Vehicle inspection schedule planning system, vehicle inspection schedule planning method and vehicle inspection schedule planning program

Abstract

To provide a vehicle inspection schedule planning system that enables the planning of inspection schedules with earlier inspection dates by utilizing data acquired in a short period.SOLUTION: A vehicle inspection schedule planning system 1 comprises: a data acquisition unit 12 for acquiring data indicating the condition of railway vehicles; a normal range calculation unit 13 for calculating a normal range which is considered as a normal value for values to be acquired in the future as data; a deviation determination unit 14 for determining deviations of values acquired as data from the normal range; and an inspection schedule planning unit 15 for planning inspection schedules for railway vehicles on the basis of the deviation condition.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a vehicle inspection planning system, a vehicle inspection planning method, and a vehicle inspection planning program that plan inspections for railway vehicles. [Background technology]

[0002] Various inspections of railway vehicles are generally performed at intervals preset by railway operators, etc. In contrast, it is possible to observe the condition of the railway vehicle while it is in operation and set the inspection period earlier than the preset period depending on the condition of the railway vehicle. By advancing the inspection period depending on the condition of the railway vehicle, if an abnormality occurs in the railway vehicle, it becomes possible to detect the abnormality early. In order to accurately grasp the condition of the railway vehicle while it is in operation, it is desirable to analyze the data in real time, taking into account information indicating the status of the route on which the railway vehicle is traveling, etc. However, in the past, it was difficult to perform such data analysis in real time due to issues such as data processing speed.

[0003] Patent Document 1 discloses an abnormality sign diagnosis device that uses sensor data acquired at each sampling period to diagnose abnormality signs in mechanical equipment. The abnormality sign diagnosis device according to Patent Document 1 generates a model using sensor data corresponding to a period designated in accordance with maintenance information that identifies the mechanical equipment on which maintenance work will be performed and the maintenance work period as a learning target, and predicts abnormalities in the mechanical equipment based on the model. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2013-8092 Summary of the Invention [Problem to be solved by the invention]

[0005] In order to predict railway vehicle anomalies using data collected from railway vehicles or sensors installed on railway vehicles, the collected data must include data from actual occurrences of abnormalities. Unless data collection is carried out over a long period of time until a large amount of data required for learning or anomaly cases has been accumulated, it is difficult to generate a model that can accurately predict abnormalities.

[0006] When applying conventional technology that predicts abnormalities based on collected data, such as the technology disclosed in Patent Document 1, to the development of railway vehicle inspection plans, a problem arises in that, without data accumulated over a long period of time, it is not possible to develop an inspection plan that advances the inspection period depending on the condition of the railway vehicle.

[0007] The present disclosure has been made in consideration of the above, and aims to provide a vehicle inspection planning system that can create an inspection plan that advances the inspection date by using data acquired over a short period of time. [Means for solving the problem]

[0008] In order to solve the above-mentioned problems and achieve the objectives, the vehicle inspection planning system disclosed herein comprises a data acquisition unit that acquires data indicating the condition of a railway vehicle, a normal range calculation unit that calculates a normal range within which values ​​to be acquired as data in the future are considered to be normal values, a deviation determination unit that determines whether the values ​​acquired as data deviate from the normal range, and an inspection plan formulation unit that formulates an inspection plan for the railway vehicle based on the deviation situation. [Effects of the Invention]

[0009] The vehicle inspection planning system according to the present disclosure has the advantage of being able to create an inspection plan with an earlier inspection time by using data acquired over a short period of time. [Brief explanation of the drawings]

[0010] [Figure 1]FIG. 1 is a diagram showing an example of the configuration of a vehicle inspection planning system according to a first embodiment; [Figure 2] FIG. 1 is a diagram showing an example of an inspection plan acquired by an inspection plan acquisition unit of the vehicle inspection planning device according to the first embodiment; [Figure 3] FIG. 1 is a diagram showing an example of travel information acquired by a data acquisition unit of the vehicle inspection planning device according to the first embodiment; [Figure 4] FIG. 1 is a diagram showing an example of operational data acquired by a data acquisition unit of the vehicle inspection planning device according to the first embodiment; [Figure 5] 1 is a flowchart showing an example of an operation procedure performed by the vehicle inspection planning device according to the first embodiment. [Figure 6] FIG. 1 is a diagram for explaining a method for calculating a predicted value by a normal range calculation unit of the vehicle inspection planning device according to the first embodiment. [Figure 7] FIG. 1 is a diagram for explaining a method for calculating a normal range from a predicted value by a normal range calculation unit of the vehicle inspection planning device according to the first embodiment. [Figure 8] 1 is a flowchart showing an example of an operation procedure performed by a deviation determination unit of the vehicle inspection planning device according to the first embodiment. [Figure 9] FIG. 10 is a diagram showing an example of deviation situation information created by the inspection plan formulation unit of the vehicle inspection planning device according to the first embodiment. [Figure 10] FIG. 10 is a diagram showing a configuration example of a vehicle inspection planning system according to a second embodiment. [Figure 11] FIG. 10 is a diagram showing an example of deviation tendency information created by a deviation tendency learning unit of the vehicle inspection planning device according to the second embodiment; [Figure 12] 10 is a flowchart showing an example of an operation procedure of a vehicle inspection planning device according to a second embodiment. [Figure 13] FIG. 1 is a diagram showing an example of the configuration of a control circuit according to the first or second embodiment; DETAILED DESCRIPTION OF THE INVENTION

[0011] A vehicle inspection planning system, a vehicle inspection planning method, and a vehicle inspection planning program according to embodiments will be described in detail below with reference to the accompanying drawings.

[0012] Embodiment 1 FIG. 1 is a diagram showing an example of the configuration of a vehicle inspection planning system 1 according to a first embodiment. The vehicle inspection planning system 1 is a system that plans an inspection plan for a railway vehicle based on data indicating the condition of the railway vehicle. The vehicle inspection planning system 1 plans an inspection plan that brings forward the inspection period from the period indicated in a previously created inspection plan. Hereinafter, the term "vehicle" refers to a railway vehicle.

[0013] The vehicle inspection planning system 1 is realized by a vehicle inspection planning device 2. The vehicle inspection planning device 2 is a device installed in a vehicle depot 3. The vehicle depot 3 is a facility where multiple vehicles are stored.

