System and method for diagnosing abnormalities in electric motor bearings for railway vehicles

Abstract

To provide an abnormality diagnostic system and a method of an electric motor bearing for a railway vehicle capable of highly accurately obtaining the influence of train operation on vibration of a bearing of an electric motor for a railway vehicle from various aspects.SOLUTION: An abnormality diagnostic system of a bearing of an electric motor for a railway vehicle includes an input unit for obtaining bearing vibration information of the electric motor for driving the railway vehicle and vehicle position information of the railway vehicle, a diagnostic database which links the bearing vibration information and the vehicle position information and records them, and an arithmetic unit. The arithmetic unit groups the bearing vibration information into a plurality of groups by using the vehicle position information and records them in the diagnostic database.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a system and method for diagnosing an abnormality in a bearing of an electric motor for a railway vehicle, and more particularly to a method for diagnosing an abnormality in a bearing of an electric motor for a railway vehicle while the train is in operation, using data acquisition and diagnosis criteria linked to position information. [Background technology]

[0002] Various bearing maintenance systems and abnormality diagnosis systems have been proposed for railway vehicles, and Patent Document 1 is particularly known as a management system for bearing usage status linked to location information. Patent Document 1 states, "The railway vehicle is equipped with a GPS receiver and a communication device that wirelessly transmits the received location information. An external usage status management device is provided, and this usage status management device is equipped with a mileage calculation means that calculates the traveling distance of the railway vehicle based on data transmitted from the transmitter of the railway vehicle. The railway vehicle is further equipped with a temperature sensor that measures the temperature of each axle bearing, and the measured temperature is transmitted to the usage status management device by the communication device." [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2016-210209 A Summary of the Invention [Problem to be solved by the invention]

[0004] There is a real-time monitoring technology for detecting and diagnosing abnormalities in railroad vehicle bearings. In this case, there is a concern that the amount of data would be enormous if real-time data were acquired for the entire line. Also, in urban areas with many points, mountainous areas with many slopes, or lines including railway bridges, the accuracy of vibration diagnosis may decrease due to disturbances depending on the operating environment. Furthermore, railway motors are used under conditions where there is a temperature difference between the inside and outside of the bearings depending on the environment. This temperature change affects the viscosity of the grease, and is therefore considered to affect the vibration change of the motor. In this way, vibrations due to environmental factors in specific sections or specific rail wheels may lead to misdiagnosis.

[0005] As a real-time monitoring technique, there is a method for managing bearing usage status using position information using GPS, as shown in Patent Document 1. In Patent Document 1, vehicle speed, movement history, and travel distance are recorded and transmitted using GPS. In addition, the bogie bearing temperature is also recorded and transmitted. However, it is not possible to perform vibration diagnosis excluding environmental factors such as disturbances in specific sections (such as points) and vibration changes due to changes in outside air temperature.

[0006] According to Patent Document 1, position information and vibration information are linked and the effect of bogie bearing temperature is also taken into consideration, but no consideration is given to a multifaceted analysis of the effect that train operation has on the vibration of the bearings of railway vehicle electric motors.

[0007] In view of the above, the present invention aims to provide an abnormality diagnosis system and method for railway vehicle electric motor bearings that targets bearings of railway vehicle electric motors and makes it possible to determine with high accuracy from multiple angles the effect that train operation has on the vibration of railway vehicle electric motor bearings. [Means for solving the problem]

[0009] The present invention also provides a system for detecting the bearing vibration of a motor that drives a railway vehicle and vehicle position information of the railway vehicle, comprising: an input unit that acquires bearing vibration information of an electric motor that drives a railway vehicle and vehicle position information of the railway vehicle; a diagnostic database that records the bearing vibration information and the vehicle position information in association with each other; and a calculation unit, the input unit acquires train operation information, the calculation unit classifies the bearing vibration information into a first plurality of groups using the vehicle position information and the train operation information, the input unit acquires weather information, the calculation unit classifies the bearing vibration information into a second plurality of groups using the vehicle position information and the weather information, the first plurality of groups include a running distance, a running section, and a number of round trips along the running section for the train, and the second plurality of groups include a region, a season, and an outside temperature in which the vehicle is running,The calculation unit classifies the bearing vibration information into a plurality of groups using vehicle position information, records the grouped information in a diagnostic database, and performs abnormality diagnosis of the bearings of the electric motor that drives the railway vehicle using the bearing vibration information belonging to a group specified by the input unit.

