AS) pressure value of the air spring 230. However, the pressure data that can be used in this embodiment is not limited to the pressure data described above, and if there is related equipment that uses compressed air generated by the air compressor 210, the pressure data for each related equipment may also be input to the data input unit 110. The above is similar to other embodiments.

The data input unit 110 may input data by directly connecting the data input unit 110 to each device, or, if a vehicle (e.g., a railroad vehicle) equipped with each device is equipped with a vehicle information control device (not shown) that aggregates and controls information from each device, the data input unit 110 may be connected to the vehicle information control device to input each data. If a vehicle equipped with each device has a function capable of transmitting each data to a storage area of a server installed in a vehicle depot or the like or a server constructed in a cloud environment using public wireless communication, the failure sign diagnosis device 100 may be implemented in an environment in which it can be connected to the server, and each data may be input from the server to the data input unit 110. The above is similar to other embodiments.

The operating time calculation unit 120 inputs the operating data of the air compressor 210 from the data input unit 110, calculates the actual operating time based on the input information, and outputs this to the failure sign diagnosis unit 150. The operating data of the air compressor 210 indicates at least the operating state of the air compressor 210 (operating or stopped). Details of the processing by the operating time calculation unit 120 will be described later.

The integrated pressure displacement calculation unit 130 inputs the operation data, BC pressure value, and AS pressure value from the data input unit 110, calculates the integrated pressure displacement (integrated BC pressure displacement, integrated AS pressure displacement) of each related device based on the input information, and outputs these to the operation time prediction model unit 140. The integrated pressure displacement is the pressure displacement of the related device for one operation (which may be a predetermined number of times) of the air compressor 210, and is calculated for each related device. The integrated pressure displacement can also be said to be the amount of compressed air used by the related device during one operation of the air compressor 210. Details of the processing by the integrated pressure displacement calculation unit 130 will be described later.

The operating time prediction model unit 140 inputs the integrated BC pressure displacement amount and the integrated AS pressure displacement amount from the integrated pressure displacement amount calculation unit 130, derives a predicted operating time, which is a predicted value of the operating time, based on the input information, and outputs this to the failure sign diagnosis unit 150. Details of the processing by the operating time prediction model unit 140 will be described later.

The failure sign diagnosis unit 150 inputs the actual operating time from the operating time calculation unit 120 and the predicted operating time from the operating time prediction model unit 140, diagnoses failure signs based on the input information, and outputs the diagnosis results to the driver and the vehicle depot. Details of the processing by the failure sign diagnosis unit 150 will be described later.

The following describes in detail the processing performed by each functional unit of the failure prediction diagnosis device 100.

(1-2) Processing by the Operating Time Calculation Unit 120 Fig. 2 is a flowchart showing an example of a processing procedure by the operating time calculation unit 120. The processing shown in Fig. 2 is repeatedly executed at a predetermined cycle.

According to FIG. 2, first, the operation time calculation unit 120 acquires operation data of the air compressor 210 from the data input unit 110. As described above, the operation data of the air compressor 210 indicates at least the operation status (operating/stopped) of the air compressor 210 (step S101).

Next, the operating time calculation unit 120 refers to the operating data acquired in step S101 and determines whether the operating state of the air compressor 210 has changed from stopped to operating (step S102). If the operating state has changed from stopped to operating (YES in step S102), the process proceeds to step S103, and if the operating state has not changed from stopped to operating (NO in step S102), the process proceeds to step S104.

In step S103, the operating time calculation unit 120 starts measuring the operating time and proceeds to step S104.

In step S104, the operating time calculation unit 120 refers to the operating data acquired in step S101 and determines whether the operating state of the air compressor 210 has changed from operating to stopped. If the operating state has changed from operating to stopped (YES in step S104), the process proceeds to step S105, and if the operating state has not changed from operating to stopped (NO in step S104), the process ends.

In step S105, the operation time calculation unit 120 stops measuring the operation time, sets the measured time as the actual operation time, and proceeds to step S106. The actual operation time is the actual measurement of the operation time that has elapsed since the air compressor 210 started operating until it was stopped, and the operation time calculation unit 120 stores the actual operation time in a specified memory area.

Next, the operating time calculation unit 120 outputs the actual operating time set in step S105 to the failure symptom diagnosis unit 150 (step S106), and ends the process.

By executing the process shown in FIG. 2 as described above, the operation time calculation unit 120 can calculate and output the actual operation time of the air compressor 210 based on the operation data of the air compressor 210.

(1-3) Processing by the Integrated Pressure Displacement Calculation Unit 130 Fig. 3 is a flowchart showing an example of the processing procedure by the integrated pressure displacement calculation unit 130. The processing shown in Fig. 3 is repeatedly executed in the same cycle as the processing in Fig. 2.

According to FIG. 3, first, the integrated pressure displacement calculation unit 130 acquires operation data (operating/stopped) of the air compressor 210, the BC pressure value of the brake device 220, and the AS pressure value of the air spring 230 from the data input unit 110 (step S201). As described in the explanation of FIG. 2, the process of step S201 is executed at the same cycle as the process of step S101 in FIG. 2.

Next, the integrated pressure displacement calculation unit 130 refers to the operation data acquired in step S201 and determines whether the operation state of the air compressor 210 has changed from stopped to operating (step S202). If the operation state has changed from stopped to operating (YES in step S202), the process proceeds to step S204, and if the operation state has not changed from stopped to operating (NO in step S202), the process proceeds to step S203.

In step S203, the integrated pressure displacement calculation unit 130 determines whether the air compressor 210 is in operation based on the operation data acquired in step S201. If the air compressor 210 is in operation (YES in step S203), the process proceeds to step S204. If the air compressor 210 is not in operation (NO in step S203), the process proceeds to step S206, which will be described later.

In step S204, the integrated pressure displacement calculation unit 130 calculates the integrated pressure displacement for the pressure data for each related device. Specifically, the integrated pressure displacement calculation unit 130 calculates the difference between the BC pressure value and the AS pressure value acquired in step S201 and the pressure value one cycle earlier, and calculates the integrated pressure displacement for the BC pressure value (integrated BC pressure displacement) and the integrated pressure displacement for the AS pressure value (integrated AS pressure displacement) by integrating the absolute value of this difference into each integrated pressure displacement. The integrated pressure displacement calculation unit 130 then stores the current BC pressure value and AS pressure value in a specified memory area (step S205) and proceeds to step S206.

