Operation management support system, operation management support method, and operation management support program

Abstract

To obtain a train operation management support system that can improve the accuracy of predicting the timing of train operation restrictions in train operation management. [Solution] The train operation support system 1 includes a restricted section determination unit 232 that determines restricted sections where train operations will be restricted based on weather forecast information, and a restricted information creation unit 233 that predicts the restriction time for restricted sections based on weather forecast information and information on the inspection history of facilities along the railway line. The train operation support system 1 has the effect of improving the accuracy of predicting the restriction time for train operations in train operation management.

Description

Technical Field

[0001] The present disclosure relates to an operation management support system, an operation management support method, and an operation management support program.

Background Art

[0002] In railway operation management, train operation regulations are implemented to prevent accidents caused by meteorological phenomena such as wind, rain, and snow. Patent Document 1 describes an operation management support system that controls the temporary speed of trains based on meteorological variations. The operation management support system described in Patent Document 1 determines a predicted regulation section where speed regulation setting or cancellation is performed based on meteorological prediction information, determines trains subject to speed regulation in the predicted regulation section, and determines the temporary speed in the predicted regulation section. Then, when the meteorological prediction value given by the meteorological prediction information is lower than the regulation reference value defined in the regulation section management table, the speed regulation is cancelled.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the operation management support system of the above Patent Document 1, the determination at the time of regulation cancellation is only when the meteorological prediction value is lower than the regulation reference value. However, at the actual site where the operation regulation is issued, the determination of cancellation of the operation regulation is made after inspecting the roadside facilities. Therefore, the operation management support system of Patent Document 1 has a problem of low accuracy in predicting the regulation time.

[0005] The present disclosure has been made in view of the above, and an object thereof is to obtain an operation management support system capable of improving the prediction accuracy of the regulation time of operation regulations in train operation management. [Means for solving the problem]

[0006] To solve the aforementioned problems and achieve the objectives, the operation management support system described herein comprises a restricted section determination unit that determines restricted sections where train operations will be restricted based on weather forecast information, and a restricted information creation unit that predicts the restriction times for restricted sections based on weather forecast information and information on the inspection history of facilities along the railway line. [Effects of the Invention]

[0007] According to this disclosure, it is possible to improve the accuracy of predicting the timing of restrictions on train operations in train operation management. [Brief explanation of the drawing]

[0008] [Figure 1] This figure shows an example of an operating environment in which the operation management support system according to Embodiment 1 is used. [Figure 2] This figure shows an example of the configuration of the railway disaster prevention information system server according to Embodiment 1. [Figure 3] This figure shows an example of the configuration of the operation management system server according to Embodiment 1. [Figure 4] This diagram shows an example of the information flow related to the railway disaster prevention information system according to Embodiment 1. [Figure 5] A flowchart showing an example of the processing procedure in the disaster prevention information data acquisition unit of the disaster prevention information processing unit of the railway disaster prevention information system server according to Embodiment 1. [Figure 6] A flowchart showing an example of the processing procedure in the disaster prevention information processing unit of the railway disaster prevention information system server according to Embodiment 1. [Figure 7] Figure 1 illustrates a method for determining whether or not there are trains subject to restrictions in the disaster prevention information processing unit of the railway disaster prevention information system server according to Embodiment 1. [Figure 8] Figure 2 illustrates a method for determining whether or not there are trains subject to restrictions in the disaster prevention information processing unit of the railway disaster prevention information system server according to Embodiment 1. [Figure 9] Figure 3 illustrates a method for determining whether or not there are trains subject to restrictions in the disaster prevention information processing unit of the railway disaster prevention information system server according to Embodiment 1. [Figure 10] A first flowchart showing an example of a detailed procedure for calculating the predicted time of deregulation in the deregulation information creation unit of the railway disaster prevention information system server according to Embodiment 1. [Figure 11] A second flowchart showing an example of a detailed procedure for calculating the predicted time of deregulation in the deregulation information creation unit of the railway disaster prevention information system server according to Embodiment 1. [Figure 12] A diagram showing an example of an association information table according to Embodiment 2. [Figure 13] Figure showing another example of the association information table according to Embodiment 2. [Figure 14] A flowchart showing an example of the procedure for creating an association information table according to Embodiment 2. [Figure 15] A diagram showing an example of a weather forecast information table according to Embodiment 2. [Figure 16] This diagram illustrates the process by which a regulatory information creation unit, which has a machine learning device, searches for past weather information similar to weather forecast information in Embodiment 2. [Figure 17] Figure 1 illustrating the method for obtaining the predicted water level in Embodiment 3. [Figure 18] Figure 2 illustrates the method for obtaining the predicted water level in Embodiment 3. [Figure 19] Figure showing the first association information table according to Embodiment 4. [Figure 20] Figure showing the second association information table according to Embodiment 4. [Figure 21] This figure illustrates how the regulatory information creation unit uses a machine learning device to predict the inspection completion time in Embodiment 4. [Figure 22] This figure shows an example of the track shape used when the regulatory information creation unit, which has a machine learning device, predicts the inspection completion time in Embodiment 4. [Figure 23]FIG. showing another example of the shape of the line used when the regulation information creation unit having the machine learning device predicts the inspection completion time in Embodiment 4 [Figure 24] FIG. showing an example of the jam distance database used when the regulation information creation unit having the machine learning device predicts the inspection completion time in Embodiment 4 [Figure 25] FIG. showing the processing of the railway disaster prevention information system server in Embodiment 5 [Figure 26] FIG. showing the processing of the operation management system server in Embodiment 6 [Figure 27] FLOWCHART showing an example of the procedure of the processing of the operation management processing unit of the operation management system server in Embodiment 6 [Figure 28] FIG. showing an example of the usage environment in which the operation management support system is used in Embodiment 7 [Figure 29] FIG. showing an example of the flow of information related to the railway disaster prevention information system in Embodiment 7 [Figure 30] FIG. showing the processing of the railway disaster prevention information system server in Embodiment 7 [Figure 31] FLOWCHART showing an example of the procedure of the processing of the regulation information creation unit of the disaster prevention information processing unit of the railway disaster prevention information system server in Embodiment 7 [Figure 32] FIG. showing the processing of the operation management system server in Embodiment 8 [Figure 33] FIG. showing a configuration in which the respective functions of the control units according to Embodiments 1 to 8 are realized by hardware [Figure 34] FIG. showing a configuration in which the respective functions of the control units according to Embodiments 1 to 8 are realized by software

MODE FOR CARRYING OUT THE INVENTION

[0009] Hereinafter, the operation management support system, the operation management support method, and the operation management support program according to the embodiments will be described in detail based on the drawings.

[0010] Embodiment 1. Figure 1 shows an example of an operating environment in which the operation management support system according to Embodiment 1 is used. The operation management support system 1 is a system that creates operation restriction information, which is necessary for train operation management, such as speed restrictions and cancellations, based on weather information. As shown in Figure 1, the operation management support system 1 according to Embodiment 1 can communicate with a weather forecasting system 4, a station system 5, a train system 6, a train 6a, measuring instruments 7, and a passenger information system 8, and acquires various information from these configurations. The operation management support system 1 can also transmit information to the World Wide Web (Web) 9. The operation management support system 1 includes a railway disaster prevention information system 2 and an operation management system 3.

[0011] The Railway Disaster Prevention Information System 2 collects data on observed values ​​such as rainfall, wind speed, and earthquakes from measuring instruments 7 placed along the railway lines by the railway company, creates and issues train operation restriction information, and supports security operations for facilities along the railway lines. The Railway Disaster Prevention Information System 2 is installed in the railway company's control center. The Railway Disaster Prevention Information System 2 is implemented, for example, by a server called the Railway Disaster Prevention Information System Server 2S.

[0012] Train operation restrictions are instructions necessary for managing train operations, such as speed limits and service suspensions.

[0013] Traffic restriction information is information indicating traffic restrictions. This information includes details about the traffic restriction and the predicted time of the restriction.