[0011] The present invention also provides a method for obtaining bearing vibration information of a motor that drives a railway vehicle and vehicle position information of the railway vehicle, linking the bearing vibration information and the vehicle position information and recording the information, obtaining train operation information, and classifying the bearing vibration information into a first plurality of groups using the vehicle position information and the train operation information; obtaining weather information, and classifying the bearing vibration information into a second plurality of groups using the vehicle position information and the weather information; the first plurality of groups including a running distance, a running section, and a number of round trips along the running section for the train; and the second plurality of groups including a region, a season, and an outside temperature in which the vehicle is running; The present invention provides a method for diagnosing an abnormality in a bearing of an electric motor for a railway vehicle, the method comprising: classifying bearing vibration information into a plurality of groups using vehicle position information; and diagnosing an abnormality in the bearings of the electric motor that drives the railway vehicle using the bearing vibration information belonging to a specified group. Effect of the Invention

[0012] According to the present invention, it is possible to provide an abnormality diagnosis system and method for railway vehicle electric motor bearings, which targets the bearings of railway vehicle electric motors and makes it possible to determine with high accuracy from multiple angles the effect that train operation has on the vibration of the bearings of railway vehicle electric motors.

[0013] Furthermore, according to the embodiments of the present invention, it is possible to perform a diagnosis excluding sections with a lot of disturbance vibration, and it is possible to perform a diagnosis that takes into account factors that affect vibration, such as outside temperature, thereby improving the accuracy of vibration diagnosis. [Brief description of the drawings]

[0014] [Figure 1] 1 is a diagram showing an example of the configuration of a railway vehicle electric motor bearing abnormality diagnosis system according to the present invention; [Diagram 2] 4 is a flowchart showing information input-related processing executed by a CPU in the diagnostic device. [Diagram 3] 6 is a flowchart showing the processing executed by a CPU in the diagnosis device for grouping bearing vibration information corresponding to position information. [Figure 4]6 is a flowchart showing the processing steps executed by a CPU in the diagnostic device for grouping bearing vibration information in accordance with geographical environment information. [Diagram 5] FIG. 13 is a diagram showing an example of information stored in a diagnostic database DB as groupings of bearing vibration information corresponding to position information. [Figure 6] FIG. 13 is a diagram showing an example of information stored in a diagnostic database DB as groupings of bearing vibration information corresponding to geographic environment information. [Figure 7a] FIG. 11 is a diagram showing an example of grouping of bearing vibration information corresponding to position information. [Figure 7b] FIG. 11 is a diagram showing an example of grouping of bearing vibration information corresponding to geographical environment information. [Figure 8] 4 is a flowchart showing diagnostic processing among the processing contents executed by a CPU in the diagnostic device. [Figure 9] FIG. 13 is a diagram for explaining the advantage of grouping driving-related diagnostic items. [Figure 10] A diagram to explain the advantages of grouping diagnostic items into geographical environment-related items. [Figure 11] FIG. 13 shows diagnostic examples based on a combination of multiple items. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. EXAMPLES

[0016] FIG. 1 is a diagram showing an example of the configuration of a railway vehicle electric motor bearing abnormality diagnosis system according to the present invention.

[0017] The abnormality diagnosis system is configured to diagnose railway vehicles 10 owned by a railway operator 1 by a diagnosis device 20 owned by a service provider 2, and to achieve this, it is preferable to obtain meteorological information D3 from a weather service company 3 and train operation information D4 from a train operation management system in the railway operator 1. Note that the railway operator 1 and the service provider 2 may be the same company.

[0018] Of these, the railway vehicle 10 to be diagnosed is equipped with position detection means 14, such as a GPS, for detecting vehicle position information D2 indicating the vehicle's position, vibration sensors S (S1 to S4 in the illustrated example) for detecting the vibration of the bearings of the main motor 12 attached to the vehicle bogie 11 as motor bearing vibration information D1, and information communication means 15 for transmitting the detected information D1, D2 to the service provider 2.

[0019] A diagnostic device 20 owned by the service provider 2 and configured with a computer is configured with an input / output section 21 that inputs information from various places and outputs information that has been processed into an appropriate format, and a memory section including a RAM 22, a ROM 23, a common bus 24, and a CPU 25. Calculations in the CPU 25 are performed according to a program stored in the ROM 23, and the CPU 25 is further connected to a diagnostic database DB that accumulates and stores the input information, the processed secondary information, and the final output information.