In step S206, the integrated pressure displacement calculation unit 130 determines whether the operating state of the air compressor 210 has changed from operating to stopped based on the operating data acquired in step S201. If the operating state has changed from operating to stopped (YES in step S206), the process proceeds to step S207, and if the operating state has not changed from operating to stopped (NO in step S206), the process ends.

In step S207, the integrated pressure displacement calculation unit 130 outputs the current integrated BC pressure displacement and integrated AS pressure displacement to the operating time prediction model unit 140. After that, the integrated pressure displacement calculation unit 130 initializes the integrated pressure displacement value of each related device that it manages to "0" (step S208), and ends the process.

As described above, by the calculation process of the accumulated pressure displacement amount shown in FIG. 3, the accumulated pressure displacement amount calculation unit 130 can calculate the amount of compressed air used by each related device for one operation from when the air compressor 210 starts to when it stops.

In this example, the case where the pressure data input from the data input unit 110 to the integrated pressure displacement calculation unit 130 is BC pressure and AS pressure has been described, but if pressure data other than the above is input to the data input unit 110, the integrated pressure displacement calculation unit 130 can perform the processes of steps S204, S205, S207, and S208 for each input pressure data.

(1-4) Processing of the operating time prediction model unit 140 Fig. 4 is a flowchart showing an example of a processing procedure of the operating time prediction model unit 140. The processing shown in Fig. 4 is started when the integrated pressure displacement amount calculation unit 130 outputs the integrated pressure displacement amount of each related device in step S207 in Fig. 3.

According to FIG. 4, first, the operating time prediction model unit 140 acquires the accumulated pressure displacement amount (e.g., the accumulated BC pressure displacement amount and the accumulated AS pressure displacement amount) of each related device output from the accumulated pressure displacement amount calculation unit 130 in step S207 of FIG. 3 (step S301).

Next, the operating time prediction model unit 140 substitutes the accumulated pressure displacement amount obtained in step S301 into the prediction model equation of Equation 1 described below to calculate the predicted operating time (step S302).

Then, the operating time prediction model unit 140 outputs the predicted operating time calculated in step S302 to the failure sign diagnosis unit 150 (step S303), and ends the process.

式１において、Ｙ_ｔ［秒］は予測稼働時間、Ａ［秒］は基準稼働時間、Ｘ_ｎ［ｋＰａ］は関連機器ｎの積算圧力変位量、α_ｎ［秒／ｋＰａ］は関連機器ｎの影響度である。 (1-4-1) Prediction Model A detailed description will now be given of the prediction model for calculating the predicted operating time of the air compressor 210. The prediction model equation used in step S302 in FIG.

In formula 1, Y _t [sec] is the predicted operating time, A [sec] is the reference operating time, X _n [kPa] is the integrated pressure displacement of related device n, and α _n [sec/kPa] is the influence of related device n.

The reference operating time A is the normal operating time of the air compressor 210 in a configuration that is not affected by related equipment. When the air compression performance W [kPa/sec] of the air compressor 210 in the normal state and the start pressure P _min and stop pressure P _max in a tank that accumulates the compressed air generated by the air compressor 210 are known in advance, the reference operating time A can be calculated using the formula "A = (P _max - P _min )/W". Note that the start pressure P _min is the lower limit pressure value of the start pressure in the tank, and the stop pressure P _max is the upper limit pressure value of the stop pressure in the tank.

Furthermore, when the values of the air compression performance W, the starting pressure _Pmin , and the stopping pressure _Pmax are unknown, the values of the actual operation time when the integrated pressure displacement of each related device was "0" for a certain period from when it was new or immediately after inspection or repair may be accumulated, and the average value may be used. The above-mentioned certain period refers to a period during which data that comprehensively includes the expected operation (station intervals, type) of the vehicle (train) on which the air compressor 210 is mounted can be obtained.

The influence degree _αn of each related device is a parameter indicating the degree of influence of the integrated pressure displacement amount in each related device on the air compressor 210, more specifically, a parameter indicating the extension [seconds] of the operating time of the air compressor 210 per 1 kPa of compressed air used by each related device. Each value _α1 to _αn of the influence degree _αn is calculated in advance using regression learning or the like, using as learning data the actual operating time for a certain period of time and the integrated BC pressure displacement amount and integrated AS pressure displacement amount at that time.

In addition, when the integrated pressure displacement amount of the related equipment other than the related equipment n is "0", the influence degree α _n of the related equipment n may be determined based on the relationship between the integrated pressure displacement amount of the related equipment n and the operation time at that time, as shown in Fig. 5. Specifically, for example, the integrated pressure displacement amount of the related equipment n and the corresponding operation time are accumulated for a certain period of time, an approximation formula is calculated by a known method such as the least squares method, and the value of the slope in the approximation formula is determined as the influence degree α _n (see Fig. 5). The above-mentioned certain period is a period during which data that comprehensively includes the operation (station interval, type) expected for the vehicle (train) on which the air compressor 210 is mounted can be obtained.

Fig. 5 is a diagram for explaining an example of a method for determining the influence degree _αn of the related device. As shown in Fig. 5, an approximation formula can be calculated using a predetermined method for data on the operation time and integrated pressure displacement amount of the related device n accumulated over a certain period of time. Then, the slope of the approximation formula of the linear function shown in Fig. 5 can be determined as the influence degree _αn of the related device n.

(1-5) Processing by the Failure Sign Diagnosis Unit 150 Fig. 6 is a flowchart showing an example of a processing procedure by the failure sign diagnosis unit 150. The processing shown in Fig. 6 is executed after the processing in Figs. 2 and 4 is completed.

According to FIG. 6, first, the failure sign diagnosis unit 150 obtains the actual operating time from the operating time calculation unit 120 and obtains the predicted operating time from the operating time prediction model unit 140 (step S401).