[0014] The inspection system 4 is installed in the railroad depot 3. The inspection system 4 manages inspection plans created by the railway operator. The inspection plans managed by the inspection system 4 include inspection plans that are past plans and inspection plans that are future plans.

[0015] The traffic control system 5 is installed in the railway operation control center. The traffic control system 5 manages train operations. The traffic control system 5 manages data showing the status of trains. A dispatcher at the operation control center uses the traffic control system 5 to monitor the train operation status and give instructions to train crews or station staff.

[0016] The display terminal 6 is installed in the vehicle depot 3. The display terminal 6 displays information output by the vehicle inspection planning device 2. The display terminal 6 may display information output by the vehicle inspection planning device 2 and information output by a device or system other than the vehicle inspection planning device 2. For example, the display terminal 6 may display information output by the inspection system 4 or information output by the operation control system 5.

[0017] The vehicle inspection planning device 2 has an inspection plan acquisition unit 10, an inspection plan memory unit 11, a data acquisition unit 12, a normal range calculation unit 13, a deviation determination unit 14, an inspection plan formulation unit 15, and an inspection plan output unit 16.

[0018] The inspection system 4 outputs the inspection plan to the vehicle inspection planning device 2. The inspection plan acquisition unit 10 acquires the inspection plan from the inspection system 4. The inspection plan acquisition unit 10 stores the acquired inspection plan in the inspection plan storage unit 11. The inspection plan storage unit 11 stores the inspection plan.

[0019] The traffic management system 5 acquires data indicating the state of the vehicle from the vehicle or equipment installed on the vehicle. Hereinafter, the data indicating the state of the vehicle will be referred to as operation data. The traffic management system 5 outputs the operation data to the vehicle inspection planning device 2. The operation data is output linked to vehicle running information. The running information is various information about the operation of trains including the vehicle. The data acquisition unit 12 acquires the operation data and running information from the traffic management system 5. That is, the data acquisition unit 12 acquires data indicating the state of the vehicle and the running information of the vehicle.

[0020] The operational data acquired by the data acquisition unit 12 is input to the normal range calculation unit 13. The normal range calculation unit 13 calculates a normal range within which values ​​to be acquired in the future as operational data are considered to be normal values. The normal range calculation unit 13 predicts values ​​to be acquired in the future as operational data based on the operational data acquired by the data acquisition unit 12, and calculates a normal range based on the predicted values. The normal range calculation unit 13 outputs information indicating the calculated normal range to the deviation determination unit 14.

[0021] The normal range is a range that is considered to be normal for the values ​​of operational data. If the value acquired as operational data deviates from the normal range, it can be said that the vehicle may be in a state where an abnormality actually occurs or where signs of an abnormality are displayed. Note that, while a value deviating from the normal range as operational data is abnormal as an operational data value, it does not necessarily indicate that an abnormality has occurred or that signs of an abnormality are displayed. In other words, even if the value of operational data deviates from the normal range, there may be no abnormality or signs of an abnormality in the vehicle.

[0022] The operational data and driving information acquired by the data acquisition unit 12 are input to the deviation determination unit 14. The deviation determination unit 14 reads out an inspection plan from the inspection plan storage unit 11. The deviation determination unit 14 determines whether the value acquired as the operational data deviates from the normal range based on the operational data, the inspection plan, and information indicating the normal range. The deviation determination unit 14 outputs the determination result to the inspection plan formulation unit 15.

[0023] The inspection plan formulation unit 15 formulates an inspection plan for the vehicle based on the deviation status of the values ​​acquired as operational data from the normal range. The inspection plan formulation unit 15 formulates the inspection plan by advancing the scheduled inspection date for the vehicle based on the deviation status. The inspection plan formulation unit 15 outputs the formulated inspection plan to the inspection plan output unit 16. The inspection plan output unit 16 outputs the inspection plan formulated by the inspection plan formulation unit 15 to the display terminal 6.

[0024] In this way, the vehicle inspection planning device 2 creates an inspection plan for the vehicle based on the vehicle's operation data. The display terminal 6 displays the inspection plan created by the vehicle inspection planning device 2. As a result, the created inspection plan is notified to the workers who will inspect the vehicles at the vehicle depot 3.

[0025] Next, a description will be given of details of the inspection plan acquired by the inspection plan acquisition unit 10. Fig. 2 is a diagram showing an example of the inspection plan acquired by the inspection plan acquisition unit 10 of the vehicle inspection planning device 2 according to the first embodiment.

[0026] In the inspection plan shown in Figure 2, the vehicle number is linked to information on the route name, scheduled inspection date, and inspection items. The vehicle number is an identification number assigned to each of multiple vehicles. The route name is the name of the route on which the vehicle runs. The scheduled inspection date is the date on which the vehicle is scheduled to be inspected. The inspection items are the items to be inspected. Note that there are multiple items to be inspected for a vehicle.

[0027] 2, for example, the inspection plan for a vehicle with vehicle number "TR001" includes the following information: the route name "AB Line," the scheduled inspection date "2X01 / 7 / 2," and the inspection item "pantograph slider." This inspection plan indicates that the vehicle with vehicle number "TR001" is a vehicle that runs on the "AB Line," and that an inspection of the "pantograph slider" for this vehicle is scheduled for July 2, 2X01.

[0028] The inspection plan acquired by the inspection plan acquisition unit 10 is sufficient if it includes at least the information on the vehicle number, the scheduled inspection date, and the inspection items. The information on the line name may be omitted from the inspection plan. For example, if all the vehicles stored at the vehicle depot 3 run on a common line, the information on the line name may be omitted. The inspection plan acquired by the inspection plan acquisition unit 10 may also include information other than the above information.

[0029] Next, a description will be given of details of the travel information acquired by the data acquisition unit 12. Fig. 3 is a diagram showing an example of the travel information acquired by the data acquisition unit 12 of the vehicle inspection planning device 2 according to the first embodiment.

[0030] The running information is information organized by vehicle number. In Figure 3, the running information for each vehicle number is linked to each piece of information: running date, route name, train type, and formation number. The running date is the day the vehicle ran on the route. The train type is a name given to the train to distinguish the stations it stops at, etc. The formation number is a number given to the formation, including the vehicles.