[0020] 2 is a flowchart showing information input related processing executed by the CPU 25 in the diagnostic device 20. In this flow, first, in processing step St1, information D1, D2 transmitted by the information communication means 15 in the railway vehicle 10 is stored in the database DB. Note that this information may be obtained online from a vehicle currently in operation and used to immediately execute the subsequent diagnostic processing, or may be obtained as detection information for each vehicle accumulated for a certain period of time on the railway business operator 1 side. However, these pieces of information D1, D2 include the detection time and information related to the detected vehicle (vehicle name, main motor name, etc.), and are considered to be information that can be linked to each other. Linking based on this time information and the like is also performed for the various subsequent pieces of information D3, D4.

[0021] The service provider 2 may obtain information passively from the railway business operator 1, or may actively approach the railway business operator 1 depending on the result of the service provider 2's judgment and present the conditions for obtaining information. For example, when it is known from the position information that the vehicle is traveling in a tunnel, or when the conditions for obtaining information are met, the diagnostic system may instruct the railway vehicle 10 to obtain information (or not). Alternatively, the diagnostic system may instruct the railway vehicle 10 to obtain information under conditions that are unlikely to cause vibration due to the terrain.

[0022] In processing step St2, train operation information D4 (route map, vehicle configuration, etc.) is provided from the train operation management system of the railway company 1, and this is stored in the database DB. Similarly, in processing step St3, meteorological information D3 (temperature, precipitation, snowfall information, etc.) is provided from the weather service company 3, and this is stored in the diagnostic database DB.

[0023] Processing steps St1 to St3 are processes at the information acquisition stage, and Fig. 3 shows a flowchart showing information grouping processing among the processing contents executed by CPU 25 in diagnosis device 20. Information grouping processing can be broadly divided into two processes. One is the idea of ​​grouping bearing vibration information corresponding to vehicle position information (first grouping), and the other is the idea of ​​grouping bearing vibration information corresponding to geographical environment information (second grouping). Note that it is preferable to execute both of the two groupings in combination.

[0024] 3, the flow chart for grouping bearing vibration information corresponding to vehicle position information shows that in processing step St11, vehicle position information D2, motor bearing vibration information D1, and train operation information D4 are obtained from diagnostic database DB. Note that the motor bearing vibration information D1 may be obtained at this time, or may be stored in the diagnostic database DB in advance.

[0025] In processing step St12, a judgment is made as to whether the motor bearing vibration information D1 is classified into a traveling-related diagnostic item or not, depending on the vehicle position information D2 and the train operation information D4. Here, the traveling-related diagnostic items are the traveling distance, traveling section, and number of round trips in the traveling section during vehicle operation, and these items can be determined from the vehicle position information D2 and the train operation information D4. The train operation information D4 includes information on the traveling distance, traveling section, and number of round trips in the traveling section for each train, and by comparing it with the vehicle position information D2, the current situation of the vehicle can be confirmed.

[0026] Incidentally, if there is an increase in the amount of motor bearing vibration information D1 classified here from the viewpoint of travel distance, the correlation between distance and vibration can be calculated, and motor bearing vibration information D1 that does not show the correlation can be suspected to be abnormal. Also, if there is an increase in the amount of motor bearing vibration information D1 classified here from the viewpoint of travel section, the correlation between speed and vibration in this section can be calculated, and motor bearing vibration information D1 that does not show the correlation can be suspected to be abnormal. Also, if there is an increase in the amount of motor bearing vibration information D1 classified here from the viewpoint of the number of round trips made on a travel section, the correlation between the start and stop of the train and vibration can be calculated, and motor bearing vibration information D1 that does not show the correlation can be suspected to be abnormal.

[0027] The classification process in the process step St12 may be performed continuously while the train is in operation, but since the amount of accumulated information would be enormous, it is better to sample and obtain the information when a condition matching some event is met. For example, this point of view may be when the mileage reaches 10,000 km, 20,000 km, or 40,000 km. In addition, it is better to classify the information together with information TP on the location and date and time when these events are met.

[0028] In process steps St13, St14, and St15 in FIG. 3, information on the travel distance, travel section, and number of round trips in the travel section when the event occurred (D5, D6, and D7) is stored together with information TP on the location and date and time when the event occurred, and is stored in the diagnostic database DB.

