JP2018121378A - Method for detecting abnormality of running motor for railway vehicle - Google Patents

Abstract

PROBLEM TO BE SOLVED: To achieve a method for detecting an abnormality of a running motor for a railway vehicle that can detect occurrences of abnormalities of the running motor with high accuracy, utilizing equipment monitoring data of the railway vehicle, without being affected by differences in conditions such as an ambient temperature and a boarding rate.SOLUTION: The method for detecting an abnormality of a running motor for a railway vehicle includes: a first step of receiving and memorizing temperature information on the running motor and electric current value information on the running motor collected by a data collection system mounted on the railway vehicle; a second step of calculating an RMS value (a root-mean-square of accumulated electric current values) during predetermined time on the basis of the memorized electric current value information on the running motor; and a third step of calculating a regression line by a multiple regression analysis, using at least the RMS value and the square of the RMS value as explanatory variables and the temperature of the running motor as a dependent variable, and performing a process for determining a state of the running motor, using the calculated regression line and the temperature information and the electric current value information collected at the first step.SELECTED DRAWING: Figure 7

Description

  The present invention relates to a method for detecting an abnormality by monitoring the state of a drive induction motor in order to prevent a failure of a drive induction motor (travel motor) in an electric vehicle of a railway vehicle.

In an electric car (electric car), if the parts of the drive induction motor deteriorate or fail due to long-term operation, or if the cooling capacity decreases due to the adhesion of dust, etc., abnormal heat generation occurs and the function stops. There is a risk of hindering train operation. In addition, if the drive induction motor is repaired after a failure, the maintenance cost increases.
Therefore, conventionally, an abnormality detection technique has been proposed in which a maintenance request is made after grasping that the cooling capacity of the induction motor for driving an electric vehicle has decreased (Patent Document 1).

  An abnormality detection technique for an induction motor for driving an electric vehicle disclosed in Patent Document 1 is based on a torque current in an electric vehicle using an induction motor driven by a VVVF (variable voltage variable frequency control) type inverter device. Based on the command value and the actual torque current value, the secondary resistance correction value of the induction motor is calculated to correct the secondary resistance. The corrected secondary resistance value, the reference secondary resistance value, and the rotor material of the induction motor To estimate the rotor temperature of the induction motor based on the rotor temperature coefficient determined by, and to prompt maintenance when the estimated temperature exceeds the set temperature that requires maintenance, and to prevent overload of the induction motor The value is corrected or the induction motor is temporarily opened.

  On the other hand, as a technique for analyzing the measured data to determine the state of the device, a data storage unit for storing actual vehicle data, and a first feature amount by obtaining a singular value decomposition of the simulation data and determining the actual vehicle data An SVD processing unit that performs value decomposition to obtain a second feature value, converts the first feature value into a first Mahalanobis distance, and determines the state of the train control device based on the first Mahalanobis distance; The abnormality determination threshold value is set, the second feature value is converted into the second Mahalanobis distance, and the state of the train control device is determined based on the comparison result between the second Mahalanobis distance and the abnormality determination threshold value. There is an invention in which the determination is made (Patent Document 2).

JP-A-11-262102 JP 2013-55777 A

  The abnormality detection technique for an induction motor for driving an electric vehicle disclosed in Patent Document 1 estimates the rotor temperature of the induction motor, and detects an abnormality by comparing the estimated temperature with a constant threshold value. Therefore, although it is possible to prevent the occurrence of a serious failure of the induction motor, the threshold value for detecting an abnormality is set by the maximum temperature allowed by design, so it may be set too low. Can not.

On the other hand, drive induction motors for railway vehicles (hereinafter referred to as travel motors) differ in the way they generate heat depending on the outside air temperature, boarding rate, etc., and when the load on the travel motor is low, dust or the like adheres. Even if the cooling performance of the traveling motor is reduced due to the above, the estimated temperature may not reach the threshold value for detecting an abnormality. Therefore, there is a problem that it is difficult to detect the occurrence of an abnormality at an early stage by simply monitoring the temperature of the electric motor using the abnormality detection technique disclosed in Patent Document 1.
The present invention has been made in order to solve the above-described problems, and the use of railway vehicle equipment monitoring data can generate an abnormality in a travel motor without being affected by differences in conditions such as outside air temperature and boarding rate. An object of the present invention is to provide an abnormality detection method capable of detecting with high accuracy.