Next, the failure sign diagnosis unit 150 determines whether or not the actual operation time is greater than the sum of the predicted operation time and a threshold value _d1 based on the actual operation time and the predicted operation time acquired in step S401 (step S402). The threshold value _d1 is a parameter used to determine whether or not a failure may occur in the air compressor 210 or its associated devices, based on the actual operation time and the predicted operation time of the air compressor 210, as will be described in detail later.

If a positive result is obtained in step S402 (YES in step S402), the actual operating time of the air compressor 210 is too long compared to the predicted operating time, and therefore it can be determined that an abnormality (failure) may occur in the air compressor 210 or related equipment. Therefore, the failure sign diagnosis unit 150 adds 1 to the value of the failure sign counter, which is a parameter held by the unit 150 (step S403), and proceeds to step S404.

On the other hand, if a negative result is obtained in step S402 (NO in step S402), the actual operating time of the air compressor 210 is within the normal range relative to the predicted operating time, and therefore no signs of an abnormality (failure) occurring in the air compressor 210 or related equipment are detected. Therefore, the failure sign diagnosis unit 150 initializes the value of the failure sign counter to "0" (step S406) and proceeds to step S407.

In step S404, the failure sign diagnosis unit 150 determines whether the value of the failure sign counter is greater than a threshold value _d2 (step S404). Although details will be described later, the threshold value _d2 is a parameter used to determine whether there is a sign of a failure in the air compressor 210 or its associated devices, from the value of the failure sign counter.

If the value of the failure sign counter is greater than the threshold value _d2 in step S404 (YES in step S404), the value of the failure sign counter has reached the detection criterion for the failure sign. Then, the failure sign diagnosis unit 150 notifies a predetermined notification means or its control means that a failure sign has been detected, and the predetermined notification means or control means issues a warning (failure sign alert) corresponding to the detection of the failure sign to a predetermined notification destination such as a driver, an operation commander, or an inspection and maintenance area (step S405). Details of the notification of the failure sign alert will be described later. After step S405, the process proceeds to step S407.

On the other hand, if the value of the failure sign counter is equal to or less than the threshold value _d2 in step S404 (NO in step S404), the value of the failure sign counter is equal to or greater than 1 but has not yet reached the detection standard for a failure sign. Therefore, the failure sign diagnosis unit 150 does not issue a failure sign alert at this stage, and proceeds to step S407.

Then, in step S407, the failure sign diagnosis unit 150 stores the current value of the failure sign counter in a specified memory area, and then ends the process.

(1-5-1) Threshold _d1
The threshold value _{d1 is} a parameter for determining whether the actual operation time is an abnormal value with respect to the predicted operation time, and indicates a standard for the allowable excess time of the actual operation time from the predicted operation time.

As a method of calculating the threshold value _d1 , for example, when the average value of the accumulated data is used in calculating the reference operating time A in the above-mentioned formula 1, the standard deviation σ of the accumulated data may be calculated, and a value that is considered to be an outlier in statistics (such as 3σ) may be used as the threshold value _d1 .

Furthermore, for example, if the maximum value W _max and minimum value W _min of the air compression performance W [kPa/sec] of the air compressor 210 in a normal state are known in advance, the threshold value d ₁ may be calculated from the following equation 2.

In addition, when it is known that there is a range between the values of the starting pressure _Pmin and the stopping pressure _Pmax of the air compressor 210, for example, " _Pmin ± _ΔP1 " and " _Pmax ±ΔP2 _" , the threshold value _d1 may be calculated from the following equation 3 using the values of _ΔP1 and _ΔP2 .

Furthermore, when the maximum value _Wmax and minimum value _Wmin of the air compression performance W and the above-mentioned _ΔP1 and _ΔP2 are all known, the threshold value _d1 may be calculated from the following formula 4.

(1-5-2) Threshold _d2
The details of the threshold value _d2 will be described. The threshold value _d2 is a parameter for determining whether a phenomenon in which the actual operation time is excessively long compared to the predicted operation time (specifically, a phenomenon in which the actual operation time is longer than the predicted operation time by the threshold value _d1 or more) occurs continuously, and indicates a standard for the number of continuous occurrences of the above phenomenon.

The value of threshold d2 is determined from the train operation plan so that if the actual operating time is continuously longer than the predicted operating time by at least threshold d1 in data that comprehensively includes conditions such as station intervals and time periods, a malfunction can be detected.

In addition, in order to detect a sudden failure such as when an object collides with an air pipe and causes a crack, if the actual operating time indicates a value that significantly exceeds the value obtained by multiplying the predicted operating time by the threshold value _d1 (for example, a value twice the threshold value _d1 ), the value of the threshold value _d2 may be set to a number of times less than the above-mentioned threshold value _d2 (for example, two or three times).

(1-5-3) Notification of a failure sign alert The following describes in detail a method for notifying a failure sign alert. The failure sign alert is a function in which, when the failure sign diagnosis unit 150 detects a failure sign in the air compressor 210, a predetermined notification means or its control means notifies the driver, the operation commander, or the inspection and maintenance department by displaying on a screen or emitting an audio sound that the failure sign in the air compressor 210 has been detected.

For example, if the failure sign diagnosis device 100 is installed on a train, it outputs a failure sign alert to a vehicle information control device (not shown), and the vehicle information control device displays a screen on the display in the cab indicating that a failure sign has been detected. Also, the failure sign diagnosis device 100 may directly display a screen on the display in the cab indicating that a failure sign has been detected. Also, if the failure sign diagnosis device 100 has a function to transmit the aggregated vehicle data of the vehicle information control device to a ground system in an operation command or inspection area using public wireless communication or the like, the failure sign alert may be included in the vehicle data and transmitted to the ground system, so that the failure sign alert may be notified through a screen on the ground system or the like. Furthermore, if the failure sign diagnosis device 100 is implemented on a ground system in an operation command or inspection area, the failure sign alert may be displayed on a screen on the ground system or the like.