[0014] The predicted restriction time is the predicted time for train operation restrictions, and includes the predicted start time of the restriction and the predicted end time of the restriction. The predicted start time of the restriction is the predicted time when the operation restriction will begin. The predicted end time of the restriction is the predicted time when the operation restriction will be lifted. The predicted end time of the restriction corresponds to both the predicted time when currently set operation restrictions will be lifted and the predicted time when future operation restrictions, based on weather forecast information included in weather information, will be lifted. The predicted restriction time is shown in minutes, for example, at XX:XX.

[0015] The lifting of train service restrictions is achieved when two conditions are confirmed: the weather forecast value, which is a value given in weather forecast information, falls below the regulatory standard, and no abnormalities are found during track inspections.

[0016] The train operation management system 3 creates a train operation schedule 321 and a predicted schedule 322 using various information such as predicted regulation times, train schedules, platform congestion levels, and train congestion levels. The train operation management system 3 is installed in the railway company's control center or on the cloud. The train operation management system 3 is implemented, for example, by a train operation management system server 3S, which is a server. Note that the schedule may sometimes be written as "schedule".

[0017] Figure 2 shows an example of the configuration of a railway disaster prevention information system server according to Embodiment 1. Figure 3 shows an example of the configuration of an operation management system server according to Embodiment 1. Figure 4 shows an example of the flow of information related to the railway disaster prevention information system according to Embodiment 1.

[0018] As shown in Figures 2 and 4, the railway disaster prevention information system server 2S comprises a disaster prevention information communication unit 21, a disaster prevention information storage unit 22, a disaster prevention information processing unit 23, and a disaster prevention information control unit 24. Information can be exchanged between each component of the railway disaster prevention information system server 2S. The disaster prevention information communication unit 21, the disaster prevention information processing unit 23, and the disaster prevention information control unit 24 are components implemented, for example, as software.

[0019] The disaster prevention information and communication unit 21 is connected to a network (not shown) and communicates with external devices of the railway disaster prevention information system server 2S via this network. The network is, for example, the internet.

[0020] The disaster prevention information storage unit 22 stores various types of information used to control the railway disaster prevention information system server 2S, including information acquired from outside the railway disaster prevention information system server 2S and information created within the railway disaster prevention information system server 2S. The disaster prevention information storage unit 22 includes an inspection history database 221, an observation value database 222, an external weather information database 223, a personnel plan database 224, and a station distance database 225. Note that databases may sometimes be referred to as DB (Data Base).

[0021] The inspection history database 221 stores inspection history data, which is data on past inspection results of facilities along the railway line related to train operations. Inspections include, for example, daily inspections carried out as part of routine operations, and temporary inspections carried out before the lifting of issued operational restrictions. Inspections are carried out by inspectors in sections along the railway line where operational restrictions have been set.

[0022] Train service restrictions include service cancellations, speed limits, and changes to train turnarounds, as well as any other restrictions necessary for managing train operations.

[0023] The inspection history includes information on the inspection completion time, which is the time required to inspect the equipment along the railway line. The inspection completion time is the time it takes to complete the inspection of the equipment along the railway line in the restricted section of the line, and is the time required to inspect the equipment along the railway line in the restricted section of the line. The inspection history DB221 stores information such as the location where the inspection was performed, the date and time the inspection was performed, the range of the observed values ​​from the measuring instruments, the number of inspectors, and the inspection completion time. For inspections, items that are inspected when the observed values ​​from measuring instruments, such as precipitation, fall outside a predetermined standard range are predetermined for each type of observed value from the measuring instrument. The number of inspectors is the number of inspectors who perform the inspection.

[0024] The observation database 222 stores data on observed environmental conditions along the railway line, measured by the measuring instrument 7, that is, data on observed environmental conditions along the train's route.

[0025] The external weather information database 223 stores weather forecast information obtained from the weather forecasting system 4.

[0026] The personnel planning database 224 stores data on personnel plans for inspections of railway infrastructure related to train operations. The inspection personnel plan is a pre-planned personnel plan for inspection personnel in a designated section. The inspection personnel plan is entered by the user, the dispatcher, at the time the timetable is created. However, the timing of creating the inspection personnel plan is not limited to this. For example, the dispatcher may enter the inspection personnel plan information into the railway disaster prevention information system server 2S when a traffic restriction is issued, or when the time for issuing a future traffic restriction is determined.

[0027] The personnel plans for inspections stored in the personnel plan DB224 are not personnel plans for when operational restrictions are in place, but rather personnel plans for routine inspections performed as part of daily operations. Furthermore, even for temporary inspections conducted before operational restrictions are lifted, the personnel plans stored in the personnel plan DB224 are generally used. The personnel plan DB224 contains tables that store information such as the inspection date, inspection section, and the number of inspectors.

[0028] The station distance database 225 stores data on the section of the railway line where inspections are conducted, and data on the station distance, which is the distance from that section to the station.

[0029] Stations are places where inspectors who conduct inspections along the railway line wait, and multiple such stations are set up along the line. When an inspection is to be carried out, the inspectors wait at a predetermined station along the line and then move from the station to the section to be inspected.

[0030] The station distance is the distance between the station and the inspection site, and the distance it takes for the inspector to travel from the station to the inspection site. If the distance from the station to the restricted section is relatively far, the time required for the inspection will be relatively longer, and the time until the traffic restrictions are lifted will also be longer. If the distance from the station to the restricted section is relatively short, the time required for the inspection will be relatively shorter, and the time until the traffic restrictions are lifted will also be shorter. The restricted section is the section along the railway line where traffic restrictions have been issued. The station distance is entered by the user or set in advance.

[0031] The disaster prevention information processing unit 23 is responsible for creating and issuing train operation restrictions. Based on weather forecast information obtained from the weather forecasting system 4, the disaster prevention information processing unit 23 creates and issues train operation restriction information. Based on information such as weather information obtained from the weather forecasting system 4, observed values ​​collected from measuring instruments 7, inspection history along the railway line, personnel plans for inspections, and distances to inspection stations, the disaster prevention information processing unit 23 is responsible for predicting the predicted time of restriction lifting for train operation restrictions. Weather information includes weather forecast information and current weather information.

[0032] The disaster prevention information processing unit 23 comprises a disaster prevention information data acquisition unit 231, a restricted area determination unit 232, a restricted information creation unit 233, and a restricted information notification unit 234. Information can be exchanged between the various components of the disaster prevention information processing unit 23.

[0033] The disaster prevention information data acquisition unit 231 acquires various information, including weather information including weather forecast information, observed values ​​from measuring instrument 7, inspection history along the railway line, personnel plan for inspections, and distance to inspection stations, and stores it in the database of the disaster prevention information storage unit 22. In other words, the disaster prevention information data acquisition unit 231 receives information such as weather information acquired from the weather forecasting system 4, observed values ​​from measuring instrument 7, inspection history along the railway line, personnel plan for inspections, and distance to inspection stations. The disaster prevention information data acquisition unit 231 also transmits the information such as weather information acquired from the weather forecasting system 4, observed values ​​from measuring instrument 7, inspection history along the railway line, personnel plan for inspections, and distance to inspection stations to the disaster prevention information storage unit 22 and the regulation information creation unit 233.

[0034] The restricted section determination unit 232 determines the restricted section, which is a section along the railway line where train operations are restricted, based on weather forecast information from weather information.

[0035] The regulation information creation unit 233 predicts the time of restriction in the restricted section of the train service based on weather forecast information and inspection history information of facilities along the railway line. The regulation information creation unit 233 predicts the predicted time of restriction, which is the predicted time of the restriction on train operations in the restricted section of the train service based on weather forecast information and inspection history information of facilities along the railway line.

[0036] The regulation information creation unit 233 creates information on train operation restrictions and the predicted start time of said restrictions based on weather forecast information. The regulation information creation unit 233 uses the time when the value of the weather forecast information exceeds a predetermined restriction standard value as the predicted start time of the train operation restrictions. Based on various information such as weather forecast information, observed values ​​from measuring instruments 7, inspection history along the line, personnel plan for inspections, and distance to the station, the regulation information creation unit 233 predicts the predicted time for lifting the restrictions and creates information on the predicted time for lifting the restrictions.