  The invention disclosed in Patent Document 2 is similar to the present invention in that the actual vehicle data is acquired and accumulated, the motor current value is selected as the actual vehicle data, and the acquired data is analyzed statistically. However, the abnormality detection target is not a traveling motor but an abnormality in the train control device, and since simulation data is used, it is necessary to perform a simulation in advance or during analysis. The present invention is different from the present invention described below in that it is determined using the Mahalanobis distance.

In order to solve the above problems, an abnormality detection method for a railway vehicle travel motor according to the present invention includes:
A first step of receiving and storing estimated temperature information of the traveling motor and current value information of the traveling motor collected by a data collection system mounted on the railway vehicle;
A second step of calculating, for each traveling motor, an RMS value (root mean square of accumulated current value) based on the stored traveling motor current value information;
A regression line is calculated by multiple regression analysis using at least the RMS value and the square of the RMS value as explanatory variables and the estimated temperature of the traveling motor as a dependent variable, and the calculated regression line and the estimated temperature information collected in the first step And a third step for performing a process of determining the state of the traveling motor using the current value information.

  According to the above method, the current value information of the traveling motor is collected, the RMS value at a predetermined time is calculated, the regression line is calculated by the multiple regression analysis method using the RMS value and the square of the RMS value as an explanatory variable, and the calculation is performed. Because the travel motor state is judged using the collected regression line and the collected estimated temperature information and current value information of the travel motor, the occurrence of the travel motor abnormality is high without being influenced by the difference in conditions such as the boarding rate. It can be detected with accuracy.

Preferably, in the third step, the regression line includes a population in a graph in which samples are plotted with the temperature information collected in the first step and the RMS value calculated in the second step as parameters. The boundary line is set by parallel movement to the position to be performed.
In this way, a boundary line is set at a position including the group, and the state of the traveling motor is determined using the set boundary line and the collected temperature information and current value information. It can be detected with higher accuracy.

Preferably, in the process of determining the state of the traveling motor in the third step, the number of times that the temperature information collected in the first step and the RMS value calculated in the second step exceed the boundary line. Is determined, and it is determined whether or not the count value is larger than a predetermined number of times set in advance. When the count value is larger than the predetermined number of times set in advance, information notifying abnormality is output.
In this way, the number of times that the temperature information and the RMS value degree exceed the boundary line are counted, and it is determined whether the count value is larger than a predetermined number of times set in advance. It is possible to determine whether or not an abnormality has occurred with a simple process, and to improve the reliability of the determination result and notification.

  Further preferably, in the process of determining the state of the traveling motor in the third step, a change rate of the number of times exceeding the boundary line is calculated, and whether or not the change rate is larger than a predetermined value set in advance. If the rate of change is larger than a predetermined value set in advance, information notifying abnormality is output.

  In this way, the rate of change of the number of times exceeding the boundary line is calculated, and whether or not the rate of change is larger than a predetermined value set in advance is determined and output based on the number of times by outputting information notifying abnormality. Compared to the case, the occurrence of abnormality can be detected and notified more quickly.

  In the calculation of the regression line by the multiple regression analysis in the third step, the calculation may be performed by further including the outside air temperature as an explanatory variable. By including the outside air temperature as an explanatory variable in the calculation of the regression line by multiple regression analysis, more accurate abnormality detection can be performed.

  Advantageous Effects of Invention According to the present invention, it is possible to detect the occurrence of an abnormality in a travel motor with high accuracy without being affected by differences in conditions such as outside air temperature and boarding rate using equipment monitoring data of a railway vehicle. There is.