As described above, according to the failure sign diagnosis device 100 of the first embodiment, even if the air compressor 210 is operated during the operation of the vehicle (train), it is possible to accurately estimate the operation time (predicted operation time) of the air compressor 210. Furthermore, the failure sign diagnosis device 100 has a function of calculating the amount of compressed air used by related devices that use the compressed air generated by the air compressor 210 during the operation of the air compressor 210, and a function of considering the degree of influence of the amount of compressed air used by each related device on the predicted operation time. By having these functions, the failure sign diagnosis device 100 can determine that a failure sign has occurred in the air compressor 210 or its related devices (e.g., the brake device ₂₂₀ or the air spring 230) when the actual operation time of the air compressor 210 indicates a value longer than the predicted operation time by at least the threshold value d ₁ for a certain period of time or more (continuously up to the number of times equal to the threshold value d 2).

Thus, the failure prediction diagnosis device 100 according to this embodiment is capable of consistently and accurately detecting and diagnosing signs of abnormalities (failures) in the air compressor 210, which operates at various times while the vehicle is traveling, or in each associated device that uses the compressed air generated by the air compressor 210, without being limited by the vehicle's operational and linear conditions.

(2) Second embodiment (2-1) configuration FIG. 7 is a block diagram showing a configuration example of a failure sign diagnosis device 100 according to a second embodiment of the present invention. As shown in FIG. 7, the configuration of the failure sign diagnosis device 100 according to the second embodiment is the same as the configuration shown in FIG. 1 in the first embodiment. As a difference from the first embodiment, in the second embodiment, a vehicle equipped with an air compressor 210 has an air door device 240 that uses compressed air to open and close the door. That is, in the second embodiment, a door device 240 is added to the brake device 220 and air spring 230 similar to those in the first embodiment as related devices that use the compressed air generated by the air compressor 210, and data is input from the door device 240 to the data input unit 110.

In general rail vehicles, the pressure value of the air tank that stores the compressed air used by the door device 240 is often not measured. In such cases, pressure data cannot be obtained from the door device 240. Therefore, in the second embodiment, the data input unit 110 obtains door opening/closing information as input data from the door device 240.

In the failure sign diagnosis device 100 according to the second embodiment configured as described above, the operating time calculation unit 120 and the failure sign diagnosis unit 150 are similar in both configuration and processing to those of the first embodiment, so a description thereof will be omitted. In addition, the data input unit 110, the integrated pressure displacement calculation unit 130, and the operating time prediction model unit 140 will be described, focusing on the differences from the first embodiment.

(2-2) Processing of Data Input Unit 110 In the second embodiment, the data input unit 110 inputs operation data from the air compressor 210, pressure data (BC pressure value, AS pressure value) from the braking device 220 and the air spring 230, and opening/closing data from the door device 240. The opening/closing data is information indicating the open/closed state of the door in the door device 240. In addition, the data input unit 110 outputs operation data of the air compressor 210 to the operation time calculation unit 120 and the integrated pressure displacement amount calculation unit 130, and outputs pressure data (BC pressure value, AS pressure value) of the braking device 220 and the air spring 230 and opening/closing data (open/closed) of the door device 240 to the integrated pressure displacement amount calculation unit 130.

(2-3) Processing of the integrated pressure displacement amount calculation unit 130 The processing of the integrated pressure displacement amount calculation unit 130 in the second embodiment will be described with reference to Fig. 8. Fig. 8 is a flowchart showing an example of the processing procedure of the integrated pressure displacement amount calculation unit 130 in the second embodiment. In Fig. 8, the same processes as those in Fig. 3 described in the first embodiment are denoted by the same reference numerals, and detailed description thereof will be omitted.

According to FIG. 8, first, the integrated pressure displacement calculation unit 130 acquires operation data (operating/stopped) of the air compressor 210, the BC pressure value of the brake device 220, the AS pressure value of the air spring 230, and opening/closing data of the door device 240 from the data input unit 110 (step S501).

The processing in the following steps S202 to S205 is the same as the processing in steps S202 to S205 in FIG. 3. After processing in step S205, the process proceeds to step S502.

In step S502, the integrated pressure displacement calculation unit 130 determines whether the open/close state of the door device 240 has changed from closed to open based on the open/close data acquired in step S201. If the open/close state has changed from closed to open (YES in step S502), the process proceeds to step S503, and if the open/close state has not changed from closed to open (NO in step S502), the process proceeds to step S206.

In step S503, the integrated pressure displacement calculation unit 130 adds 1 to the value of the number of door openings, which is a parameter held by the unit 130, and proceeds to step S206.

In step S206, as described in FIG. 3, the integrated pressure displacement calculation unit 130 determines whether the operation state of the air compressor 210 has changed from operating to stopped based on the operation data acquired in step S201. If the operation state has changed from operating to stopped (YES in step S206), the process proceeds to step S504, and if the operation state has not changed from operating to stopped (NO in step S206), the process ends.

In step S504, the integrated pressure displacement calculation unit 130 outputs the current integrated BC pressure displacement, integrated AS pressure displacement, and door opening count to the operating time prediction model unit 140. The integrated pressure displacement calculation unit 130 then initializes the integrated pressure displacement and door opening count values of each associated device managed by the unit 130 to "0" (step S505), and ends the process.

(2-4) Processing of the operating time prediction model unit 140 In the second embodiment, the processing procedure of the processing executed by the operating time prediction model unit 140 is similar to the processing procedure example shown in Fig. 4 in the first embodiment. However, since the prediction model used in the second embodiment is different, the following describes changes to the prediction model.

In the second embodiment, the operation time prediction model unit 140 can calculate the predicted operation time of the air compressor 210 by using, for example, the following Equation 5.

In formula 5, _Yt [seconds] is the predicted operating time, A [seconds] is the reference operating time, _Xn [kPa] is the integrated pressure displacement of related device n, and _αn [seconds/kPa] is the influence of related device n. These are the same as the prediction model formula explained in formula 1 in the first embodiment. Furthermore, in formula 5, the influence _β1 [seconds/times] is the influence of the number of door openings, and the number of door openings _Z1 [times] is the value of the number of door openings.