[0029] 4, the flow chart for grouping bearing vibration information corresponding to geographical environment information shows that in processing step St21, vehicle position information D2, motor bearing vibration information D1, and weather information D3 are obtained from diagnostic database DB. Note that the weather information D3 may be obtained at this time from weather service company 3, or may be stored in advance in diagnostic database DB.

[0030] In processing step St22, a judgment is made as to whether the electric motor bearing vibration information D1 is classified into a geographical environment-related diagnostic item or not classified into any of the items according to the vehicle position information D2 and the meteorological information D3. Here, the geographical environment-related diagnostic items are the region, season, and outside temperature in which the vehicle is traveling, and these items can be determined from the vehicle position information D2 and the meteorological information D3.

[0031] Incidentally, if there is a large amount of motor bearing vibration information D1 classified here from the regional viewpoint, the correlation between topography and vibration can be calculated, and motor bearing vibration information D1 that deviates from the correlation can be suspected to be abnormal. Also, if there is a large amount of motor bearing vibration information D1 classified here from the seasonal viewpoint, the correlation between weather and vibration in that season can be calculated, and motor bearing vibration information D1 that deviates from the correlation can be suspected to be abnormal. Also, if there is a large amount of motor bearing vibration information D1 classified here from the outdoor air temperature viewpoint, the correlation between air temperature and bearing temperature can be calculated, and motor bearing vibration information D1 that deviates from the correlation can be suspected to be abnormal.

[0032] The classification process in processing step St12 may be performed continuously while the train is in operation, but since the amount of accumulated information would be enormous, it is better to sample and obtain the information when a condition matching some event is established. For example, this viewpoint may be when the mileage reaches 10,000 km, 20,000 km, or 40,000 km. In addition, it is better to classify the information together with the location and date and time when these events are established. This makes it possible to link and view the running-related diagnostic items described in FIG. 3 and the geographical environment-related diagnostic items described in FIG. 4.

[0033] In the process steps St23, St24, and St25 in Fig. 4, the information on the region, season, and outside temperature at the time of the occurrence of the event (D8, D9, and D10) is stored together with the information TP on the location and date and time at which the event occurred, and stored in the diagnostic database DB. It goes without saying that other items may be added to the diagnostic database DB as appropriate.

[0034] In this way, the diagnostic database DB stores the information shown in Fig. 5 as groupings of bearing vibration information corresponding to position information. Fig. 5 is a diagram showing an example of grouping of bearing vibration information based on measurement position. In this example, bearing information D1 is grouped by route D11, by area D8, by travel distance D5, by travel section D6, or by the number of round trips in a travel section D7, based on vehicle position information D2.

[0035] For example, the routes D11 are grouped by each route (route A, route B, ..., etc.). The regions D8 are grouped by extracting urban areas, mountainous areas, areas with railway bridges, etc. for each route. The travel sections D6 are grouped by extracting travel sections with the same conditions, such as being flat and straight, for each route. The number of round trips in the travel section D6 is grouped by the number of round trips in a predetermined travel section for each route D11. It should be noted that when grouping, it is advisable to group the same vehicles and motors of the same model. This makes it possible to compare, for example, when the number of round trips in the travel section changes with the same vehicle and motor of the same model, improving the accuracy of the diagnosis.

[0036] In this way, the diagnostic database DB stores the information shown in Fig. 6 as groupings of bearing vibration information corresponding to geographical environment information. Fig. 6 shows an example of grouping vibration information D1 based on geographical environment information. Grouping is performed based on coast, flat terrain, many curves, gradient, dense residential area for region D8, wind strength, snowfall, rainfall for season D9, and time information stored in conjunction with location information for outside air temperature D10. This makes it possible to incorporate, for example, the relationship between outside air temperature, bearing temperature, and grease viscosity that change with the season into the diagnostic logic, enabling diagnosis that takes into account the impact of bearing temperature changes on bearing vibration.

[0037] Next, specific examples of grouping will be described with reference to Figures 7a and 7b. Figure 7a is an example of grouping of bearing vibration information corresponding to position information. In the example on the left, the line D11 is line A, and when the position and time date at this time are Tp1, the train's running distance D5 is 10,000 km, the running section D6 is a low-speed area before and after a station, and the number of round trips in the section D7 is less than 100 times. In the example second from the left, the line D11 is line A, and when the position and time date at this time are Tp2, the train's running distance D5 is 20,000 km, the running section D6 is a high-speed area with the maximum speed, and the number of round trips in the section D7 is 200 times. In the example in the center, the line D11 is line A, and when the position and time date at this time are Tp3, the train's running distance D5 is 20,000 km, the running section D6 is a high-speed area with the maximum speed, and the number of round trips in the section D7 is 200 times. In the second example on the right, line D11 is line A, the position and time date at this time are Tp4, the train's travel distance D5 is 20,000 km, the travel section D6 is a high-speed area where the train is at its maximum speed, and the number of round trips D7 is 200. In the example on the right, line D11 is line A, the position and time date at this time are Tp5, the train's travel distance D5 is 10,000 km, the travel section D6 is a low-speed area where the train is at its maximum speed, and the number of round trips D7 is less than 100.