It is the block diagram which showed schematic structure of the system which collects data required when implementing the abnormality detection method of the traveling motor for rail vehicles which concerns on this invention. (A) is a graph showing the transition of the daily maximum value of the estimated temperature of the traveling motor obtained in a test on a normal business train, (B) is the frequency of the daily maximum value of the estimated temperature of the traveling motor, the horizontal axis Is a graph showing the estimated temperature. It is a graph which shows transition of 1 day of each data of the estimated temperature of the motor obtained by the driving | running | working test, external temperature, boarding rate, motor current value, and vehicle speed. (A) is a graph showing the collected data (sample) with the instantaneous current value and the estimated temperature of the traveling motor as parameters, and (B) is the 2-hour RMS value calculated from the collected data and the estimated temperature of the traveling motor. It is a graph which shows the relationship between the point plotted as a parameter, and the boundary line used for determination. It is the graph which plotted the collected data as a parameter in the RMS value and driving | running | working motor estimated temperature at the time of changing accumulation time. It is a graph which shows 1-day transition of each data obtained by the running test, and the calculated 2 hour RMS value. It is a flowchart which shows the procedure of the process in the abnormality detection method of the traveling motor for rail vehicles which concerns on one Embodiment of this invention. It is a figure which shows the idea of the design of the threshold value in the abnormality detection method of the traveling motor for rail vehicles which concerns on embodiment.

Hereinafter, an embodiment of an abnormality detection method for a railway vehicle travel motor according to the present invention will be described with reference to the drawings.
The abnormality detection method for a railway vehicle travel motor according to the present invention grasps the state of the travel motor of each electric vehicle based on temperature data collected in a traveling train, and the travel motor quickly generates abnormal heat. The occurrence of abnormality is detected at the stage. A configuration of a data collection system necessary for abnormality detection and a structure of a travel motor abnormality detection system that determines and notifies the state of the travel motor based on the data collected by the system will be described first with reference to FIG.

FIG. 1 shows an outline of a system 10 that collects data from a running train and an abnormality detection system 20 that detects an abnormality of a traveling motor based on the collected data.
As shown in FIG. 1, each vehicle A, B, C... Of a train of trains is equipped with a traveling motor 11 and a driving VVVF inverter 12 at a ratio of one to several vehicles. (Vehicle B in the figure) is connected, and the VVVF inverter 12 is provided with a controller (control device) CNT. The data collection system 10 in the present embodiment is configured to collect temperature data from the VVVF inverters 12 of each electric vehicle using a data transmission path 13 provided in the train.

  The collected motor temperature may be an actual value measured by the temperature sensor, but the location where the temperature sensor for detecting the temperature of the motor is installed has severe environmental conditions. There is difficulty in property and service life. On the other hand, in the VVVF inverter 12 of the electric vehicle in this embodiment, the controller CNT calculates the secondary resistance correction value of the induction motor based on the torque current command value and the actual torque current value by software processing, and the corrected secondary resistance The rotor temperature of the induction motor is estimated by comparing the resistance value and the reference secondary resistance value.

  In this embodiment, the temperature data of the motor estimated by the controller CNT is acquired at a predetermined cycle (for example, 10 seconds) by the transmission terminal device 14B provided in the vehicle, and for example, the leading vehicle is transmitted via the data transmission path 13. The transmission is made to the central terminal device 15 provided in (No. 1 car).

Furthermore, since the controller CNT of the VVVF inverter 12 knows the magnitude of the current value flowing through the motor, the transmission terminal device 14B also acquires the current value information of the motor from the controller CNT and passes through the data transmission path 13. Transmit to the central terminal device 15.
The central terminal device 15 records temperature data and motor current value information collected via the data transmission path 13 together with electric vehicle identification information (car information) and a recording device 16 having a storage device such as a hard disk or semiconductor memory. And the transmission unit 17 having a wireless communication function is configured to periodically transmit the collected data to the ground side device 20.
The recording device 16 stores the identification information (train number) of the train. When the central terminal device 15 transmits the collected data, the train identification information together with the collected temperature data and motor current value data. And the electric vehicle identification information are transmitted. The recording device 16 may be a server.