The influence degree β ₁ is a parameter indicating the extension amount [seconds] of the operation time of the air compressor 210 per one door opening in the door device 240. The influence degree β ₁ can be calculated in the same manner as the influence degree α _n of the integrated pressure displacement amount described in the first embodiment. Specifically, for example, the influence degree β 1 may be calculated in advance using regression learning or the like in which the actual operation time for a certain period and the door opening number at that time are used as learning data. For example, as illustrated in FIG. 5, when the integrated pressure displacement amount of other related equipment is "0", the door opening number in that situation and the operation time at that time may be accumulated for a certain period, an approximation formula may be calculated by a known method such as the least squares method, and the value of the slope in the approximation formula may be determined as the influence degree β _1. The above-mentioned certain period is a period during which data including comprehensively the operation (station interval, type) expected for the vehicle (train) on which the air compressor 210 is mounted can be obtained.

As described above, according to the failure sign diagnosis device 100 of the second embodiment, the related devices included in the failure sign diagnosis target are not limited to only the first related devices from which pressure data can be obtained, such as the brake device 220 and the air spring 230, but even if a second related device from which pressure data cannot be obtained, such as the door device 240, is included, the predicted operating time of the air compressor 210 can be calculated taking into account the degree of influence of the first and second related devices on the operating time of the air compressor 210. That is, according to the failure sign diagnosis device 100 of the second embodiment, in a vehicle equipped with various related devices, it is possible to accurately estimate the operating time and always accurately diagnose the failure sign of the air compressor 210 or its related devices based on the estimated operating time without being limited by the operation and linear conditions of the vehicle.

In the above explanation, only the door device 240 is shown as the second related device from which pressure data cannot be acquired. However, the failure sign diagnosis device 100 according to the second embodiment can accurately diagnose failure signs even when multiple second related devices are connected. In such a case, specifically, the predicted operating time is calculated using Equation 5 with the additional term "β×Z" corresponding to each second related device, and failure signs are detected and diagnosed based on the calculated predicted operating time and actual operating time.

(3) Third embodiment A third embodiment of the present invention will be described. In the anomaly detection method disclosed in the above-mentioned Patent Document 1, a boundary line serving as a guide for judging anomaly detection is calculated using data from one year after the start of operation of a specific vehicle. However, such a method cannot take into account individual differences between vehicles or differences in characteristics when the same type of vehicle runs on different railway lines, and there is a risk that the accuracy of diagnosis will decrease if the method is applied to a vehicle other than the vehicle for which the boundary line was calculated. In view of such a problem, in the third embodiment of the present invention, a failure sign diagnosis device is provided that can accurately detect and diagnose a failure sign of an air compressor or its related equipment without being affected by individual differences between vehicles or differences in railway lines on which the vehicle is introduced.

(3-1) Configuration Fig. 9 is a block diagram showing an example of the configuration of a failure sign diagnosis device 300 according to a third embodiment of the present invention. As shown in Fig. 9, the failure sign diagnosis device 300 includes a data input unit 310, an operation time calculation unit 320, an integrated pressure displacement amount calculation unit 330, an operation time prediction model unit 340, a failure sign diagnosis unit 350, and a model update unit 360.

Furthermore, the failure sign diagnosis device 300 in FIG. 9 is connected to an air compressor 210, a brake device 220, and an air spring 230 as devices to be diagnosed for failure signs, similar to the failure sign diagnosis device 100 shown in FIG. 1 in the first embodiment. Note that FIG. 9 is an example, and the number of related devices of the air compressor 210 connected to the failure sign diagnosis device 300 may be one or more. Furthermore, the related devices may be devices from which pressure data cannot be obtained, such as the door device 240 shown in the second embodiment.

The data input unit 310 has the same configuration as the data input unit 110 described in the first embodiment.

The operating time calculation unit 320 has the same configuration as the operating time calculation unit 120 described in the first embodiment, except that it outputs the calculated actual operating time to the failure sign diagnosis unit 350 and the model update unit 360.

The integrated pressure displacement calculation unit 330 has the same configuration as the integrated pressure displacement calculation unit 130 described in the first embodiment.

The operating time prediction model unit 340 inputs the accumulated pressure displacement (accumulated BC pressure displacement, accumulated AS pressure displacement) of each related device from the accumulated pressure displacement calculation unit 330, inputs the influence value of each accumulated pressure displacement from the model update unit 360, and calculates the predicted operating time of the air compressor 210 using a predetermined prediction model based on the input information. Furthermore, the operating time prediction model unit 340 outputs the calculated predicted operating time to the failure sign diagnosis unit 350, and outputs the calculated predicted operating time and the accumulated pressure displacement and influence value of each related device in the prediction model used to calculate the predicted operating time to the model update unit 360. Details of the processing by the operating time prediction model unit 340 will be described later.

The failure sign diagnosis unit 350 inputs the actual operating time from the operating time calculation unit 320 and the predicted operating time from the operating time prediction model unit 340, and performs a diagnosis of failure signs based on the input information. Furthermore, the failure sign diagnosis unit 350 outputs the results of the failure sign diagnosis to the driver or the vehicle depot, and outputs the value of the diagnosis status to the model update unit 360. In this description, the diagnosis status takes the value of "0", "1", or "2" depending on the status, but other values indicating other statuses may be prepared. Details of the processing by the failure sign diagnosis unit 350 will be described later.

The model update unit 360 inputs the actual operating time from the operating time calculation unit 320, inputs the values of each impact and feature in the prediction model and the predicted operating time from the operating time prediction model unit 340, and inputs the value of the diagnosis state from the failure sign diagnosis unit 350. The model update unit 360 then updates the values of each impact in the prediction model based on this input information, and outputs the updated values of each impact to the operating time prediction model unit 340. Details of the processing by the model update unit 360 will be described later.

In the failure sign diagnosis device 300 configured as described above, the processing by the data input unit 310, the operating time calculation unit 320, and the integrated pressure displacement calculation unit 330 is the same as in the first embodiment, so detailed explanations will be omitted. Below, detailed explanations will be given of the operating time prediction model unit 340, the failure sign diagnosis unit 350, and the model update unit 360, which perform processing different from that in the first embodiment.