[0031] In FIG. 3, for example, in the running information of a vehicle with vehicle number "TR001," the running date "2X01 / 6 / 28" is linked to the information on the route name "AB Line," the train type "rapid," and the train formation number "H101." This running information indicates that the vehicle with vehicle number "TR001" ran on the "AB Line" on June 28, 2X01, the train type at that time was "rapid," and the formation number of the formation including that vehicle was "H101." The data acquisition unit 12 acquires running information such as that shown in FIG. 3 for each of the multiple vehicles.

[0032] It should be noted that the running information acquired by the data acquisition unit 12 is sufficient as long as it includes at least the vehicle number. By linking the running information including the vehicle number to the operation data, the vehicle inspection planning device 2 can identify which vehicle the operation data acquired by the data acquisition unit 12 relates to. In the running information, at least one piece of information, namely, the line name, train type, and formation number, may be omitted. For example, if all the vehicles stored at the vehicle depot 3 are local trains that stop at every station on the line, the information on the train type may be omitted.

[0033] Next, a description will be given of details of the operational data acquired by the data acquisition unit 12. Fig. 4 is a diagram showing an example of operational data acquired by the data acquisition unit 12 of the vehicle inspection planning device 2 according to the first embodiment.

[0034] In the first embodiment, the operational data is assumed to be time-series data. The operational data is a time series of values ​​represented by electrical signals output from sensors or other devices mounted on the vehicle, or values ​​represented by electrical signals indicating the electrical state of the vehicle. In the following description, electrical signals will be simply referred to as signals. The data acquisition unit 12 acquires operational data for each of a plurality of signals for each vehicle. FIG. 4 shows an example of a graph representing the relationship between the value represented by a signal and time for a certain signal. In the example shown in FIG. 4, the operational data is data whose values ​​constantly change over time. The operational data is not limited to data whose values ​​constantly change. The operational data may also be data whose values ​​remain constant over a certain period of time.

[0035] Next, a description will be given of the procedure of operation by the vehicle inspection planning device 2. Fig. 5 is a flowchart showing an example of the procedure of operation by the vehicle inspection planning device 2 according to the first embodiment.

[0036] In step S1, the inspection plan acquisition unit 10 acquires an inspection plan for the vehicle. In step S2, the inspection plan storage unit 11 stores the inspection plan for the vehicle acquired in step S1.

[0037] In step S3, the data acquisition unit 12 acquires operational data of the vehicle. The data acquisition unit 12 also acquires driving information linked to the operational data. In step S4, the normal range calculation unit 13 obtains a predicted value based on the operational data acquired in step S3, and calculates a normal range based on the predicted value. The normal range calculation unit 13 predicts a value to be acquired in the future as operational data based on the operational data acquired up to the present. The predicted value is a value predicted to be acquired in the future. A method for calculating the predicted value in the normal range calculation unit 13 and a method for calculating the normal range from the predicted value will be described later. The normal range calculation unit 13 outputs information indicating the calculated normal range to the deviation determination unit 14.

[0038] In the first embodiment, the acquisition and storage of the inspection plan in steps S1 and S2 and the acquisition of the operational data and calculation of the normal range in steps S3 and S4 may be performed in parallel.

[0039] The operational data and driving information acquired by the data acquisition unit 12 are input to the deviation determination unit 14. In step S5, the deviation determination unit 14 determines whether the values ​​acquired as operational data deviate from the normal range. The deviation determination unit 14 reads out the inspection plan from the inspection plan storage unit 11. The deviation determination unit 14 references the inspection items in the inspection plan for the vehicle with the vehicle number included in the driving information input to the deviation determination unit 14. The deviation determination unit 14 determines whether the values ​​deviate from the normal range for the operational data indicating the state of the location corresponding to the referenced inspection item or the operational data indicating the state of the location related to the referenced inspection item. If a value deviates from the normal range, the deviation determination unit 14 outputs information indicating the deviation to the inspection plan formulation unit 15.

[0040] In step S6, the inspection plan formulation unit 15 determines whether the deviation situation determined in step S5 corresponds to the inspection plan correction criteria. The inspection plan formulation unit 15 detects the deviation situation based on information from the deviation determination unit 14. In the following description, the inspection plan acquired by the inspection plan acquisition unit 10 is referred to as the original inspection plan. The inspection plan correction criteria are indicators for determining whether to make corrections to advance the inspection timing indicated in the original inspection plan. Examples of inspection plan correction criteria and a method for determining whether the deviation situation corresponds to the inspection plan correction criteria will be described later.

[0041] If the deviation situation meets the inspection plan modification criteria (step S6, Yes), in step S7, the inspection plan formulation unit 15 formulates an inspection plan in which the inspection date is brought forward from the original inspection plan. On the other hand, if the deviation situation does not meet the inspection plan modification criteria (step S6, No), in step S8, the inspection plan formulation unit 15 formulates an inspection plan that is the same as the original inspection plan. The inspection plan formulation unit 15 outputs the inspection plan formulated in step S7 or step S8 to the inspection plan output unit 16.

[0042] In step S9, the inspection plan output unit 16 outputs the inspection plan formulated in step S7 or step S8 to the display terminal 6. With the above, the vehicle inspection planning device 2 ends the operation according to the procedure shown in FIG.

[0043] The inspection plan formulation unit 15 may determine the number of days by which the inspection date should be advanced from the scheduled inspection date in the original inspection plan, and formulate an inspection plan in which the inspection date is advanced by the determined number of days. The inspection plan formulation unit 15 may also adjust the number of days by which the inspection date is advanced depending on the condition of the vehicle indicated in the operation data. For example, for the inspection of wear parts such as pantograph sliders, the number of days by which the inspection date is advanced may be adjusted depending on the remaining amount of wear parts.

[0044] Next, we will explain a method for calculating predicted values ​​by the normal range calculation unit 13. Fig. 6 is a diagram for explaining a method for calculating predicted values ​​by the normal range calculation unit 13 of the vehicle inspection planning device 2 according to the first embodiment.