[0037] The regulation information creation unit 233 receives various information, including weather forecasts, observed values ​​from measuring instruments 7, inspection history along the line, personnel plans for inspections, and distances to inspection stations. The regulation information creation unit 233 also transmits operational regulation information, such as predicted times for lifting restrictions, to the operation management system server 3S and WEB9 via the regulation information notification unit 234. In Figure 4, for ease of understanding, connection lines are shown from the regulation information creation unit 233 to the diagram prediction unit 333 and WEB9.

[0038] The regulatory information notification unit 234 transmits the train operation restriction information created in the regulatory information creation unit 233 to the operation management system 3 and WEB9.

[0039] The disaster prevention information control unit 24 controls the entire railway disaster prevention information system server 2S.

[0040] The Railway Disaster Prevention Information System Server 2S stores the Railway Disaster Prevention Information System Application Software, which is application software for executing the functions of the Railway Disaster Prevention Information System 2 by executing the functions of each component of the Railway Disaster Prevention Information System Server 2S described above, in the Disaster Prevention Information Storage Unit 22. The Railway Disaster Prevention Information System Application Software is application software for executing the functions of the Operation Management Support System 1.

[0041] The railway disaster prevention information system application software includes an operation management support program that causes the computer to execute the functions of the operation management support system 1, and a railway disaster prevention information system program that causes the computer to execute the functions of each component of the railway disaster prevention information system server 2S described above. The railway disaster prevention information system program is installed in the disaster prevention information storage unit 22.

[0042] As shown in Figures 3 and 4, the operation management system server 3S comprises an operation management communication unit 31, an operation management storage unit 32, an operation management processing unit 33, and an operation management control unit 34. Information can be exchanged between each component of the operation management system server 3S. The operation management communication unit 31, the operation management processing unit 33, and the operation management control unit 34 are components implemented, for example, as software.

[0043] The operation management communication unit 31 is connected to a network (not shown) and communicates with external devices of the operation management system server 3S via the network. The network is, for example, the internet.

[0044] The operation management memory unit 32 stores various types of information used to control the operation management system server 3S, including information acquired from outside the operation management system server 3S and information created within the operation management system server 3S. The operation management memory unit 32 stores the operation schedule 321 and the predicted schedule 322.

[0045] The train schedule 321 is train schedule information that shows the train schedule during normal operation. The train schedule 321 is created in the schedule creation unit 332 of the train management processing unit 33, which will be described later.

[0046] The predicted timetable 322 is operational forecast plan information that shows the predicted train operation plan after the lifting of operational restrictions. The predicted timetable 322 is created in the timetable forecast unit 333 of the operation management processing unit 33, which will be described later.

[0047] The train operation management processing unit 33 is responsible for creating a timetable using various information such as predicted restriction times, train schedules, platform congestion levels, and train congestion levels. The train operation management processing unit 33 comprises a train operation data acquisition unit 331, a timetable creation unit 332, and a timetable prediction unit 333. Information can be exchanged between the various components of the train operation management processing unit 33.

[0048] The operation management data acquisition unit 331 acquires various information such as the operation schedule 321, the predicted time for lifting restrictions, platform congestion, and train congestion, and stores it in the operation management storage unit 32. The operation management data acquisition unit 331 acquires the operation schedule 321 for normal operation stored in the operation management storage unit 32. The operation management data acquisition unit 331 acquires the predicted time for lifting restrictions by receiving information on the predicted time for lifting restrictions transmitted from the restriction information notification unit 234 of the railway disaster prevention information system 2.

[0049] The diagram creation unit 332 creates a train operation diagram 321 for normal operation.

[0050] The timetable prediction unit 333 creates a timetable for trains after the lifting of the operational restrictions. Specifically, the timetable prediction unit 333 creates a predicted timetable 322, which is operational prediction plan information showing the predicted train operation plan after the lifting of the operational restrictions. The timetable prediction unit 333 can create a predicted timetable 322 for any selected train, or it can create a predicted timetable 322 for all trains currently in operation or scheduled to operate. The timetable prediction unit 333 transmits the information of the created predicted timetable 322 to train 6a, the passenger information system 8, and WEB9. The timetable prediction unit 333 transmits the information of the predicted timetable 322 to train 6a via train radio operation notification through the notification transmission server 14. Operation notifications include speed restrictions, cancellations, and turnaround changes, as well as other instructions necessary for train operation management.

[0051] The operation management control unit 34 controls the entire operation management system server 3S.

[0052] The operation management system server 3S stores the operation management system application software, which is application software for executing the functions of the operation management system 3 by executing the functions of each component of the operation management system server 3S described above, in the operation management storage unit 32. The operation management system application software is application software for executing the functions of the operation management support system 1.

[0053] The operation management system application software includes an operation management support program that causes the computer to execute the functions of the operation management support system 1, and an operation management system program that causes the computer to execute the functions of each component of the operation management system server 3S described above. The operation management system program is installed in the operation management storage unit 32.

[0054] The weather forecasting system 4 acquires weather information from weather-related websites and the Japan Meteorological Agency's website, and transmits the weather information to the railway disaster prevention information system 2. The weather forecasting system 4 includes a weather forecast information communication unit 41 that acquires weather information such as past weather information, current weather information, and future weather forecast information and transmits it to the railway disaster prevention information system 2. In other words, the weather information includes weather information such as past weather information, current weather information, and future weather forecast information. The weather forecasting system 4 may be installed, for example, in the control center of a railway company, or it may be installed outside the control center of a railway company. The weather forecasting system 4 is implemented, for example, by a server, and also includes functional units such as a communication unit that communicates with the outside, but the explanation is omitted.

[0055] The station system 5 calculates the platform congestion level, which is the degree of congestion on the station platform. The station system 5 includes a platform congestion calculation unit 51 that calculates the platform congestion level. The station system 5 is implemented by, for example, a camera and a server, and also includes functional units such as a communication unit for communicating with the outside world, but the explanation is omitted. The station system 5 is installed, for example, in the station's control room, but the installation location of the station system 5 is not limited to this.

[0056] Platform congestion is an index that numerically represents the degree of congestion on a station platform based on the number of people on the platform. This platform congestion may also be calculated by taking into account the congestion within the station premises.

[0057] The train system 6 calculates the train congestion level, which is the degree of occupancy of people inside the train. The train system 6 includes a train congestion calculation unit 61 that calculates the train congestion level. The train system 6 is implemented by, for example, a camera and a server, and also includes functional units such as a communication unit for communicating with the outside world, but the explanation is omitted. The train system 6 is installed inside the train.

[0058] Train congestion is an index that numerically represents the degree of congestion inside a train, based on the number of people on board.

[0059] The measuring instrument 7 measures the environment along the railway line, that is, the environment of the train's route along the line, at predetermined intervals. The measuring instrument 7 transmits the observed values, which are the measurement results, to the railway disaster prevention information system 2. The measuring instrument 7 is installed along the railway line within the scope of the railway company's private property. The measuring instrument 7 can transmit current observed values ​​and data on past observed values ​​to the railway disaster prevention information system 2.

[0060] Measuring instrument 7 includes instruments for measuring "precipitation," "wind speed," "wind direction," "water level," "snow depth," "flow rate," "rail temperature," "earthquake," and "landslide" along the railway line on the private property of the railway company. Measuring instruments 7 for measuring "precipitation," "wind speed," "wind direction," "snow depth," "rail temperature," "earthquake," and "landslide" are installed along the railway line on the private property of the railway company. Measuring instruments 7 for measuring "water level" and "flow rate" are installed on the bridge girders of bridges where the railway line crosses a bridge within the scope of the private property of the railway company. Note that measuring instrument 7 is not limited to those described above.

[0061] "Water level" refers to the water level around the bridge in a river when the railway tracks are installed on a bridge that crosses the river. "Flow rate" refers to the flow rate around the bridge in a river when the railway tracks are installed on a bridge that crosses the river.

[0062] The passenger information system 8 is a system for providing passengers with information about train operations, such as train schedules and operational restrictions. The passenger information system 8 displays various information, such as schedule information and predicted times for lifting restrictions, on display boards and other bulletin boards, and also broadcasts it via voice. The passenger information system 8 is installed within the station premises. The passenger information system 8 comprises an information acquisition unit 8a and a notification unit 8b. The passenger information system 8 also includes other functional units, such as a communication unit for communicating with the outside world, but their description is omitted here.