(3-2) Processing by the Operation Time Prediction Model Unit 340 FIG. 10 is a flowchart showing an example of the processing procedure by the operation time prediction model unit 340.

According to FIG. 10, first, the operating time prediction model unit 340 acquires the accumulated pressure displacement amount (e.g., the accumulated BC pressure displacement amount and the accumulated AS pressure displacement amount) of each related device output from the accumulated pressure displacement amount calculation unit 330, and acquires the influence degree values α' ₁ to α' _n corresponding to each accumulated pressure displacement amount from the model update unit 360 (step S601).

Next, the operating time prediction model unit 340 updates the influence levels α1 to αn in the prediction model formula of Equation 1 to the values α' ₁ to α' _n acquired in step S601 (step S602).

Next, the operating time prediction model unit 340 substitutes the accumulated pressure displacement amount obtained in step S601 into the prediction model equation of Equation 1 to calculate the predicted operating time (step S603).

Then, the operating time prediction model unit 340 outputs the predicted operating time calculated in step S603 to the failure sign diagnosis unit 150, and outputs the predicted operating time and the integrated pressure displacement amounts X1 to Xn and the influence degrees α1 to αn of each related device used in calculating the predicted operating time to the model update unit 360 (step S604), and the process ends.

(3-3) Processing by the Failure Sign Diagnosis Unit 350 Fig. 11 is a flowchart showing an example of the processing procedure by the failure sign diagnosis unit 350. In Fig. 11, the same processes as those in Fig. 6 described in the first embodiment are denoted by the same reference numerals, and detailed description thereof will be omitted.

According to FIG. 11, first, the failure sign diagnosis unit 350 obtains the actual operating time from the operating time calculation unit 320 and obtains the predicted operating time from the operating time prediction model unit 340 (step S401).

Next, the failure sign diagnosis unit 350 determines whether the actual operation time is greater than the predicted operation time plus a threshold value _d1 based on the actual operation time and predicted operation time acquired in step S401 (step S402). The threshold value _d1 is a parameter calculated in the same manner as the threshold value _d1 described in the first embodiment. If the actual operation time is greater than the predicted operation time plus the threshold value _d1 in step S402 (YES in step S402), the failure sign diagnosis unit 350 increments the value of the failure sign counter by 1 (step S403) and proceeds to step S701.

In step S701, the failure symptom diagnosis unit 350 sets the value of the diagnosis status to "0." A diagnosis status of "0" indicates that a failure symptom has been detected in the current cycle, and that for diagnosis purposes, it is necessary to continue to monitor whether the failure symptom continues to occur thereafter.

Following step S701, the failure sign diagnosis unit 350 determines whether the value of the failure sign counter is greater than the threshold value _d2 (step S404). If the value of the failure sign counter is greater than the threshold value _d2 in step S404 (YES in step S404), the failure sign diagnosis unit 350 notifies a failure sign alert to a predetermined notification destination such as the driver, the operation commander, or the inspection and maintenance area (step S405), and proceeds to step S407. On the other hand, if the value of the failure sign counter is equal to or less than the threshold value _d2 in step S404 (NO in step S404), the failure sign alert is not notified, and the process proceeds to step S407. The details of the determination in step S404 and the process according to the determination result are as described in the first embodiment.

In step S402, if the actual operation time is equal to or less than the value obtained by adding the threshold value _d1 to the predicted operation time (NO in step S402), the process proceeds to step S702.

In step S702, the failure sign diagnosis unit 350 determines whether the value of the failure sign counter is greater than "0". If the value of the failure sign counter is greater than "0", i.e., "1" or "2" (YES in step S702), the failure sign diagnosis unit 350 sets the diagnostic state value to "2" (step S703) and proceeds to step S406. The diagnostic state of "2" indicates a state in which a failure sign detected in the previous cycle was not detected in the current cycle, and thus may have been a false detection. On the other hand, if the value of the failure sign counter is "0" (YES in step S702), the failure sign diagnosis unit 350 sets the diagnostic state value to "1" (step S704) and proceeds to step S406. The diagnostic state of "1" indicates a normal state in which a failure sign has not been detected, or a false detection state in which a failure sign has not been detected (also called "undetected" to distinguish it from other false detections) in which a failure sign has not been detected, since no failure sign was detected in the current cycle following the previous cycle.

In step S406, the failure sign diagnosis unit 350 initializes the value of the failure sign counter to "0" and proceeds to step S407.

In step S407, the failure sign diagnosis unit 350 stores the current value of the failure sign counter in a specified memory area.

Finally, the failure sign diagnosis unit 350 outputs the value of the current diagnosis state to the model update unit 360 (step S705) and ends the process.

(3-4) Processing by the Model Update Unit 360 Fig. 12 is a flowchart showing an example of the processing procedure of the processing by the model update unit 360. The processing in Fig. 12 is started after the processing in step S705 in Fig. 11 .

According to FIG. 12, first, the model update unit 360 obtains the actual operating time from the operating time calculation unit 320, obtains the predicted operating time and the accumulated pressure displacement amount and impact degree of each related device from the operating time prediction model unit 340, and obtains the diagnosis status from the failure sign diagnosis unit 350 (step S801).

Next, the model update unit 360 determines the value of the diagnostic state acquired in step S801 (step S802). The diagnostic state value is one of "0", "1", and "2". If the diagnostic state value is "0", the process proceeds to step S803; if the diagnostic state value is "1", the process proceeds to step S804; if the diagnostic state value is "2", the process proceeds to step S807.

If the diagnostic status is "0", a fault sign has been detected in the current cycle, and monitoring is ongoing to see whether it continues to occur thereafter. In this state, there is no need to change the parameters of the predictive model that detects fault signs. Therefore, in step S803, the model update unit 360 updates the predicted operating time, actual operating time, and integrated pressure displacement of each associated device that are stored in its own memory area to the values acquired in step S801, and ends the process.