[0045] FIG. 6 shows an example of a graph showing the relationship between the value of operational data for a certain signal and time. Time T0 is the current time when the predicted value is calculated. The normal range calculation unit 13 predicts the value of the operational data after time T0 based on the operational data acquired up to time T0. In FIG. 6, each plot on the graph before time T0 represents the acquired operational data value. Furthermore, the graph shown by the dashed line after time T0 represents the operational data value predicted by the normal range calculation unit 13.

[0046] For example, the normal range calculation unit 13 predicts the value of the operational data by pattern matching or a local approximation method. The method for predicting the value of the operational data by the normal range calculation unit 13 is not limited to the method described here and may be any method.

[0047] Next, we will explain a method for calculating the normal range from the predicted value by the normal range calculation unit 13. Fig. 7 is a diagram for explaining a method for calculating the normal range from the predicted value by the normal range calculation unit 13 of the vehicle inspection planning device 2 according to the first embodiment.

[0048] FIG. 7 shows an example of a graph showing the relationship between predicted values ​​of operational data for a certain signal and time, and an example of a graph showing the relationship between actual measured values, which are values ​​actually acquired as operational data, and time. Curve 21 shown by a dashed dotted line is a graph showing predicted values. Curve 22 shown by a solid line is a graph showing actual measured values. Curve 23 shown by a dashed line is a graph showing the lower limit of the normal range. Curve 24 shown by a dashed line is a graph showing the upper limit of the normal range. The double arrows in FIG. 7 represent the normal range.

[0049] The normal range calculation unit 13 calculates the normal range as a numerical range of a preset ratio based on the predicted value. For example, the normal range is set to a range with a lower limit value corresponding to -10% of the predicted value and an upper limit value corresponding to +10% of the predicted value. In this way, the normal range calculation unit 13 calculates the normal range based on the predicted value.

[0050] In the above, the numerical range between the predicted value and the lower limit value and the numerical range between the predicted value and the upper limit value are assumed to be the same. The numerical range between the predicted value and the lower limit value and the numerical range between the predicted value and the upper limit value may be different from each other. Furthermore, in the above, a value smaller than the predicted value is set as the lower limit value of the normal range, and a value larger than the predicted value is set as the upper limit value of the normal range. The normal range may be a range whose upper limit is the predicted value, or a range whose lower limit is the predicted value. The normal range can be set arbitrarily, taking into consideration the nature of the operational data, the tendency of changes in the operational data when an abnormality occurs in the vehicle, etc.

[0051] Furthermore, the normal range is not limited to a constant range of values. The normal range may change over time. For example, for operation data indicating the remaining amount of wear parts such as pantograph sliders, the normal range may be determined taking into account the remaining time until the scheduled inspection date.

[0052] In the example shown in FIG. 7, there is a period in which the actual measurement value represented by curve 22 exceeds the upper limit value represented by curve 24. The deviation determination unit 14 determines whether or not the actual measurement value deviates from the normal range. If the value deviates from the normal range, the deviation determination unit 14 outputs information indicating the deviation to the inspection plan formulation unit 15. Furthermore, if the value deviates from the normal range, the deviation determination unit 14 may output the actual measurement value determined to have deviated from the normal range and the predicted value to the inspection plan formulation unit 15. The inspection plan formulation unit 15 calculates the deviation width based on the actual measurement value and the predicted value. The deviation width will be described later.

[0053] Next, a detailed description will be given of the operation by the deviation determination unit 14 in step S5 shown in Fig. 5. Fig. 8 is a flowchart showing an example of an operation procedure by the deviation determination unit 14 of the vehicle inspection planning device 2 according to the first embodiment.

[0054] In step S11, the deviation determination unit 14 acquires information on the inspection items from the inspection plan read out from the inspection plan storage unit 11. In step S12, the deviation determination unit 14 narrows down the signals to be subjected to determination based on the inspection items. Here, the deviation determination unit 14 narrows down the signals to be subjected to deviation determination from a plurality of signals for which operational data is acquired by the data acquisition unit 12. The deviation determination unit 14 narrows down the signals to be subjected to determination to signals that indicate the state of a location corresponding to the inspection item or signals related to the location corresponding to the inspection item. A signal related to a location corresponding to the inspection item is, for example, a signal whose signal intensity may change when an abnormality occurs in a location corresponding to the inspection item.

[0055] In step S13, the deviation determination unit 14 determines whether or not there is a signal for which determination of deviation of values ​​from the normal range has not been completed among the signals to be determined for deviation. If there is a signal for which determination has not been completed (step S13, Yes), in step S14, the deviation determination unit 14 selects one of the signals for which determination has not been completed, and determines whether the value of the selected signal deviates from the normal range. Upon completing step S14, the deviation determination unit 14 returns the procedure to step S13.

[0056] On the other hand, if there are no signals for which the judgment has not been completed (step S13, No), the departure judgment unit 14 ends the operation according to the procedure shown in Figure 8, since the judgment has been completed for all signals that are the subject of departure judgment.

[0057] Next, a method for detecting a deviation situation by the inspection planning unit 15 will be described. The inspection planning unit 15 creates deviation situation information indicating the deviation situation based on information from the deviation determination unit 14. The inspection planning unit 15 detects the deviation situation by creating the deviation situation information.

[0058] 9 is a diagram showing an example of deviation situation information created by the inspection plan formulation unit 15 of the vehicle inspection plan formulation device 2 according to the first embodiment. The deviation situation information is information compiled for each vehicle number and for each of a plurality of signals. FIG. 9 shows an example of deviation situation information for the operation data of a certain signal for a vehicle with the vehicle number "TR001."

[0059] In FIG. 9, deviation situation information is linked to a driving date. The deviation situation information includes information on the number of deviations and information on the deviation width. The number of deviations is the number of times a value deviates from the normal range. The inspection plan formulation unit 15 increments the number of deviations in the deviation situation information each time information indicating a deviation is input. In the example shown in FIG. 9, the information on the number of deviations includes the daily total number of deviations and the cumulative total number of deviations. The daily total number of deviations is the total number of deviations for one driving day. The cumulative total number of deviations is the cumulative number of deviations for each driving day.