  The traveling motor abnormality detection system 20 includes a data receiving unit 21 that receives the collected data transmitted from the transmission unit 17 of the data collection system 10 on the upper side of the vehicle, and data such as a hard disk or semiconductor memory that stores the received collected data. A storage unit 22 is provided. Further, the travel motor abnormality detection system 20 analyzes the received data (temperature data and current value data) and calculates a boundary line as a threshold value that is a determination criterion for abnormality detection; A determination processing unit 24 that compares the calculated boundary line with the collected data to determine an abnormal state of the traveling motor, a result storage unit 25 that stores the determination result, and alert (alarm) information as external portable information An alert transmission unit 26 that transmits to the terminal 30 or the like is provided.

Note that the functions of the boundary line calculation unit 23 and the determination processing unit 24 are an arithmetic device such as a CPU (microprocessor), a storage device such as a ROM or a RAM, an input device such as a keyboard, and an output device such as a display device. And a program stored in the storage device. Since the hardware configuration itself of such a personal computer is self-evident, its illustration is omitted.
Next, details of the boundary line calculation process and the motor abnormality detection determination process in the abnormality detection system 20 for the traveling motor will be described together with the process leading to the development of the present invention.

Prior to the development of the traveling motor abnormality detection system of the present invention, the present inventors conducted a test to obtain the estimated temperature of the traveling motor in the traveling train from the controller of the VVVF inverter for about six months.
FIG. 2 (A) shows the transition of the maximum daily value of the estimated temperature of the travel motor obtained in the test on a normal business train, with the horizontal axis indicating the day. FIG. 2B shows the frequency of the daily maximum value of the estimated temperature of the travel motor with the estimated temperature on the horizontal axis.

From Fig. 2, the maximum estimated temperature of the motor is 150 ° C, and it is possible to detect an abnormality in the running motor by comparing the maximum value and the threshold set by the maximum temperature allowed by design. It turns out that it is. However, the maximum estimated temperature varies greatly depending on the outside air temperature, motor load, that is, the occupancy rate and driving conditions (vehicle speed, etc.), etc. Conceivable.
Then, in order to perform a statistical analysis, in addition to the estimated temperature of the traveling motor, a test was performed in which the outside air temperature, the boarding rate, the motor current value, and the vehicle speed were acquired from the traveling train. In addition, since there is a method of converting from the measured value of a weighing scale that measures the weight of the vehicle body conventionally provided in the air spring, the occupancy rate is obtained by using it.

FIG. 3 shows the daily transition of each data obtained in the above test with time on the horizontal axis. From FIG. 3, a clear correlation between the estimated temperature of the traveling motor and other measurement items cannot be seen.
The present inventors consider that a traveling motor is a device that converts electrical energy into rotational energy, and a part of the loss is generated as heat and the motor temperature rises. A graph showing the relationship between the motor current value (instantaneous value) obtained in the above test and the estimated temperature was prepared by predicting that it was a promising explanatory variable. The graph is shown in FIG. FIG. 4A shows no correlation between the estimated temperature and the current value.

Then, the graph which shows RMS (root mean square) of the accumulated motor current value in a certain time, and shows the relationship with the estimated temperature was created. The graphs are shown in FIGS. In FIG. 5, (A) is the RMS of the cumulative current value for 0.5 hour, (B) is the RMS of the cumulative current value of 1 hour, (C) is the RMS of the cumulative current value of 2 hours, and (D) is The RMS of the accumulated current value for 3 hours is shown on the horizontal axis. Further, the calculated correlation coefficient ^{R 2} in each graph, the correlation coefficient of the graph of (A) ^{R 2} is 0.568, the correlation coefficient of the graph of (B) ^{R 2} is 0.716, (C) the correlation coefficient ^{R 2} graphs 0.777, the correlation coefficient ^{R 2} of the graph of (D) was 0.692. From this, it can be seen that the correlation between the RMS of the accumulated current value for 2 hours and the estimated motor temperature is the best.
Note that the accumulated time for calculating the RMS value is not uniquely determined, and is considered to vary depending on the vehicle type (body structure), the type (specification) of the motor (induction motor) used, traveling conditions, etc. Can be determined by conducting a test.