When the diagnosis state is "1", it is a normal state where no fault sign is detected, or a false detection (undetected) state where no fault sign is detected. This false detection (undetected) state means that a fault sign cannot be detected (undetected) because a predicted operating time longer than expected is calculated due to individual differences in the vehicle. Taking these states into consideration, in step S804, the model update unit 360 determines whether the predicted operating time is greater than the value obtained by adding the threshold _d1 to the actual operating time. If the predicted operating time is greater than the value obtained by adding the threshold _d1 to the actual operating time (YES in step S804), this indicates a state in which the predicted operating time is too long and there is a risk of undetection, so the process proceeds to step S805. On the other hand, if the predicted operating time is equal to or less than the value obtained by adding the threshold _d1 to the actual operating time (NO in step S804), there is no problem with the predicted operating time and no need to change anything, so the process ends.

In step S805, the model update unit 360 calculates values X ₁ α ₁ to X _n α _n by multiplying the integrated pressure displacement amount of each related device acquired in step S801 by the corresponding influence degree, calculates the ratios γ ₁ to γ _n of the magnitude of each calculated value using the following equation 6, and proceeds to step S806.

式７において、α’_ｋ［秒／ｋＰａ］はある関連機器ｋの更新後の影響度、α_ｋ［秒／ｋＰａ］は関連機器ｋの更新前の影響度、Ｘ_ｋ［ｋＰａ］は関連機器ｋの積算圧力変位量、Ｙ_ｔ［秒］は予測稼働時間、Ｙ［秒］は実稼働時間である。閾値ｄ_１は、前述した閾値ｄ_１と同様である。 In step S806, the model update unit 360 updates the values of the influence levels α ₁ to α _n to influence levels α' ₁ to α' _k using the following equation 7 according to the ratios γ ₁ to γ _n of each related device calculated in step S805, and proceeds to step S809.

In Equation 7, α' _k [sec/kPa] is the influence of a certain related device k after updating, α _k [sec/kPa] is the influence of the related device k before updating, X _k [kPa] is the integrated pressure displacement of the related device k, Y _t [sec] is the predicted operating time, and Y [sec] is the actual operating time. The threshold value d ₁ is the same as the threshold value d ₁ described above.

When the diagnostic state is "2", there is a possibility that the failure sign detected in the previous cycle was a false positive. In this state, it is preferable to change the prediction model for detecting the failure sign, and it is necessary to calculate an updated value of the influence of the prediction model. Therefore, in step S807, the model update unit 360 calculates values X ₁ α ₁ to X _n α _n by multiplying the integrated pressure displacement amount of each related device stored in the memory area by the corresponding influence, calculates the ratios γ ₁ to γ _n of the magnitudes of each calculated value using the above-mentioned formula 6, and proceeds to step S808.

式８において、α’_ｋ［秒／ｋＰａ］は更新後の関連機器ｋの影響度、α_ｋ［秒／ｋＰａ］は更新前の関連機器ｋの影響度、Ｘ_ｋ［ｋＰａ］は関連機器ｋの積算圧力変位量、Ｙ_ｔ［秒］は予測稼働時間、Ｙ［秒］は実稼働時間である。閾値ｄ_１は、前述した閾値ｄ_１と同様である。 In step S808, the model update unit 360 updates the values of the influence levels α ₁ to α _n to influence levels α' ₁ to α' _k using the following equation 8 according to the ratios γ ₁ to γ _n of each related device calculated in step S807, and proceeds to step S809.

In Equation 8, α' _k [sec/kPa] is the influence of the related device k after the update, α _k [sec/kPa] is the influence of the related device k before the update, X _k [kPa] is the integrated pressure displacement of the related device k, Y _t [sec] is the predicted operating time, and Y [sec] is the actual operating time. The threshold value d ₁ is the same as the threshold value d ₁ described above.

Then, in step S809, the model update unit 360 outputs the updated influence degree α' _k of the related device k calculated in step S806 or step S808 to the operating time prediction model unit 340, and ends the process.

As described above, in the failure sign diagnosis device 300 according to the third embodiment, the diagnosis state is determined based on the relationship between the actual operating time and the predicted operating time and the detection status of the failure sign, and the parameters of the prediction model (the degree of influence of each related device on the operating time of the air compressor 210) are successively updated based on the diagnosis state, thereby updating the prediction model to one that takes into account the influence of individual differences between vehicles and differences in the line section in which the vehicle is introduced. Thus, the failure sign diagnosis device 300 according to the third embodiment can estimate the operating time of the air compressor 210 with high accuracy regardless of individual differences between vehicles and differences in the line section in which the vehicle is introduced, and can use this estimated operating time to accurately detect and diagnose the failure signs of the air compressor 210 or its related devices.

In the above description of the third embodiment, the brake device 220 and the air spring 230 capable of acquiring pressure data are considered to be the associated devices, as in the first embodiment. However, the third embodiment can be realized even when associated devices that cannot acquire pressure data are connected, as in the second embodiment.

The present invention is not limited to the above-described embodiment, but includes various modified examples. For example, the above-described embodiment has been described in detail to clearly explain the present invention, and is not necessarily limited to having all of the configurations described. Other aspects conceivable within the scope of the technical idea of the present invention are also included in the scope of the present invention. It is also possible to replace part of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. It is also possible to add, delete, or replace part of the configuration of each embodiment with other configurations.

Furthermore, the above-mentioned configurations, functions, processing units, processing means, etc. may be realized in hardware, in part or in whole, for example by designing them as integrated circuits. Furthermore, the above-mentioned configurations, functions, etc. may be realized in software by a processor interpreting and executing a program that realizes each function. Information such as the programs, tables, files, etc. that realize each function can be stored in a memory, a recording device such as a hard disk or SSD (Solid State Drive), or a recording medium such as an IC card, SD card, DVD, etc., or the programs, etc. may be distributed from an external server or cloud.

In addition, the control lines and information lines shown in the drawings are those that are considered necessary for explanation, and do not necessarily show all control lines and information lines on the product. In reality, it can be assumed that almost all components are interconnected.