[0060] The deviation width is the numerical range between the actual measurement value that is determined to deviate from the normal range and the predicted value. The inspection plan formulation unit 15 receives the actual measurement value and the predicted value and calculates the deviation width using these values. In the example shown in FIG. 9, the deviation width information includes the maximum absolute value of the deviation width and the average deviation width. The maximum absolute value of the deviation width is the maximum absolute value of the deviation width for one driving day. The absolute value of the deviation width is calculated using the following formula. (Absolute value of deviation range) = |{(Actual value) - (Predicted value)} / (Predicted value)|

[0061] The average deviation width is the average deviation width for one day of driving. Note that if the actual measurement value is larger than the predicted value, the deviation width is expressed as a positive value, and if the actual measurement value is smaller than the predicted value, the deviation width is expressed as a negative value.

[0062] In the example shown in FIG. 9, the travel date "2X01 / 6 / 28" is linked to the information of the daily total number of deviations "16" and the cumulative total number of deviations "16." This information indicates that the daily total number of deviations on June 28, 2X01 was 16, and that the cumulative number of deviations on that day was also 16. In addition, the travel date "2X01 / 6 / 28" is linked to the information of the maximum absolute value of the deviation width "0.178" and the average deviation width "0.153." This information indicates that the maximum absolute value of the deviation width on June 28, 2X01 was 0.178, and that the average deviation width on that day was 0.153.

[0063] When the deviation situation indicated in the deviation situation information corresponds to the inspection timing correction criteria, the inspection plan formulation unit 15 determines that the inspection timing indicated in the original inspection plan should be corrected to be earlier. In the first embodiment, the inspection timing correction criteria are determined by at least one of the number of deviations and the deviation width. An example of a correction criterion determined by the number of deviations is that the number of deviations in one day, which is a driving day, is 10 or more. An example of a correction criterion determined by the deviation width is that the maximum absolute value of the deviation width is 15% or more of the predicted value.

[0064] In this way, the inspection plan formulation unit 15 formulates an inspection plan in which the scheduled inspection date is brought forward when the number of times the value acquired as operational data deviates from the normal range meets the criterion, or when the numerical range between the value that deviates from the normal range and the predicted value of the data meets the criterion.

[0065] In the above, the deviation situation information includes information on the number of deviations and information on the deviation width, but this is not limited to this. The deviation situation information may include only one of information on the number of deviations and information on the deviation width. Furthermore, the deviation situation information only needs to include information indicating the deviation situation, and may include information other than information on the number of deviations or information on the deviation width. Furthermore, the inspection timing correction criteria are not limited to those set as described above. The inspection timing correction criteria can be set arbitrarily, taking into consideration the nature of the operational data, the tendency of changes in the operational data when an abnormality occurs in the vehicle, and the like. Furthermore, the inspection timing correction criteria can be set arbitrarily by a user or the like who uses the vehicle inspection planning device 2.

[0066] According to the first embodiment, the vehicle inspection planning system 1 includes a data acquisition unit 12 that acquires data indicating the vehicle condition, a normal range calculation unit 13 that calculates a normal range within which values ​​to be acquired in the future are considered to be normal values ​​as data, a deviation determination unit 14 that determines whether the acquired data values ​​deviate from the normal range, and an inspection planning unit 15 that develops a vehicle inspection plan based on the deviation situation. Data when the vehicle is normal can be accumulated in a shorter period of time than data when an abnormality occurs in the vehicle. Therefore, the vehicle inspection planning system 1 can develop an inspection plan with an earlier inspection date using data acquired in a shorter period of time, compared to when an abnormality is predicted based on accumulated data. As a result, the vehicle inspection planning system 1 has the advantage of being able to develop an inspection plan with an earlier inspection date by using data acquired in a shorter period of time.

[0067] Furthermore, the normal range calculation unit 13 predicts values ​​to be acquired as data in the future based on the data acquired by the data acquisition unit 12, and calculates the normal range based on the predicted values. By predicting values ​​to be acquired in the future from the acquired data and calculating the normal range, the vehicle inspection planning system 1 can more accurately determine whether the values ​​acquired as data are normal.

[0068] Furthermore, the inspection planning unit 15 formulates an inspection plan by advancing the scheduled inspection time for the vehicle based on the deviation situation. This allows the vehicle inspection planning system 1 to formulate an inspection plan with an advanced inspection time when there is a possibility that an abnormality has actually occurred or that a symptom of an abnormality is present.

[0069] Furthermore, when the number of times that the value acquired as data deviates from the normal range meets the criterion, or when the numerical range between the value deviating from the normal range and the predicted value of the data meets the criterion, the inspection plan formulation unit 15 formulates an inspection plan in which the scheduled inspection time is advanced. This allows the vehicle inspection plan formulation system 1 to formulate an inspection plan in which the inspection time is advanced, taking into consideration whether the deviation situation is due to the influence of an abnormality.

[0070] Embodiment 2 In the second embodiment, an example will be described in which the relationship between the cause of a deviation of a value from the normal range and the data in which the deviation occurs is learned to estimate an abnormality. In the second embodiment, the same components as those in the first embodiment are assigned the same reference numerals, and the configuration different from the first embodiment will be mainly described.

[0071] 10 is a diagram showing an example of the configuration of a vehicle inspection planning system 1A according to embodiment 2. The vehicle inspection planning system 1A is a system that plans an inspection plan for a vehicle based on data indicating the condition of the vehicle. The vehicle inspection planning system 1A plans an inspection plan in which the inspection time is earlier than the time indicated in a previously created inspection plan.

[0072] The vehicle inspection planning system 1A is realized by a vehicle inspection planning device 2A. The vehicle inspection planning device 2A is a device installed in a vehicle depot 3.

[0073] Similar to the vehicle inspection planning device 2 shown in Fig. 1, the vehicle inspection planning device 2A has an inspection plan acquisition unit 10, an inspection plan storage unit 11, a data acquisition unit 12, a normal range calculation unit 13, a deviation determination unit 14, and an inspection plan output unit 16. The vehicle inspection planning device 2A has an inspection plan formulation unit 15A that is different from the inspection plan formulation unit 15 shown in Fig. 1. Furthermore, the vehicle inspection planning device 2A differs from the vehicle inspection planning device 2 shown in Fig. 1 in that it includes a deviation tendency learning unit 31 and a deviation tendency information storage unit 32.