[0063] The information acquisition unit 8a acquires various types of information, including timetable information, restriction start time information, predicted restriction lifting time information, weather forecast information, platform congestion information, and train congestion information.

[0064] The notification unit 8b informs passengers of train operation-related information, such as train schedules and operational restrictions, by displaying it on a display board or by broadcasting it via voice.

[0065] WEB9 refers to websites operated by, for example, railway companies or businesses that provide information related to railways.

[0066] Next, the operation of the railway disaster prevention information system server 2S will be described. First, the processing of the disaster prevention information data acquisition unit 231 of the disaster prevention information processing unit 23 of the railway disaster prevention information system server 2S will be described. Figure 5 is a flowchart showing an example of the processing procedure in the disaster prevention information data acquisition unit of the disaster prevention information processing unit of the railway disaster prevention information system server according to Embodiment 1.

[0067] In step S110, the disaster prevention information data acquisition unit 231 periodically receives weather forecast information from the weather forecasting system 4. Then, the process proceeds to step S120.

[0068] In step S120, the disaster prevention information data acquisition unit 231 records weather forecast information in the external weather information DB 223 of the disaster prevention information storage unit 22. Then, the process proceeds to step S130.

[0069] In step S130, the disaster prevention information data acquisition unit 231 periodically receives observed values ​​from each measuring instrument 7. Then, the process proceeds to step S140.

[0070] In step S140, the disaster prevention information data acquisition unit 231 records the observed values ​​received from each measuring instrument 7 into the observed value DB 222 of the disaster prevention information storage unit 22. Then, the process proceeds to step S150.

[0071] In step S150, the disaster prevention information data acquisition unit 231 receives data on inspection history, inspection personnel plan, and station distance. The inspection history is entered via the network at the time the inspection is performed, for example, from a mobile terminal (not shown) held by the user, the inspector, which is an external device to the railway disaster prevention information system server 2S. The inspection personnel plan is entered via the network at the time the inspection personnel plan is created, for each inspection plan for the inspection section, for example, from a terminal (not shown) used by the user, such as a commander, which is an external device to the railway disaster prevention information system server 2S. Furthermore, for the same inspection, the inspection personnel plan is entered again at predetermined intervals, for example, every month or every year, after the initial entry. The station distance is entered via the network, for example, from a terminal (not shown) used by the user, such as a commander, which is an external device to the railway disaster prevention information system server 2S. Furthermore, since the station distance does not basically change, after the initial entry, it is entered as needed if there are changes or additions. Then, the process proceeds to step S160.

[0072] In step S160, if the disaster prevention information data acquisition unit 231 receives data in step S150, it records the data in the corresponding DB of the disaster prevention information storage unit 22. Specifically, if the disaster prevention information data acquisition unit 231 receives inspection history in step S150, it records the inspection history in the inspection history DB 221; if it receives personnel plan for inspection in step S150, it records personnel plan for inspection in the personnel plan DB 224; and if it receives station distance in step S150, it records station distance in the station distance DB 225.

[0073] With this, the series of processes performed by the disaster prevention information data acquisition unit 231 is completed.

[0074] Next, an overview of the processing in the disaster prevention information processing unit 23 of the railway disaster prevention information system server 2S will be described. Figure 6 is a flowchart showing an example of the overview of the processing procedure in the disaster prevention information processing unit of the railway disaster prevention information system server according to Embodiment 1. The timing of the start of the flowchart in Figure 6 is the timing of creating the future predicted timetable 322 if the predicted time for lifting the restrictions to be determined is the predicted time when the operational restrictions that are scheduled to be set in the future based on weather forecast information will be lifted. If the predicted time for lifting the restrictions to be determined is the predicted time when the operational restrictions that are currently set will be lifted, the process may start from step S220 after the operational restrictions have been issued.

[0075] In step S210, the restricted section determination unit 232 determines whether or not there are restricted sections along the railway line where train operations are restricted. The restricted section determination unit 232 obtains weather forecast information from the external weather information DB 223 of the disaster prevention information storage unit 22 and determines whether or not there are restricted sections along the railway line where train operations are restricted, based on the weather forecast information. The restricted section determination unit 232 determines whether or not there are restricted sections along the entire length of the railway line where train operations are restricted. The restricted section determination unit 232 compares the weather forecast information with predetermined restriction criteria values ​​and determines that sections where the weather forecast value given in the weather forecast information is equal to or greater than the predetermined restriction criteria value are restricted sections.

[0076] The regulatory standard values ​​are criteria used to determine the sections where train operations are restricted by comparing them with weather forecast information, that is, by comparing them with weather forecast values. The regulatory standard values ​​are determined individually for each type of observed environmental value along the railway line measured by the measuring instrument 7. Specifically, the regulatory standard values ​​are determined individually for each of the following: "precipitation," "wind speed," "wind direction," "water level," "snow depth," "flow rate," "rail temperature," "earthquake," and "landslide." The regulatory standard values ​​are predetermined and stored in the disaster prevention information storage unit 22.

[0077] If it is determined that there is a restricted section where traffic restrictions will be imposed, the result in step S210 is Yes, and the restricted section determination unit 232 creates information about the restricted section and transmits it to the restricted information creation unit 233. The process then proceeds to step S220. If it is determined that there is no restricted section where traffic restrictions will be imposed, the result in step S210 is No, and the calculation process for the predicted time of lifting the restrictions ends.

[0078] In step S220, the regulatory information creation unit 233 determines whether or not there are any trains subject to operational restrictions.

[0079] Figure 7 is the first diagram illustrating a method for determining whether or not there are restricted trains in the disaster prevention information processing unit of the railway disaster prevention information system server according to Embodiment 1. Figure 7 shows an example of a method for determining restricted trains, illustrated in a train schedule diagram. Figure 8 is the second diagram illustrating a method for determining whether or not there are restricted trains in the disaster prevention information processing unit of the railway disaster prevention information system server according to Embodiment 1. Figure 8 shows the predicted passing times of trains at each section boundary point in Figure 7. Figure 9 is the third diagram illustrating a method for determining whether or not there are restricted trains in the disaster prevention information processing unit of the railway disaster prevention information system server according to Embodiment 1. Figure 9 shows the start time of the restriction for the predicted restricted section in Figure 7.

[0080] In Figure 7, the horizontal axis represents time and the vertical axis represents distance. Figure 7 shows sections 0 through 4, which are demarcated sections of the railway line. In Figure 7, trains 1101 through 1103 each proceed from section 0 to section 4. Figure 8 shows the section boundary points, which are the boundaries between adjacent sections of the railway line, and the predicted section passage times, which are the times when each train passes through the section boundary points in the operation timetable shown in Figure 7. The solid shaded lines in Figure 7 represent the operation plan determined in the operation timetable, and trains 1101 through 1103 pass through each section boundary point at the predicted section passage times shown in Figure 8. Furthermore, as shown in Figure 9, the start times of the predicted restricted sections KR1 and KR2 set in the operation timetable of Figure 7 are given.

[0081] The regulation information creation unit 233 then determines which trains are subject to regulation by determining whether the predicted passing times of trains 1101 to 1103 at each section boundary point in Figure 8 are within the respective ranges of predicted regulation section KR1 and predicted regulation section KR2. For example, in section 1, trains 1101, 1102, and 1103 pass through the section boundary point between section 0 and section 1 within the range of predicted regulation section KR1. Also, in section 2, trains 1102 and 1103 pass through the section boundary points between sections 1 and 2 within the range of predicted regulation section KR2.

[0082] If it is determined that there are trains subject to operational restrictions, the answer in step S220 is Yes, and the process proceeds to step S230. If it is determined that there are no trains subject to operational restrictions, the answer in step S220 is No, and the calculation process for the predicted time of lifting the restrictions ends.

[0083] In step S230, the regulatory information creation unit 233 reads weather forecast information, observation values ​​from measuring instruments 7, and inspection history data of facilities along the railway line from the database of the disaster prevention information storage unit 22. Then, the process proceeds to step S240.