REFERENCE SIGNS LIST 100, 300 Failure sign diagnosis device 110, 310 Data input unit 120, 320 Operation time calculation unit 130, 330 Accumulated pressure displacement calculation unit 140, 340 Operation time prediction model unit 150, 350 Failure sign diagnosis unit 210 Air compressor 220 Brake device 230 Air spring 240 Door device 360 Model update unit

Claims (11)

A failure sign diagnosis device that diagnoses a failure sign in an air compressor or a related device that uses compressed air generated by the air compressor, comprising:
a data input unit for inputting operation data of the air compressor and pressure data of the related equipment;
an operation time calculation unit that calculates an actual operation time of the air compressor based on the operation data inputted to the data input unit;
an integrated pressure change amount calculation unit that calculates, for each of the related devices, an integrated pressure change amount that indicates an amount of compressed air used by the related device in response to the operation of the air compressor, based on the operation data and the pressure data inputted to the data input unit;
an operating time prediction model unit that calculates a predicted operating time of the air compressor from a prediction model that uses the integrated pressure displacement amount of each associated device calculated by the integrated pressure displacement amount calculation unit as a feature amount;
a failure sign diagnosing unit that diagnoses the presence or absence of a failure sign in at least one of the air compressor or the related equipment based on a comparison result between an actual operation time calculated by the operation time calculation unit and a predicted operation time calculated by the operation time prediction model unit;
A failure sign diagnosis device comprising: The failure sign diagnosis unit is
periodically comparing the actual operation time with the predicted operation time;
detecting a possibility of the failure symptom when the comparison shows that the actual operation time is longer than a total time of the predicted operation time and a first threshold value;
The failure sign diagnosing device according to claim 1 , further comprising: a diagnosis of the presence or absence of the failure sign based on a result of the detection of the possibility of the failure sign. The failure sign diagnosis unit is
3. The failure sign diagnosing device according to claim 2, further comprising a step of diagnosing the presence of the failure sign when the number of consecutive detections indicating the possibility of a failure sign exceeds a second threshold value. the prediction model calculates the predicted operating time by adding an additional operating time, which is an operating time of the air compressor added by operation of the related equipment, to a normal operating time of the air compressor in a configuration not affected by the related equipment;
4. The failure sign diagnosis device according to claim 2, wherein the additional operating time is calculated for each of the related devices by multiplying the feature amount of the related device by an influence degree determined by a predetermined method. In the case where the related devices include a first related device capable of acquiring pressure data and a second related device capable of acquiring predetermined operation data but not capable of acquiring pressure data,
5. The failure sign diagnosis device according to claim 1, wherein the operating time prediction model unit calculates a predicted operating time of the air compressor from the prediction model using the features of the first and second related devices, with the integrated pressure displacement calculated based on the pressure data as a feature of the first related device and the number of operations calculated based on the operation data as a feature of the second related device. If one of the first associated devices is a brake system, the pressure data for that first associated device is a brake cylinder pressure value;
If one of the first related devices is an air spring, the pressure data of the first related device is an air suspension pressure value;
6. The failure sign diagnosis device according to claim 5, wherein when one of the second related devices is a door device, the operation data of the second related device is door opening/closing information. 5. The failure sign diagnosis device according to claim 4, further comprising a model update unit that updates an influence degree of each of the related devices in the prediction model based on a result of comparison between the actual operation time and the predicted operation time. The model update unit is
When the actual operation time is equal to or less than the sum of the predicted operation time and the first threshold value, and the predicted operation time is longer than the sum of the actual operation time and the first threshold value,
8. The failure sign diagnosis device according to claim 7, wherein the degree of influence of each of the related devices is reduced in accordance with a weight of each feature amount in the predicted operating time. The failure sign diagnosis unit is
periodically comparing the actual operation time with the predicted operation time;
detecting a possibility of the failure symptom when the comparison shows that the actual operation time is longer than a total time of the predicted operation time and a first threshold value;
When the number of consecutive detections indicating that there is a possibility of a failure symptom exceeds a second threshold, the presence of the failure symptom is diagnosed;
the prediction model calculates the predicted operating time by adding an additional operating time, which is an operating time of the air compressor added by operation of the related equipment, to a normal operating time of the air compressor in a configuration not affected by the related equipment;
the additional operating time is calculated for each of the related devices by multiplying the feature amount of the related device by an impact degree determined by a predetermined method;
a model update unit that updates an influence degree of each of the related devices in the prediction model based on a comparison result of the actual operation time and the predicted operation time,
The model update unit is
when the actual operation time is equal to or less than a sum of the predicted operation time and the first threshold value and the predicted operation time is longer than a sum of the actual operation time and the first threshold value, reducing the influence degree of each of the related devices in accordance with a weight of each feature amount in the predicted operation time;
2. The failure sign diagnosis device according to claim 1, wherein, when the actual operation time becomes equal to or less than the sum of the predicted operation time and the first threshold value before a state detected by the failure sign diagnosis unit as possibly being a failure sign occurs consecutively more than the second threshold value, the influence of each of the related devices is increased in accordance with a weight of each feature amount in the predicted operation time. 10. The failure sign diagnosing device according to claim 1, wherein the failure sign diagnosing unit is configured to notify an alert to a predetermined output destination when it has diagnosed the presence of the failure sign. A failure sign diagnosis method by a failure sign diagnosis device for diagnosing a failure sign in an air compressor or a related device that uses compressed air generated by the air compressor, comprising:
a data input step in which the failure sign diagnosis device inputs operation data of the air compressor and pressure data of the related equipment;
an operation time calculation step in which the failure sign diagnosis device calculates an actual operation time of the air compressor based on the operation data inputted in the data input step;
an integrated pressure change amount calculation step in which the failure sign diagnosis device calculates, for each of the related devices, an integrated pressure change amount indicating an amount of compressed air used by the related device in response to the operation of the air compressor, based on the operation data and the pressure data inputted in the data input step;
an operation time prediction step in which the failure sign diagnosis device calculates a predicted operation time of the air compressor from a prediction model using the integrated pressure displacement amount of each related device calculated in the integrated pressure displacement amount calculation step as a feature amount;
a failure sign diagnosing step in which the failure sign diagnosing device diagnoses the presence or absence of a failure sign in at least one of the air compressor or the related equipment based on a comparison result between the actual operation time calculated in the operation time calculating step and the predicted operation time calculated in the operation time predicting step;
A failure sign diagnosis method comprising:

Images