[0074] As in the first embodiment, the data acquiring unit 12 acquires operational data and driving information. The operational data is input to the normal range calculation unit 13. The operational data and driving information are also input to the deviation determination unit 14. Furthermore, information indicating the cause of deviation when a value deviates from the normal range is input to the data acquiring unit 12. In this way, the data acquiring unit 12 acquires the information indicating the cause of deviation. The data acquiring unit 12 outputs the operational data and the information indicating the cause of deviation to the deviation tendency learning unit 31.

[0075] The deviation tendency learning unit 31 learns the relationship between the cause of a value deviating from the normal range and the operational data causing the deviation, based on the operational data and information indicating the cause of the deviation. The deviation tendency learning unit 31 creates deviation tendency information indicating the relationship between the cause of a value deviating from the normal range and the operational data causing the deviation, through learning. The deviation tendency learning unit 31 saves the created deviation tendency information in the deviation tendency information storage unit 32. The deviation tendency information storage unit 32 stores the deviation tendency information.

[0076] The inspection plan formulation unit 15A formulates an inspection plan for the vehicle based on the deviation status of values ​​acquired as operational data from the normal range. The inspection plan formulation unit 15A estimates the abnormal part that is the cause of the deviation based on the deviation trend information and the operational data in which the deviation was determined, and formulates an inspection plan in which the timing of inspection of the estimated abnormal part is advanced. The inspection plan formulation unit 15A outputs the formulated inspection plan to the inspection plan output unit 16.

[0077] Next, learning by the deviation tendency learning unit 31 will be described. As an example, assume that a value acquired as operation data deviates from a normal range, and an inspection discovers an abnormality in an inspection item corresponding to the operation data or an inspection item related to the operation data. A user of the vehicle inspection planning device 2A inputs information indicating that an abnormality was found in a location corresponding to the inspection item or a location related to the inspection item to the data acquiring unit 12 as information indicating the cause of the deviation. Furthermore, the data acquiring unit 12 acquires operation data when the value deviates from the normal range. The data acquiring unit 12 outputs the information indicating the cause of the deviation and the operation data when the deviation occurred to the deviation tendency learning unit 31.

[0078] In the above description, the information indicating the cause of the deviation is input to the data acquisition unit 12 by the user of the vehicle inspection planning device 2A, but the data acquisition unit 12 may acquire the information indicating the cause of the deviation by other methods. The data acquisition unit 12 may also acquire the information indicating the cause of the deviation from a system that manages vehicle inspection results, etc.

[0079] Information indicating the cause of the deviation and the operation data at the time the deviation occurred are input to the deviation tendency learning unit 31. As a result, the deviation tendency learning unit 31 acquires learning data which is a combination of information indicating the cause of the deviation and the operation data in which the deviation occurred. Based on the learning data, the deviation tendency learning unit 31 learns the relationship between the cause of the deviation and the operation data in which the deviation occurred. Through learning, the deviation tendency learning unit 31 creates deviation tendency information which indicates the relationship between the cause of the deviation and the operation data in which the deviation occurred. The learning algorithm used by the deviation tendency learning unit 31 can be a well-known algorithm such as supervised learning, unsupervised learning, or reinforcement learning.

[0080] Next, we will explain in detail the deviation tendency information created by the deviation tendency learning unit 31. Fig. 11 is a diagram showing an example of deviation tendency information created by the deviation tendency learning unit 31 of the vehicle inspection planning device 2A according to the second embodiment.

[0081] As shown in FIG. 11 , in the deviation tendency information, information indicating the cause of a deviation is linked to information indicating the operational data in which a deviation occurs. In the example shown in FIG. 11 , in the deviation tendency information, each piece of information indicating the cause of a deviation can be linked to up to three pieces of operational data in which a deviation occurs. These three pieces of data are referred to as first data, second data, and third data. Note that, although up to three pieces of operational data can be linked to each piece of information indicating the cause of a deviation here, the number of pieces of operational data that can be linked is not limited to three and is arbitrary.

[0082] "M equipment" is one of the devices installed in the vehicle. "N sensor" is one of the sensors that detects the status of "M equipment". "K sensor" is one of the sensors installed in the vehicle. "First vibration sensor", "second vibration sensor", and "third vibration sensor" are each sensors that detect wheel vibrations. "First vibration sensor", "second vibration sensor", and "third vibration sensor" detect vibrations at different positions from each other.

[0083] 11, the "abnormality of device M," which is the cause of the deviation, is linked to the "output value of N sensor" as the first data and the "current value of device M" as the second data. Such deviation tendency information indicates that when an abnormality occurs in device M, the output value of N sensor and the current value of device M each tend to deviate from their normal ranges.

[0084] Furthermore, the "K sensor abnormality," which is the cause of the deviation, is linked to the "K sensor output value" as the first data. Such deviation tendency information indicates that when an abnormality occurs in the K sensor, the K sensor output value tends to deviate from the normal range.

[0085] Furthermore, "wheel deformation," which is the cause of deviation, is linked to "output value of the first vibration sensor" as first data, "output value of the second vibration sensor" as second data, and "output value of the third vibration sensor" as third data. Such deviation tendency information indicates that when an abnormality such as wheel deformation occurs, the output values ​​of the first vibration sensor, second vibration sensor, and third vibration sensor tend to deviate from their normal ranges. The deviation tendency information storage unit 32 stores deviation tendency information such as that shown in FIG. 11 regarding abnormalities discovered during vehicle inspections.

[0086] Next, the formulation of an inspection plan by the inspection plan formulation unit 15A will be described. For operational data determined by the deviation determination unit 14 to deviate from the normal range, the inspection plan formulation unit 15A reads deviation trend information including information indicating the operational data from the deviation trend information storage unit 32. The inspection plan formulation unit 15A estimates the abnormal location that is the cause of the deviation based on information indicating the cause of the deviation that is included in the read deviation trend information. The inspection plan formulation unit 15A formulates an inspection plan in which the timing of inspections targeting the estimated abnormal location is advanced.

[0087] The inspection plan formulation unit 15A may identify candidate abnormal locations based on information indicating the cause of the deviation, and may advance the timing of inspections of inspection items targeting abnormal locations selected from the candidate abnormal locations. For example, when multiple abnormal locations are identified, the inspection plan formulation unit 15A selects one or more of the multiple abnormal locations and formulates an inspection plan in which the timing of inspections targeting the selected locations is advanced.