[0084] In step S240, the regulatory information creation unit 233 compares the weather forecast information with a predetermined regulatory standard value and sets the time when the weather forecast value given in the weather forecast information falls below the regulatory standard value, that is, the time when the weather forecast value given in the weather forecast information becomes less than the regulatory standard value, as the standard regulation lifting prediction time. After that, the process proceeds to step S250.

[0085] The predicted time for lifting the standard restriction is the time used as the basis for calculating the time when the operational restrictions will be lifted, and it is the time when the weather forecast value in the weather forecast information falls below the predetermined standard restriction value.

[0086] In step S250, the regulatory information creation unit 233 corrects the predicted time for lifting the standard restriction using the observed values ​​from the measuring instrument 7, the inspection history, the personnel plan for the inspection, and the distance to the office, as needed. Details of the correction of the predicted time for lifting the standard restriction will be described later. After that, the process proceeds to step S260.

[0087] In step S260, the regulation information creation unit 233 corrects the standard regulation lifting prediction time and sets it as the final regulation lifting prediction time. If correction of the standard regulation lifting prediction time is not necessary, the regulation information creation unit 233 sets the standard regulation lifting prediction time as the final regulation lifting prediction time. The regulation information creation unit 233 transmits the information of the finalized regulation lifting prediction time to the regulation information notification unit 234. The regulation information notification unit 234 transmits the information of the regulation lifting prediction time for the restricted section to train 6a, the operation management system 3, and WEB9.

[0088] By performing the above processing, the disaster prevention information processing unit 23 of the railway disaster prevention information system server 2S determines the predicted time for lifting the restrictions, and the information of the determined predicted time for lifting the restrictions is transmitted to train 6a, the operation management system 3, and WEB 9.

[0089] Next, we will explain in detail the process by which the regulation information creation unit 233 of the disaster prevention information processing unit 23 of the railway disaster prevention information system server 2S corrects the standard regulation release prediction time to calculate the regulation release prediction time. Figure 10 is a first flowchart showing an example of the detailed procedure for calculating the regulation release prediction time in the regulation information creation unit of the railway disaster prevention information system server according to Embodiment 1. Figure 11 is a second flowchart showing an example of the detailed procedure for calculating the regulation release prediction time in the regulation information creation unit of the railway disaster prevention information system server according to Embodiment 1.

[0090] The flowcharts in Figures 10 and 11 begin after the restricted section determination unit 232 determines that there is a restricted section along the line where train operations will be restricted. The flowcharts in Figures 10 and 11 begin after the train operations restriction is issued if the predicted time for lifting the restriction is the predicted time when the currently set train operations restriction will be lifted. The flowcharts in Figures 10 and 11 begin when the future predicted timetable 322 is created if the predicted time for lifting the restriction is the predicted time when a train operations restriction scheduled to be set in the future will be lifted, based on weather forecast information.

[0091] In step S310, the regulatory information creation unit 233 determines whether or not there are any trains subject to operational restrictions. Step S310 is performed in the same manner as step S220.

[0092] If it is determined that there are trains subject to operational restrictions, the result in step S310 is Yes, and the process proceeds to step S320. If it is determined that there are no trains subject to operational restrictions, the result in step S310 is No, and the calculation process for the predicted time of lifting the restrictions ends.

[0093] In step S320, the regulation information creation unit 233 reads weather forecast information from the external weather information DB 223. The regulation information creation unit 233 reads weather forecast information for the current and subsequent periods for the restricted section of track where the restricted train will be running. Then, the process proceeds to step S330.

[0094] In step S330, the regulatory information creation unit 233 reads the observed values ​​from each measuring instrument 7 from the observed value DB 222. The regulatory information creation unit 233 reads the current observed values ​​from each measuring instrument 7 and past observed values ​​from each measuring instrument 7 for the operational restriction section in which the restricted train is running. Then, the process proceeds to step S340.

[0095] In step S340, the regulatory information creation unit 233 reads inspection history information, which is data on past inspection results of facilities along the railway line, from the inspection history DB 221. The regulatory information creation unit 233 reads the inspection history information for the operational restriction section in which the restricted train will run. After that, the process proceeds to step S350.

[0096] In step S350, the regulation information creation unit 233 compares the weather forecast information with a predetermined regulatory standard value and sets the time when the weather forecast value given in the weather forecast information falls below the regulatory standard value, that is, the time when the weather forecast value given in the weather forecast information becomes less than the regulatory standard value, as the standard regulation lifting prediction time. For example, if precipitation is used as the weather forecast information, suppose that for section A of the railway line, the regulatory standard value for precipitation at which a speed restriction, which is an operational restriction, is issued is set to 80 mm. In this case, the time when the precipitation for section A in the weather forecast information becomes less than 80 mm becomes the standard regulation lifting prediction time. Then, the process proceeds to step S360.

[0097] In step S360, the regulation information creation unit 233 determines whether the section on which the regulated train runs is related to the river's water level. That is, the regulation information creation unit 233 determines whether a river flows through the restricted section on which the regulated train runs. The regulation information creation unit 233 determines that the section on which the regulated train runs is related to the river's water level if the tracks are laid over a river that flows through the restricted section. The regulation information creation unit 233 determines that the section on which the regulated train runs is not related to the river's water level if the tracks are not laid over a river that flows through the restricted section.

[0098] If it is determined that the section in which the restricted train runs is related to the river's water level, the answer in step S360 is Yes, and the process proceeds to step S370. If it is determined that the section in which the restricted train runs is not related to the river's water level, the answer in step S360 is No, and the process proceeds to step S420.

[0099] In step S370, the regulatory information creation unit 233 obtains river water level information from the observation values ​​of each measuring instrument 7 read in step S330. The regulatory information creation unit 233 obtains river water level information in the section on which the regulated train runs, that is, river water level information measured by the measuring instrument 7 installed on the bridge girders of the river bridges located in the operational regulation section on which the regulated train runs. The regulatory information creation unit 233 obtains information on the current river water level and information on past river water levels. After that, the process proceeds to step S380.

[0100] In step S380, the regulatory information creation unit 233 acquires predicted information on the future water level of the river. The regulatory information creation unit 233 acquires predicted water level information, which is predicted information on the future water level of the river, for rivers located in the operational restriction section where the regulated train will run. The predicted water level is the predicted value of the river water level at the location of the bridge on the river located in the operational restriction section where the regulated train will run. The method for acquiring the predicted water level information will be described later. After that, the process proceeds to step S390.

[0101] In step S390, the regulatory information creation unit 233 determines whether the predicted future water level of the river at the predicted time of lifting the standard regulation is equal to or greater than a predetermined regulatory standard value.

[0102] If it is determined that the predicted future water level of the river at the predicted time for lifting the standard restriction is equal to or greater than the predetermined regulatory standard value, the answer in step S390 is Yes, and the process proceeds to step S400. If it is determined that the predicted future water level of the river at the predicted time for lifting the standard restriction is less than the predetermined regulatory standard value, the answer in step S390 is No, and the process proceeds to step S420. For example, suppose that the regulatory standard value for the water level of a river at which a suspension of operations is issued is set at 3m. In this case, if the predicted future water level of the river at the predicted time for lifting the standard restriction is 3m or more, for example, if the predicted future water level of the river at the predicted time for lifting the standard restriction is 4m, the answer in step S390 is Yes, and the process proceeds to step S400. If the predicted future water level of the river at the predicted time for lifting the standard restriction is less than 3m, for example, if the predicted future water level of the river at the predicted time for lifting the standard restriction is 2.5m, the answer in step S390 is No, and the process proceeds to step S420.

[0103] In step S400, the regulatory information creation unit 233 determines the water level drop time, which is the time it takes for the predicted future water level of the river to fall below the regulatory standard value from the time of the predicted lifting of the standard regulation. That is, based on the predicted future water level of the river, the regulatory information creation unit 233 calculates how many minutes after the predicted lifting of the standard regulation the predicted water level of the river will fall below the regulatory standard value. The water level drop time is indicated in minutes, such as XX minutes. Then, the process proceeds to step S410.