FIG. 6 shows the daily transition of the 2-hour cumulative current value RMS calculated from the motor current value (instantaneous value) obtained in the above test, with other measurement items (estimated temperature, outside air temperature, boarding rate, motor current). Value, vehicle speed) along with the daily transition. Comparing the estimated temperature with the 2-hour RMS value, it can be seen that the overall trend of rising and falling is consistent and correlated.
Next, the inventors set the estimated motor temperature as a dependent variable (objective variable) for the data obtained in the above test, and the 2-hour RMS value IRMS of the motor current and the squared RMS of the RMS value as explanatory variables. ² and the outside air temperature Ta were selected and a multiple regression analysis was performed.

The multiple regression equation using IRMS, IRMS ² and Ta, which are the above three explanatory variables, is the following equation. Dependent variable (motor estimated temperature) = a + b × IRMS ² + c × IRMS + d × Ta (1)
Indicated by
Next, by performing statistical processing by multiple regression analysis using the measured values for about half a year acquired at a cycle of 10 seconds by the test, the constant a and the coefficients b, c, d in the above formula (1) are used. It was determined. As a result, the following model formula: Estimated motor temperature = -19.702 + 0.001 x IRMS ² + 1.683 x IRMS-0.025 x Ta (2)
was gotten. Note that the values of the constant a and the coefficients b, c, d in the above formula (1) may be determined by calculating a regression line by the least square method, but various software having multiple regression analysis functions are commercially available. So you can get it using it.
From the above model equation (2), it can be seen that the coefficient of the term of the outside air temperature Ta is as small as 0.025, and even if this term is ignored, no significant error occurs.

  FIG. 4B shows a regression line D represented by an equation in which the term of the outside air temperature Ta in the above model equation is omitted from the graph of FIG. 5C showing the relationship between the estimated temperature and the 2-hour RMS value. This is a schematic representation of the object. In the present invention, this regression line D is translated substantially upward or in a direction orthogonal to the regression line D to a position that includes a group, that is, all samples (actual measurement values), and this is the boundary for the determination of abnormality detection. The line (threshold value) E was used. Further, a threshold line F based on the actual maximum value may be provided, and a boundary line constituted by the regression line D and the minimum value of the threshold line F may be provided. The amount of parallel movement is not uniquely determined, and varies depending on the vehicle type (body structure), the type (specification) of the motor (induction motor) used, the running conditions, etc. Just decide.

  FIG. 4B shows a line represented by the equation (2) in a graph in which the sample (actually measured value) is plotted on three-dimensional coordinates using the estimated motor temperature, the accumulated motor current value RMS, and the outside air temperature as parameters. Can be regarded as being projected onto two-dimensional coordinates using the estimated motor temperature and the accumulated motor current value RMS as parameters. From this, the regression line represented by the expression that does not omit the term of the outside air temperature Ta in the expression (2) is moved upward to a position including the group to determine the boundary line. It turns out that it is also possible.

The present inventors have developed a traveling motor abnormality detection method as described below from the analysis results and test results.
FIG. 7 is a flowchart illustrating a procedure of processes executed by the boundary calculation unit 23 and the determination processing unit 24 of the abnormality detection system 20 for the travel motor illustrated in FIG. In addition, when the train to be detected includes a plurality of electric vehicles, the processing described below may be executed for each electric vehicle (travel motor), or may be executed for each vehicle type or line section. .

  As shown in FIG. 7, the travel motor abnormality detection system 20 first determines whether the vehicle (train) to be evaluated is within one year from the start of business (step S1). The reason for judging within one year from the start of business is that it is desirable to obtain the actual data from the operation of the running motor in the normal state as basic data for judgment and to obtain the data for the whole year (all seasons). It is. In addition, since the abnormality detection method of a present Example is for detecting the generation | occurrence | production of the abnormality by deterioration of a traveling motor at an early stage, if the data for a full year can be acquired, the data acquisition for vehicles within one year from the start of business will be performed. It is not limited to.