[0088] The inspection plan formulation unit 15A may determine whether to advance the inspection time based on the importance of the abnormality at each identified abnormality location. The importance of an abnormality can be interpreted as the severity of the problem that may occur if the abnormality is left untreated. For example, an abnormality that could lead to a breakdown that would prevent the vehicle from running is considered to be of high importance. On the other hand, an abnormality that causes little or no problem to the vehicle's running is considered to be of low importance. The inspection plan formulation unit 15A selects candidates with high importance from among the candidate abnormality locations and formulates an inspection plan that advances the inspection time for the selected candidates. Alternatively, the inspection plan formulation unit 15A excludes candidates with low importance from among the candidate abnormality locations and formulates an inspection plan that advances the inspection time for the remaining candidates. This allows the vehicle inspection plan formulation device 2A to formulate an inspection plan that prioritizes the inspection of abnormality locations with high importance.

[0089] Next, a procedure of operation performed by the vehicle inspection planning device 2A will be described. Fig. 12 is a flowchart showing an example of the procedure of operation performed by the vehicle inspection planning device 2A according to the second embodiment.

[0090] Steps S1 to S6, S8, and S9 shown in Fig. 12 are the same as steps S1 to S6, S8, and S9 shown in Fig. 5. The procedure shown in Fig. 12 includes steps S31 and S32 instead of step S7 shown in Fig. 5.

[0091] Furthermore, in the vehicle inspection planning device 2A, the data acquisition unit 12 acquires information indicating the cause of the deviation and the operational data when a deviation from the normal range occurred. The deviation tendency learning unit 31 acquires learning data which is a combination of information indicating the cause of the deviation and the operational data in which the deviation occurred, and learns the relationship between the cause of the deviation and the operational data in which the deviation occurred based on the learning data. The deviation tendency learning unit 31 creates deviation tendency information through learning and stores the deviation tendency information in the deviation tendency information storage unit 32.

[0092] If the deviation situation meets the inspection plan correction criteria (Step S6, Yes), in Step S31, the inspection plan formulation unit 15A identifies candidate abnormal locations that are the cause of the deviation. For the operational data determined to meet the inspection plan correction criteria in Step S6, the inspection plan formulation unit 15A reads deviation trend information including information indicating the operational data from the deviation trend information storage unit 32. The inspection plan formulation unit 15A identifies candidate abnormal locations based on information indicating the cause of the deviation that is included in the read deviation trend information.

[0093] In step S32, the inspection plan formulation unit 15A formulates an inspection plan in which the timing of inspections targeting abnormal locations selected from the candidate abnormal locations is advanced. The inspection plan formulation unit 15A determines whether to advance the inspection timing based on the severity of the abnormality at each identified abnormal location. After completing step S32, the vehicle inspection plan formulation device 2A proceeds to step S9.

[0094] In the above, it has been described that the deviation tendency information is created by learning in the deviation tendency learning unit 31, but this is not limited to this. The vehicle inspection planning device 2A may create the deviation tendency information by a method other than learning. Furthermore, the deviation tendency information is not limited to information created by the vehicle inspection planning device 2A. Deviation tendency information created outside the vehicle inspection planning device 2A may be input to the vehicle inspection planning device 2A. The deviation tendency information may be created, for example, by a user of the vehicle inspection planning device 2A.

[0095] According to the second embodiment, the vehicle inspection planning device 2A includes a deviation tendency learning unit 31 that learns the relationship between the cause of a deviation of a value from a normal range and the data in which the deviation occurs. The inspection planning unit 15A estimates the abnormal location that is the cause of the deviation based on deviation tendency information that indicates the relationship between the cause of the deviation and the data in which the deviation occurs and the data in which the deviation is determined, and formulates an inspection plan that advances the timing of inspections of the estimated abnormal location. This allows the vehicle inspection planning device 2A to formulate an inspection plan that prioritizes the inspection of abnormal locations.

[0096] Next, a description will be given of a hardware configuration for realizing the vehicle inspection planning device 2, 2A according to the first or second embodiment. The vehicle inspection planning device 2, 2A is realized by a processing circuit. The processing circuit is a circuit in which a processor executes software.

[0097] When the processing circuit is realized by software, the processing circuit is, for example, a control circuit 40 shown in FIG. 13. FIG. 13 is a diagram showing an example configuration of the control circuit 40 according to the first or second embodiment. The control circuit 40 includes an input unit 41, a processor 42, a memory 43, and an output unit 44. The input unit 41 is an interface circuit that receives data input from outside the control circuit 40 and provides the data to the processor 42. The output unit 44 is an interface circuit that sends data from the processor 42 or the memory 43 to outside the control circuit 40.

[0098] The vehicle inspection planning devices 2, 2A are realized by software, firmware, or a combination of software and firmware. The software or firmware is written as a program and stored in memory 43. In the control circuit 40, the processor 42 reads and executes the program stored in memory 43, thereby realizing each function of the vehicle inspection planning devices 2, 2A. In other words, the control circuit 40 includes memory 43 for storing a vehicle inspection planning program, which is a program that results in the processing of the vehicle inspection planning devices 2, 2A. The vehicle inspection planning program can also be said to cause a computer to execute the procedures and methods of the vehicle inspection planning devices 2, 2A. The memory 43 is also used as temporary memory when the processor 42 executes various processes.

[0099] The processor 42 is a CPU (Central Processing Unit), a central processing unit, a processing unit, an arithmetic unit, a microprocessor, a microcomputer, a processor, or a DSP (Digital Signal Processor). The memory 43 is, for example, a non-volatile or volatile semiconductor memory such as a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable Read Only Memory), an EEPROM (Electrically Erasable Programmable Read Only Memory), a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, or a DVD (Digital Versatile Disc).

[0100] The vehicle inspection planning device 2, 2A may include an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). The vehicle inspection planning program according to the first or second embodiment may be provided by being stored on a recording medium such as a CD (Compact Disc)-ROM or a DVD-ROM. The vehicle inspection planning program according to the first or second embodiment may be provided by being stored in a computer connected to a network such as the Internet and downloaded via the network such as the Internet. The vehicle inspection planning program according to the first or second embodiment may be provided or distributed via a network such as the Internet.