[0104] In step S410, the regulatory information creation unit 233 adds the water level drop time to the standard regulatory release prediction time. That is, the regulatory information creation unit 233 corrects the standard regulatory release prediction time by adding the water level drop time to the standard regulatory release prediction time. After that, the process proceeds to step S420.

[0105] In step S420, the regulatory information creation unit 233 determines whether or not it is necessary to inspect the railway infrastructure related to train operation. When railway infrastructure restrictions are set because observed values ​​of the railway environment exceed regulatory standards, whether or not inspection of the railway infrastructure is necessary after the restrictions are lifted depends on the type of observed value of the railway environment that caused the restrictions to be set. For example, if railway infrastructure restrictions are set because the "rail temperature" exceeds regulatory standards, no inspection is required after the restrictions are lifted. If railway infrastructure restrictions are set because observed values ​​of any type of railway environment other than "rail temperature" exceed regulatory standards, an inspection of the railway infrastructure is required after the restrictions are lifted. The disaster prevention information storage unit 22 has in advance information on the types of observed values ​​of the railway environment that require inspection after the restrictions are lifted when railway infrastructure restrictions are set because the observed values ​​exceed regulatory standards.

[0106] If it is determined that inspection of railway infrastructure related to train operation is necessary, the answer in step S420 is Yes, and the process proceeds to step S430. If it is determined that inspection of railway infrastructure related to train operation is not necessary, the answer in step S420 is No, and the process proceeds to step S490.

[0107] In step S430, the regulatory information creation unit 233 searches for past inspection data for the restricted traffic section from the inspection history information read in step S340. Then, it proceeds to step S440.

[0108] In step S440, the regulatory information creation unit 233 reads personnel plan information for inspections of the restricted traffic section from the personnel plan DB 224 and station distance information for the restricted traffic section from the station distance DB 225. Then proceeds to step S450.

[0109] In step S450, the regulatory information creation unit 233 compares the number of inspectors in past inspection data for the searched traffic restriction section with the number of inspectors in the personnel plan for inspections of the traffic restriction section obtained from the personnel plan DB 224. Then, the process proceeds to step S460.

[0110] In step S460, the regulatory information creation unit 233 determines, based on the comparison results in step S450, whether the number of inspectors in the past inspection data for the restricted traffic section differs from the number of inspectors in the personnel plan for the inspection of the restricted traffic section.

[0111] If it is determined that the number of inspectors in past inspection data for the restricted traffic section differs from the number of inspectors in the personnel plan for inspections of the restricted traffic section, the answer in step S460 is Yes, and the process proceeds to step S470. If it is determined that the number of inspectors in past inspection data for the restricted traffic section differs from the number of inspectors in the personnel plan for inspections of the restricted traffic section, the answer in step S460 is No, and the process proceeds to step S490.

[0112] In step S470, the regulatory information creation unit 233 determines the estimated inspection completion time for the inspection of the restricted traffic section, including the distance to the inspection station, corresponding to the number of inspectors in the personnel plan for the inspection of the restricted traffic section.

[0113] The estimated inspection completion time is the predicted time for the inspection to be completed. This time is the estimated time required to complete the inspection of the facilities along the railway line in the restricted section after the lifting of the restrictions. Then proceed to step S480.

[0114] In step S480, the regulation information creation unit 233 corrects the standard regulation lifting prediction time by adding the predicted inspection completion time to the standard regulation lifting prediction time, thereby using the inspection time required for inspecting the facilities along the railway line in the restricted section after the restrictions are lifted. The regulation information creation unit 233 corrects the standard regulation lifting prediction time by adding the predicted inspection completion time to the standard regulation lifting prediction time, or by adding the predicted inspection completion time to the time when the water level drop time is added to the standard regulation lifting prediction time, thereby using the inspection time required for inspecting the facilities along the railway line in the restricted section after the restrictions are lifted. The process then proceeds to step S490.

[0115] In step S490, the regulatory information creation unit 233 determines the predicted time for lifting the restrictions. The regulatory information creation unit 233 determines one of the following times as the predicted time for lifting restrictions: the standard predicted time for lifting restrictions, the time when the water level drop time is added to the standard predicted time for lifting restrictions, the time when the inspection completion time is added to the standard predicted time for lifting restrictions, or the time when the water level drop time and the inspection completion time are added to the standard predicted time for lifting restrictions.

[0116] By performing the above processing, the calculation process for the predicted time of restriction lifting is completed. The timing at which the restriction information creation unit 233 reads various information from each DB of the disaster prevention information storage unit 22 is not limited as long as the predicted time of restriction lifting can be calculated as described above.

[0117] According to Embodiment 1 described above, a train operation management support system is realized that includes a restricted section determination unit that determines restricted sections where train operations will be restricted based on weather forecast information, and a restricted information creation unit that predicts the restricted time for restricted sections based on weather forecast information and information on the inspection history of facilities along the railway line.

[0118] As described above, in the operation management support system 1 of Embodiment 1, the restricted section determination unit 232 determines the restricted section where train operations will be restricted based on weather forecast information, and the restriction information creation unit 233 predicts the restriction time for the restricted section based on weather forecast information and information on the inspection history of facilities along the railway line. Therefore, by using the inspection history information in predicting the restriction time for the restricted section, the restriction information creation unit 233 can predict a restriction time with high prediction accuracy, thereby improving the prediction accuracy of the restriction time. As a result, the restriction information creation unit 233 can predict the restriction time for the restricted section more accurately.

[0119] For example, if inspections are required at multiple locations simultaneously, there may not be enough inspectors, and it will take time to complete the inspections, thus delaying the resumption of train 6a's operation. However, this time is not taken into account based solely on weather forecast information, so the actual resumption time may differ significantly from the predicted time. The operation management support system 1 can predict the restriction time for restricted sections of train operation based on the inspection completion time, which is information from the inspection history of facilities along the railway line.

[0120] Furthermore, the regulation information creation unit 233 predicts the regulation time by correcting the standard regulation lifting prediction time calculated based on weather forecast information based on the inspection completion time, which is information from the inspection history. Furthermore, the regulation information creation unit 233 predicts the regulation time by correcting the standard regulation lifting prediction time calculated based on weather forecast information based on the number of inspectors who will be inspecting the facilities along the line. Furthermore, the regulation information creation unit 233 predicts the regulation time by correcting the standard regulation lifting prediction time calculated based on weather forecast information based on the observed values ​​of the measuring instrument 7. In other words, the regulation information creation unit 233 predicts the regulation time by adding or subtracting the inspection completion time, which fluctuates based on the number of inspectors and the observed values ​​of the measuring instrument 7, to the standard regulation lifting prediction time. As a result, the regulation information creation unit 233 can improve the accuracy of predicting the regulation time for the restricted section of the train.

[0121] Therefore, the operation management support system 1 of Embodiment 1 can improve the accuracy of predicting the restriction time for operation restrictions in the operation management of train 6a. This further has the effect of enabling railway operators' dispatchers to manage train operations with greater accuracy.

[0122] Embodiment 2. Embodiment 2 describes a case in which, in predicting the inspection completion time in the railway disaster prevention information system server 2S according to Embodiment 1, association information is used, which is compiled by linking past observation data, past inspection personnel plans, and past inspection completion times for predetermined sections along the railway line.

[0123] Figure 12 shows an example of an association information table according to Embodiment 2. In the association information table shown in Figure 12, association information is compiled in tabular format by the regulatory information creation unit 233 and stored in the disaster prevention information storage unit 22. In the association information table shown in Figure 12, for Section 1, which is a predetermined section along the railway line, actual data of past observed values, "precipitation (mm)", data of past inspection personnel plans, "inspection personnel (people)", and data of past "inspection completion time (minutes)" are compiled and associated for each range of "precipitation". The ranges of "precipitation" are defined as "20 mm or more and less than 30 mm", "30 mm or more and less than 40 mm", "40 mm or more and less than 50 mm", and "50 mm or more". The ranges of "precipitation" are just examples and can be set as appropriate.