If it is determined in the above step S1 that it is within one year from the start of business (Yes), the process proceeds to step S2 to start calculation processing of a boundary line serving as a threshold, and 4 hours or more have elapsed since the start. Judge whether or not. If it is determined that four hours or more have not elapsed (No), the processing is terminated without performing calculation for calculating the boundary line. As can be seen from the graph of FIG. 3, the temperature of the motor is not stable until about 4 hours have passed.
If it is determined in step S2 that four hours or more have passed since the start (Yes), the process proceeds to step S3, and it is determined whether or not the vehicle is traveling. When it is determined that the vehicle is not in business travel (No), the process is terminated without performing calculation for calculating the boundary line. This is because performance data during business travel is used as basic data for judgment.

  If it is determined in step S3 that the vehicle is traveling in business (Yes), the process proceeds to step S4 to start calculation processing of a boundary line serving as a threshold, and first, the 2-hour RMS value of the current value of the traveling motor is calculated. . Subsequently, the regression line D in FIG. 4B is calculated using the above-described model formula by the method of multiple regression analysis using the calculated RMS value, and the regression line D is translated to the center. A boundary line E including the group is determined (step S5), the boundary line information is stored in the storage device, and the process is terminated (step S6). Further, the threshold line F shown in FIG. 4B may be determined and stored based on the maximum value of the performance data.

On the other hand, if it is determined in the first step S1 that the vehicle to be evaluated is not within one year from the start of business (No), the process proceeds to step S7 to start the determination process, and whether or not four hours have passed since the start. to decide. If it is determined that four hours or more have not elapsed (No), the processing is terminated without performing calculation for calculating the boundary line.
If it is determined in step S7 that four hours or more have elapsed since the start (Yes), the process proceeds to step S8, and it is determined whether or not the vehicle is traveling. When it is determined that the vehicle is not in business travel (No), the process is terminated without performing calculation for calculating the boundary line.

If it is determined in step S8 that the vehicle is traveling in business (Yes), the process proceeds to step S9, and the 2-hour RMS value of the current value of the traveling motor is calculated.
Thereafter, the process proceeds to step S10, the calculated value is compared with the boundary line information stored in the storage device in step S6, and the number of times of exceeding the boundary line is counted (step S11). Then, it is determined whether or not the number of times of exceeding the boundary line (count value) is equal to or greater than a predetermined number of times (step S12). Here, if it is determined that the number of times of crossing the boundary line (count value) is equal to or greater than the predetermined number of times (Yes), the process proceeds to step S13 to issue an alert (or issue an alarm), and then to step S17. Then, the determination result is stored in the storage device, and the process ends.

  If it is determined in step S12 that the number of times that the boundary line has been exceeded (count value) is not equal to or greater than the predetermined number (No), the process proceeds to step S14 to calculate the rate of change of the count value (comparison with the previous day). It is determined whether or not the rate of change is greater than or equal to a predetermined threshold (step S15). If it is determined that the calculated rate of change is equal to or greater than the threshold (Yes), the process proceeds to step S16, an alert is transmitted, the process proceeds to step S17, and the determination result is stored in the storage device. The process ends. By determining whether or not the rate of change is greater than or equal to a predetermined value (step S15), if the rate of change of the number of times suddenly increases even if the number of times of crossing the boundary line is small, an alert is sent and attention is paid Can be encouraged.

FIG. 8A shows an image of the determination in step S12, FIG. 8B shows an image of the determination in step S15, and the horizontal axis shows the date.
Even before the traveling motor breaks down, as the traveling motor deteriorates, the amount of heat generation increases and the temperature rises, and the number of times that the boundary line is exceeded gradually increases. Moreover, it is expected that the rate of change in the number of times will gradually increase as the traveling motor deteriorates. In the flowchart of the abnormality detection process for the traveling motor shown in FIG. 7, the number of times exceeding the boundary line gradually increases as shown in FIG. 8 (A) and exceeds the predetermined number, or the number of times as shown in FIG. 8 (B). When the rate of change of the vehicle suddenly increases and exceeds a predetermined value, an alert is transmitted. Therefore, the occurrence of abnormality can be notified by accurately grasping a sign of a failure of the traveling motor.