[0038] In this example, the second from the right and the second from the left, or the left and right observation examples, are similar to each other and are therefore thought to essentially show similar vibration tendencies, and if the comparison results in a discrepancy, it is possible to diagnose some kind of abnormality.

[0039] Figure 7b shows an example of grouping bearing vibration information according to geographical environment information. In this example, area D8 on route A of route D11 is a terrain that changes from flat to sloping, and the season D9 includes areas with weak and strong winds, areas with heavy and light snowfall, and areas with heavy and light rainfall. Temperature D10 varies from 15 degrees to 5 degrees, and has other geographical and environmental characteristics on the route.

[0040] By the grouping process of FIGS. 3 and 4, the information of FIGS. 7a and 7b is linked to each other and stored in the diagnostic database DB.

[0041] Fig. 8 is a flowchart showing diagnostic processing among the processing contents executed by the CPU 25 in the diagnostic device 20. First, in processing step St31 in Fig. 8, the user operates the input / output unit 21 to specify the vehicle to be diagnosed and further the bearings of the main electric motor.

[0042] In addition, the user operates the input / output unit 21 to select an item to be diagnosed from among the driving-related diagnostic items and the geographical environment-related diagnostic items in processing step St32. This involves selecting at least one of the driving distance D5, driving section D6, number of round trips in the driving section D7, and the area D8, season D9, outside temperature D10, etc., which are classified as driving-related diagnostic items. When one item is selected, only this item is diagnosed, and when multiple items are selected, all of these are subject to diagnosis. In addition, in this selection, it is possible to select a composite element, and for example, it is possible to specify a diagnosis as the logical product of the driving distance D5, the area D8, and the season D9.

[0043] In process step St33, all past information on items matching the selected item is retrieved from the diagnostic database DB, and in process step St34, the correlation between each item and vibration is obtained by, for example, machine learning using the retrieved information. In process step St35, a diagnostic evaluation is performed on a specified portion of the vehicle bearing using the correlation relationship obtained by learning.

[0044] In this series of diagnostic evaluation processes, it is advisable to calculate diagnostic criteria according to the measurement position for these grouped bearing vibration information, and judge the bearing abnormality against the diagnostic criteria. Note that grouping, calculation of diagnostic criteria, and bearing abnormality diagnosis may be performed later, not at the time of measurement (real time). Also, it may be possible to determine whether or not to diagnose the bearing abnormality based on the measurement position.

[0045] It is also a good idea to identify the route schedule from position information and time information, and then identify the train formation from the schedule. For example, the load on the motor may differ near the stairs of the platform, due to high congestion levels. By identifying the position in the train formation where the train stops near the stairs using position information, it becomes possible to take the change in load on the motor into account in the vibration diagnosis, improving the accuracy of the diagnosis.

[0046] 9 and 10 are diagrams for explaining the advantages of grouping diagnostic items into driving-related and geographical environment-related diagnostic items, respectively. According to FIG. 9, for driving-related diagnostic items, if the driving distance is used, it is possible to calculate the correlation between distance and vibration. For example, since vibration increases when a certain distance is exceeded, it is possible to calculate the distance of increased vibration. If the driving section is used, it is possible to calculate the correlation between speed and vibration. For example, since vibration increases in sections driven at maximum speed, it is possible to identify sections with high vibration. If the number of round trips in a driving section is used, it is possible to calculate the correlation between starts / stops and vibration or bearing damage. For example, since frequent starts and stops may lead to increased bearing wear, it is possible to identify sections with frequent starts / stops.

[0047] Furthermore, according to Figure 10, for the geographical environment-related diagnostic items, if region is used, it is possible to calculate the correlation between topography and vibration; for example, to eliminate the influence of the environment, measurements can be made on flat terrain, and when there is a slope, the correlation between motor load, vibration, and bearing damage can be digitized. If season is used, it is possible to calculate the correlation between weather and vibration; for example, to eliminate the influence of the environment, measurements can be made on sunny days, and vibration trends can be digitized using information from adverse environments (heavy rain, heavy snow). If outside air temperature is used, it is possible to calculate the correlation between air temperature and bearing temperature.