[0124] Figure 13 shows another example of the association information table according to Embodiment 2. In the association information table shown in Figure 13, association information is compiled in tabular form by the regulatory information creation unit 233 and stored in the disaster prevention information storage unit 22. In the association information table shown in Figure 13, for Section 1, which is a predetermined section along the railway line, the actual data of "wind speed (m / s)" which is a past observation value, the data of "inspection personnel (people)" which is a past inspection personnel plan, and the data of past "inspection completion time (minutes)" are compiled and associated for each range of "wind speed". The ranges of "wind speed" are "25 m / s or more and less than 30 m / s", "30 m / s or more and less than 35 m / s", "35 m / s or more and less than 40 m / s", and "40 m / s or more". The ranges of "wind speed" are just examples and can be set as appropriate.

[0125] Note that the association information tables shown in Figures 12 and 13 are examples, and association information tables are created for each type of observed value, such as water level. Furthermore, the association information does not need to be compiled in a tabular format, as long as it can be linked to past observation data, past inspection personnel plans, and past inspection completion times.

[0126] Figure 14 is a flowchart showing an example of the procedure for creating an association information table according to Embodiment 2. Figure 14 shows, as an example, the method for creating the association information shown in Figure 12.

[0127] In step S610, the regulatory information creation unit 233 reads the actual inspection history data for section 1 from the inspection history DB 221. Then, the process proceeds to step S620.

[0128] In step S620, the regulatory information creation unit 233 aggregates the actual inspection history data for section 1, which was read in step S610, by "precipitation" range, and creates the association information shown in Figure 12. The inspection completion time is, for example, the average value of multiple data for each "precipitation" range. This creates the association information tables shown in Figures 12 and 13.

[0129] Next, a method for searching for inspection completion time using association information will be described. Figure 15 shows an example of a weather forecast information table according to Embodiment 2. In the weather forecast information table shown in Figure 15, weather forecast information stored in the external weather information DB 223 is compiled in a tabular format by the regulatory information creation unit 233 and stored in the disaster prevention information storage unit 22. In the weather forecast information table shown in Figure 15, for section 1, which is a predetermined section along the railway line, weather forecast information such as "weather" data, "precipitation (mm)" data, "wind speed (m / s)" data, and "temperature (degrees)" data are compiled and associated for each "time". The "times" are set to "13:00", "14:00", "15:00", and "16:00". The "times" are just examples and can be set as appropriate.

[0130] For example, suppose the precipitation threshold for issuing a speed restriction, which is a traffic restriction, is set at 20 mm. Also, suppose the precipitation threshold for issuing a service suspension, which is another traffic restriction, is set at 25 mm. Based on the weather forecast information table shown in Figure 15, the restriction information creation unit 233 determines that the precipitation will reach 25 mm at 14:00, and therefore issues a service suspension at 14:00. The restriction information creation unit 233 adds the actual past inspection completion times obtained from the association information table to the predicted time for lifting the restriction, which is the time when the precipitation falls below the restriction threshold in the weather forecast information.

[0131] The regulation information creation unit 233 sets the time when the amount of precipitation in section 1 falls below the regulatory threshold of 20 mm, as the standard regulation lifting prediction time, based on the weather forecast information. Based on the weather forecast information table shown in Figure 15, the regulation information creation unit 233 sets 16:00 as the standard regulation lifting prediction time, since the amount of precipitation will be 10 mm at 16:00.

[0132] The regulatory information creation unit 233 searches the association information table in Figure 12 for the inspection completion time when the rainfall is 25 mm and obtains the information for an inspection completion time of "5 minutes". Then, the regulatory information creation unit 233 sets the inspection completion time of "5 minutes" obtained from the association information table in Figure 12 as the predicted inspection completion time.

[0133] Then, the regulatory information creation unit 233 corrects the standard regulatory restriction lifting predicted time by adding "5 minutes," which is the predicted inspection completion time obtained based on the association information table in Figure 12, to 16:00, which is the standard regulatory restriction lifting predicted time, thereby correcting the standard regulatory restriction lifting predicted time with the predicted inspection completion time required for inspecting the facilities along the railway line in the restricted section after the operational restriction is lifted. The regulatory information creation unit 233 then confirms 16:05, the time after correcting the standard regulatory restriction lifting predicted time, as the regulatory restriction lifting predicted time.

[0134] In actual practice, inspections begin at 16:00 and are completed in 5 minutes, resulting in a resumption of service at 16:05. This ensures that the actual resumption time coincides with the predicted time for lifting the restrictions. On the other hand, if the predicted time for completing inspections of the trackside facilities in the restricted section after the restrictions are lifted is not considered, the predicted time for lifting the restrictions becomes 16:00, resulting in a larger discrepancy with the actual resumption time. Thus, by considering the predicted time for completing inspections of the trackside facilities in the restricted section after the restrictions are lifted, it is possible to predict both the resumption time and the predicted time for lifting the restrictions more accurately. The resumption time of service is the same as the predicted time for lifting the restrictions.

[0135] Furthermore, let's consider a scenario where, for example, the current observed rainfall in section 1 is 50 mm, and weather forecast information indicates that the rainfall will reach 80 mm in one hour. In the past, when rainfall similarly increased from 50 mm to 80 mm in one hour, the associated information table retrieves information indicating an inspection completion time of "5 minutes". In this case as well, by adding "5 minutes" to the predicted time when the rainfall in section 1 falls below the regulatory threshold of 20 mm according to the weather forecast information, the predicted time when the regulatory restrictions will be lifted can be corrected to reflect the predicted time when the regulatory restrictions will be lifted, which is the estimated time required to inspect the equipment along the railway line in the restricted section after the restrictions have been lifted.

[0136] Furthermore, if, for example, the inspection plan allows for a reduction in inspection time by increasing the number of inspection personnel compared to the past performance data recorded in the associated information table, the predicted time for lifting the restriction can be corrected by subtracting the time saved from the inspection completion time obtained from the past performance data. This allows the restriction information creation unit 233 to improve the accuracy of predicting the restriction time for the restricted section of the route.

[0137] Furthermore, the regulatory information creation unit 233 may have a machine learning device with existing machine learning capabilities. Figure 16 is a diagram illustrating the process by which the regulatory information creation unit having a machine learning device searches for past weather information similar to weather forecast information in Embodiment 2. In Figure 16, for interval A, the actual precipitation data, which is the change in past observed values, and the change in future precipitation obtained from weather forecast information are shown corresponding to time.

[0138] If such information is available, the machine learning device extracts information similar to the future precipitation changes obtained from weather forecast information from past precipitation change data. The machine learning device obtains the inspection completion time from the association information table corresponding to the extracted past data and sets it as the inspection completion prediction time. Then, the machine learning device can correct the standard restriction lifting prediction time by adding the inspection completion prediction time to the standard restriction lifting prediction time. As a result, the restriction information creation unit 233 can correct the standard restriction lifting prediction time using the inspection completion prediction time recorded in the association information table that has changes in observed values ​​similar to the future changes in observed values.

[0139] As described above, in Embodiment 2, the regulatory information creation unit 233 can predict a more accurate standard regulatory release time by adding the inspection completion time included in the inspection history information to the standard regulatory release prediction time.

[0140] The regulatory information creation unit 233 then uses a correlation information table that associates past observation data, past inspection personnel plans, and past inspection completion times for predetermined sections along the railway line when predicting the inspection completion time. By associating past observation data, past inspection personnel plans, and past inspection completion times with each other and compiling them into a correlation information table, it becomes easier to search for the inspection completion time when predicting the inspection completion time, and the accuracy of the prediction is improved compared to predicting the restriction lifting time using only weather forecast information.

[0141] Furthermore, by acquiring current observation values ​​in addition to weather forecast information, the regulatory information creation unit 233 can also predict the inspection completion time based on the change in observation values ​​from the present to the future. In other words, based on the association information table, the regulatory information creation unit 233 can predict the predicted time for lifting traffic restrictions from the present to the future, and predict the predicted time for lifting traffic restrictions from the future to even further into the future, such as tomorrow. In addition, during typhoons, by creating an association information table that combines wind speed and precipitation, it is possible to predict the inspection completion time with greater accuracy and the predicted time for lifting traffic restrictions with greater accuracy when a typhoon of the same magnitude is expected in the future.