  Although the invention made by the present inventor has been specifically described based on the embodiment, the present invention is not limited to the embodiment. For example, in the flowchart of FIG. 7, an alert is issued when it is determined in step S12 that the number of times the boundary has been exceeded is greater than or equal to a predetermined number, or in step S15 that the rate of change in the number of times is greater than or equal to a threshold value. But when it is determined in step S12 that the number of times the boundary has been exceeded is greater than or equal to a predetermined number and in step S15 it is determined that the rate of change of the number is greater than or equal to a threshold value (logical condition is satisfied) An alert may be sent at a time.

Further, in the traveling motor abnormality detection method of the above embodiment, when calculating the boundary line, the regression line is calculated by omitting the term of the outside air temperature in the model formula calculated by including the outside air temperature as an explanatory variable by the multiple regression analysis. Although it is determined, the regression line may be determined based on a model formula including the outside air temperature as an explanatory variable. Further, the boundary line may be determined by calculating the regression line including the vehicle speed in the explanatory variable in the multiple regression analysis.
Moreover, in the abnormality detection method for the travel motor of the above embodiment, when the coefficient is determined using the multiple regression equation (1), the estimated temperature calculated by the controller of the VVVF inverter is used as the motor temperature. You may make it use the motor temperature measured using the temperature sensor.

10 Data collection system 20 Ground side device (abnormality detection system)
DESCRIPTION OF SYMBOLS 11 Traveling motor 12 VVVF inverter 13 Data transmission path 14A, 14B, 14C Transmission terminal device 15 Central terminal device 16 Recording device 17 Transmission unit 21 Data receiving part 22 Data storage part 23 Boundary line calculation part 24 Judgment processing part 25 Result storage part 26 Alert dispatcher

Claims (5)

A first step of receiving and storing travel motor temperature information and travel motor current value information collected by a data collection system mounted on a railway vehicle;
A second step of calculating, for each traveling motor, an RMS value (root mean square of accumulated current value) based on the stored traveling motor current value information;
A regression line is calculated by multiple regression analysis using at least the RMS value and the square of the RMS value as explanatory variables and the temperature of the traveling motor as a dependent variable, and the calculated regression line and the temperature information and current collected in the first step A third step of performing a process of determining the state of the traveling motor using the value information;
An abnormality detection method for a railway vehicle travel motor, comprising:   In the third step, the regression line is translated to a position including a group in a graph in which samples are plotted with the temperature information collected in the first step and the RMS value calculated in the second step as parameters. The abnormality detection method for a railway vehicle travel motor according to claim 1, wherein the boundary line is set.   In the process of determining the state of the traveling motor in the third step, the number of times the temperature information collected in the first step and the RMS value calculated in the second step exceed the boundary line are counted, 3. The railway vehicle according to claim 2, wherein it is determined whether or not the count value is larger than a predetermined number of times set, and information notifying abnormality is output when the count value is larger than a predetermined number of times set in advance. An abnormality detection method for a traveling motor.   In the process of determining the state of the traveling motor in the third step, a change rate of the number of times exceeding the boundary line is calculated, it is determined whether or not the change rate is larger than a predetermined value, 4. The method for detecting an abnormality of a railway vehicle travel motor according to claim 3, wherein information indicating an abnormality is output when the rate is larger than a predetermined value set in advance. The travel motor is an induction motor driven by a variable voltage variable frequency control type inverter device, and the inverter device is configured to estimate a rotor temperature of the induction motor and perform current control based on the estimated rotor temperature. ,
The abnormality detection method for a railway vehicle travel motor according to claim 1, wherein the temperature information in the first step is information on the estimated rotor temperature.

Images