[0048] Fig. 11 shows a diagnosis example based on a combination of multiple items, and all items are considered here. All reference items are taken into consideration when comprehensively evaluating factors that are thought to have influenced the vehicle vibration at each position, date and time, from TP1 to TP5. Past cases include cases with the same or similar conditions, and new evaluations are also possible by adding temperature conditions.

[0049] As described above, according to the present invention, it is possible to record bearing information of railway electric motors in association with the measurement location, store criteria for diagnosing bearing abnormalities in association with geographical information, read out the diagnostic criteria corresponding to the measurement location, and perform abnormality judgment, thereby improving the accuracy of bearing diagnosis of railway electric motors. [Explanation of symbols]

[0050] 1. Railway operators 2: Service providers 3. Weather service company 10:Railroad cars 11: Vehicle bogie 12: Main motor 14: Position detection means 15: Means of information and communication 20: Diagnostic equipment 21: Input / output section 22:RAM 23:ROM 24: Common bus 25: CPU D1: Motor bearing vibration information D2: Vehicle location information D3: Meteorological information D4:Train operation information DB: Diagnostic database S: Vibration sensor

Claims

1. an input unit that acquires bearing vibration information of an electric motor that drives a railway vehicle and vehicle position information of the railway vehicle, a diagnostic database that records the bearing vibration information and the vehicle position information in association with each other, and a calculation unit; The input unit obtains train operation information, and the calculation unit classifies the bearing vibration information into a first plurality of groups using the vehicle position information and the train operation information, The input unit obtains weather information, and the calculation unit classifies the bearing vibration information into a second plurality of groups using the vehicle position information and the weather information, The first plurality of groups include a running distance, a running section, and a number of round trips per running section for a train, The second plurality of groups includes a region, a season, and an outside temperature in which the vehicle is traveling; The calculation unit uses the vehicle position information to classify the bearing vibration information into a plurality of groups and record the groups in the diagnostic database, and performs abnormality diagnosis of the bearings of the electric motor that drives the railway vehicle using the bearing vibration information belonging to a group specified by the input unit.

2. A system for diagnosing an abnormality in a bearing of an electric motor for a railway vehicle as described in claim 1, The input unit obtains train operation information, and the calculation unit classifies the bearing vibration information into a first plurality of groups using the vehicle position information and the train operation information, The input unit obtains weather information, and the calculation unit classifies the bearing vibration information into a second plurality of groups using the vehicle position information and the weather information, The system for diagnosing an abnormality in a bearing of an electric motor for driving a railway vehicle, characterized in that the calculation unit uses the bearing vibration information belonging to multiple groups specified from the input unit to diagnose an abnormality in the bearings of the electric motor that drives the railway vehicle.

3. Acquire bearing vibration information of an electric motor that drives a railway vehicle and vehicle position information of the railway vehicle, and record the bearing vibration information and the vehicle position information in association with each other, obtaining train operation information, and classifying the bearing vibration information into a first plurality of groups using the vehicle position information and the train operation information; obtaining weather information and classifying the bearing vibration information into a second plurality of groups using the vehicle position information and the weather information; The first plurality of groups include a running distance, a running section, and a number of round trips per running section for a train, The second plurality of groups includes a region, a season, and an outside temperature in which the vehicle is traveling; A method for diagnosing an abnormality in a bearing of an electric motor for a railway vehicle, comprising: using the vehicle position information to group the bearing vibration information into a plurality of groups; and using the bearing vibration information belonging to a specified group to perform an abnormality diagnosis of the bearings of the electric motor that drives the railway vehicle.

4. A method for diagnosing an abnormality in a railway vehicle electric motor bearing as described in claim 3, comprising: obtaining train operation information, and classifying the bearing vibration information into a first plurality of groups using the vehicle position information and the train operation information; obtaining weather information and classifying the bearing vibration information into a second plurality of groups using the vehicle position information and the weather information; A method for diagnosing an abnormality in a bearing of an electric motor for driving a railway vehicle, comprising: diagnosing an abnormality in the bearing of an electric motor that drives a railway vehicle, using the bearing vibration information belonging to a plurality of specified groups.

Images