[0101] In the first or second embodiment, the vehicle inspection planning system 1, 1A is realized by a single device, that is, the vehicle inspection planning device 2, 2A. However, the vehicle inspection planning system 1, 1A may be realized using two or more devices. That is, the vehicle inspection planning system 1, 1A may be composed of two or more devices. The two or more devices are connected to each other so that they can communicate with each other. Each of the two or more devices has a configuration similar to that of the control circuit 40. The two or more devices may include a cloud server. The cloud server is a server built in a cloud environment that includes computer resources provided by a cloud service platform.

[0102] The configurations shown in the above embodiments are examples of the contents of the present disclosure. The configurations of each embodiment can be combined with other known technologies. The configurations of each embodiment can also be combined as appropriate. Part of the configuration of each embodiment can be omitted or modified without departing from the gist of the present disclosure.

[0103] Various aspects of the present disclosure are summarized below as appendices.

[0104] (Appendix 1) a data acquisition unit that acquires data indicating the state of the railway vehicle; a normal range calculation unit that calculates a normal range within which values ​​to be acquired in the future as the data are considered to be normal values; a deviation determination unit that determines deviation of the acquired data value from the normal range; an inspection plan formulation unit that formulates an inspection plan for the railway vehicle based on the deviation situation. A vehicle inspection planning system characterized by: (Appendix 2) The normal range calculation unit predicts values ​​to be acquired in the future as the data based on the data acquired by the data acquisition unit, and calculates the normal range based on the predicted values. 2. A vehicle inspection planning system according to claim 1. (Appendix 3) The inspection plan formulation unit formulates the inspection plan by advancing the timing of a scheduled inspection of the railcar based on the deviation situation. 3. A vehicle inspection planning system according to claim 1 or 2. (Appendix 4) The examination plan formulation unit formulates the examination plan in which the time of the scheduled examination is advanced when the number of times the value acquired as the data deviates from the normal range meets a criterion, or when the numerical range between the value deviating from the normal range and the predicted value of the data meets a criterion. 4. A vehicle inspection planning system according to claim 3. (Appendix 5) a deviation tendency learning unit that learns the relationship between the cause of a deviation of a value from the normal range and the data causing the deviation, The inspection plan formulation unit estimates an abnormality that is the cause of the deviation based on deviation trend information that indicates the relationship between the cause of the deviation and the data in which the deviation occurs and the data in which the deviation is determined, and formulates the inspection plan in which the timing of inspection targeting the estimated abnormality is advanced. 5. A vehicle inspection planning system according to any one of appendices 1 to 4. (Appendix 6) acquiring data indicative of a condition of the rail vehicle; calculating a normal range within which values ​​to be acquired in the future as the data are considered to be normal values; determining whether the acquired data values ​​deviate from the normal range; and developing an inspection plan for the rail vehicle based on the circumstances of the deviation. A vehicle inspection planning method comprising: (Appendix 7) acquiring data indicative of a condition of the rail vehicle; calculating a normal range within which values ​​to be acquired in the future as the data are considered to be normal values; determining whether the acquired data values ​​deviate from the normal range; and developing an inspection plan for the railcar based on the deviation situation. A vehicle inspection planning program characterized by: [Explanation of symbols]

[0105] 1,1A Vehicle inspection planning system, 2,2A Vehicle inspection planning device, 3 Vehicle depot, 4 Inspection system, 5 Operation management system, 6 Display terminal, 10 Inspection plan acquisition unit, 11 Inspection plan memory unit, 12 Data acquisition unit, 13 Normal range calculation unit, 14 Deviation judgment unit, 15,15A Inspection plan formulation unit, 16 Inspection plan output unit, 21,22,23,24 Curve, 31 Deviation tendency learning unit, 32 Deviation tendency information memory unit, 40 Control circuit, 41 Input unit, 42 Processor, 43 Memory, 44 Output unit.

Claims

1. a data acquisition unit that acquires data indicating the state of the railway vehicle; a normal range calculation unit that calculates a normal range within which values ​​to be acquired in the future as the data are considered to be normal values; a deviation determination unit that determines deviation of the acquired data value from the normal range; an inspection plan formulation unit that formulates an inspection plan for the railway vehicle based on the deviation situation. A vehicle inspection planning system characterized by:

2. The normal range calculation unit predicts values ​​to be acquired in the future as the data based on the data acquired by the data acquisition unit, and calculates the normal range based on the predicted values.

2. The vehicle inspection planning system according to claim 1.

3. The inspection plan formulation unit formulates the inspection plan by advancing the timing of a scheduled inspection of the railcar based on the deviation situation.

3. The vehicle inspection planning system according to claim 1 or 2.

4. The examination plan formulation unit formulates the examination plan in which the time of the scheduled examination is advanced when the number of times the value acquired as the data deviates from the normal range meets a criterion, or when the numerical range between the value deviating from the normal range and the predicted value of the data meets a criterion.

4. The vehicle inspection planning system according to claim 3.

5. a deviation tendency learning unit that learns the relationship between the cause of a deviation of a value from the normal range and the data causing the deviation, The inspection plan formulation unit estimates an abnormality that is the cause of the deviation based on deviation trend information that indicates the relationship between the cause of the deviation and the data in which the deviation occurs and the data in which the deviation is determined, and formulates the inspection plan in which the timing of inspection targeting the estimated abnormality is advanced.

3. The vehicle inspection planning system according to claim 1 or 2.

6. acquiring data indicative of a condition of the rail vehicle; calculating a normal range within which values ​​to be acquired in the future as the data are considered to be normal values; determining whether the acquired data values ​​deviate from the normal range; and developing an inspection plan for the rail vehicle based on the circumstances of the deviation. A vehicle inspection planning method comprising:

7. acquiring data indicative of a condition of the rail vehicle; calculating a normal range within which values ​​to be acquired in the future as the data are considered to be normal values; determining whether the acquired data values ​​deviate from the normal range; and developing an inspection plan for the railcar based on the deviation situation. A vehicle inspection planning program characterized by:

Images