[0142] Furthermore, the regulatory information creation unit 233 only needs to determine regulatory criteria values ​​for deciding whether to issue operational restrictions such as train service suspensions. By comparing the acquired weather forecast information with the regulatory criteria values ​​stored in the disaster prevention information storage unit 22, it can easily predict the time when restrictions will be lifted.

[0143] Furthermore, the regulatory information creation unit 233 can use machine learning functionality to perform searches, and even if there is no associated information table with similar changes in observed values ​​to the changes in observed values ​​in the weather forecast information, it can predict the inspection completion time from an associated information table similar to the changes in observed values ​​in the weather forecast information and correct the standard restriction lifting prediction time. In other words, the regulatory information creation unit 233 calculates the standard restriction lifting prediction time based on the weather forecast information. The regulatory information creation unit 233 also predicts the inspection completion time in the restricted operation section based on a machine learning device that has learned associated information including data from the measured values ​​of the measuring instrument 7 that measures the environment along the train line, data from the personnel plan for the inspection, and data from the inspection completion time. The regulatory information creation unit 233 can then predict the restriction time by correcting the standard restriction lifting prediction time based on the predicted inspection completion time. The machine learning device may be located outside the operation management support system 1 or may be provided within the operation management support system 1. Furthermore, the associated information table created by the machine learning device is stored in the disaster prevention information storage unit 22.

[0144] Embodiment 3. Embodiment 3 describes a method for acquiring predicted water levels, which are prediction information for the future water level of a river, as shown in step S380 of Embodiment 1 above, in the railway disaster prevention information system server 2S according to Embodiment 1. Figure 17 is the first diagram illustrating the method for acquiring predicted water levels in Embodiment 3. Figure 17 shows measuring instruments 7 installed by the railway company and measuring instruments 7a installed by the national or local government. Predicting the future water level of a river requires environmental information such as the flow rate and precipitation in the upper reaches of the river 12. However, as shown in Figure 17, the measuring instruments 7 installed by the railway company are only installed in the area along the railway tracks 11 within the railway company's private property, and the flow meters and water level gauges are only installed on the bridge girders of bridges where the railway tracks 11 are located. For this reason, the measuring instruments 7 installed by the railway company cannot acquire observed values ​​of flow rate and precipitation along the river upstream of the river 12.

[0145] On the other hand, the national or local government installs measuring instruments 7a at upstream points along the river 12 to measure the flow rate along the river and the amount of rainfall upstream of the river 12, and conducts water level forecasts for the river 12. The water level forecasts for the river 12 by the national or local government are conducted to predict the possibility of levee breaches. For this reason, the water level forecasts for the river 12 by the national or local government generally predict increases in water level, not decreases, nor do they provide pinpoint predictions for the water level at the bridge where the railway tracks 11 are located.

[0146] Therefore, in Embodiment 3, the disaster prevention information data acquisition unit 231 acquires actual measured data of river flow rate along the river upstream of River 12 and precipitation in the upstream area of ​​River 12 from information published by the national or local government, and stores it as historical performance data in the observation value DB 222. The disaster prevention information data acquisition unit 231 acquires actual measured data of river flow rate along the river upstream of River 12 and precipitation in the upstream area of ​​River 12 from a website operated by the national or local government. Figure 18 is a second diagram illustrating the method of acquiring predicted water levels in Embodiment 3. Figure 18 schematically illustrates the information published on a website operated by the national or local government.

[0147] Then, the regulatory information creation unit 233 stores the existing water level prediction model. The regulatory information creation unit 233 combines the actual measured data of current and past flow rates and precipitation obtained by the flow meters and water level gauges, which are measuring instruments 7 installed by the railway company, with the actual measured data of current and past flow rates and precipitation obtained from national or local government information, and uses the existing water level prediction method based on the existing water level prediction model to predict the future water level of the river 12. One example of an existing water level prediction method is the nearest neighbor method. With the nearest neighbor method, even if the flow rate of the entire river basin of the river 12 is not known precisely, by collecting data on precipitation from a small number of observation points and the water level patterns of the river 12, it is possible to predict the water level of the river 12 at the location of the bridge on the river 12 at the point where the railway tracks 11 are located in the operational restriction section where the regulated trains run.

[0148] As a result, the regulatory information creation unit 233 can acquire predicted water level information, which is prediction information for the future water level of the river 12, and can calculate the predicted time for lifting the restrictions by correcting the standard predicted time for lifting restrictions with the water level drop time, which is the time it takes for the future predicted water level of the river 12 to drop below the standard restriction limit from the time of the standard predicted time for lifting restrictions. In other words, the regulatory information creation unit 233 can calculate the standard predicted time for lifting restrictions based on weather forecast information and predict the restriction time by correcting the standard predicted time for lifting restrictions based on the observed values ​​of measuring instruments 7,7a that measure the environment along the train line. Furthermore, if the railway tracks 11 are installed over the river 12 located in the restricted section of the train, the regulatory information creation unit 233 can predict the restriction time by correcting the standard predicted time for lifting restrictions based on the water level drop time, which is the time it takes for the observed values, including the predicted water level of the river 12, to drop below a predetermined restriction limit.

[0149] Therefore, according to Embodiment 3, the regulation information creation unit 233 of the disaster prevention information processing unit 23 of the railway disaster prevention information system server 2S can improve the accuracy of predicting the time when trains will resume operation at stations 13 located near the river 12 by reflecting the predicted water level information of the river 12 at the location of the bridge over the river 12, which is located in the restricted operation section where the restricted trains are running, in the predicted time when the restrictions will be lifted.

[0150] Embodiment 4. Embodiment 4 describes a method for determining the estimated inspection completion time corresponding to the number of inspectors in the personnel plan for inspections of the restricted-operation section, as shown in step S470 of Embodiment 1, in the railway disaster prevention information system server 2S according to Embodiment 1.

[0151] Figure 19 shows the first association information table according to Embodiment 4. Figure 20 shows the second association information table according to Embodiment 4. The first association information table shown in Figure 19 is association information compiled by associating past observation data, the number of inspection personnel (which is the personnel plan for past inspections), and the past inspection completion time for section 1 along the railway line, in the case where there is one inspection person. The second association information table shown in Figure 20 is association information compiled by associating past observation data, the number of inspection personnel (which is the personnel plan for past inspections), and the past inspection completion time for section 1 along the railway line, in the case where there are two inspection personnel.

[0152] In Embodiment 4, as described in Embodiment 2 above, when the regulatory information creation unit 233 obtains the estimated inspection completion time from the associated information, it determines the estimated inspection completion time corresponding to the number of people inspected.

[0153] In the second embodiment described above, based on the predicted rainfall amount of "25 mm" at 14:00, the time for completing the inspection when the rainfall is 25 mm was searched in the association information table in Figure 12, and information for the time for completing the inspection of "5 minutes" was obtained.

[0154] Here, we assume that information regarding the number of personnel scheduled to be inspected in this inspection, namely two people, is entered into the regulatory information creation unit 233 by a commander from outside the railway disaster prevention information system server 2S. In this case, when the regulatory information creation unit 233 obtains the information that there are two people scheduled to be inspected in this inspection, it searches the second association information table in Figure 20, which is an association information table for cases where there are two people, for the inspection completion time when the rainfall is 25 mm, and obtains the information that the inspection completion time is "4 minutes". Then, the regulatory information creation unit 233 sets the inspection completion time of "4 minutes" obtained from the association information table in Figure 20 as the predicted inspection completion time.

[0155] For similar rainfall amounts, the inspection completion time varies depending on the number of inspectors, but simply increasing the number of inspectors from one to two does not halve the inspection completion time. In Embodiment 4, when the regulatory information creation unit 233 obtains the predicted inspection completion time from the associated information, it can determine the predicted inspection completion time corresponding to the number of inspectors.

[0156] Then, the regulatory information creation unit 233 corrects the standard regulatory restriction lifting predicted time by adding "4 minutes," which is the predicted inspection completion time obtained from the second association information table in Figure 20, to 16:00, which is the standard regulatory restriction lifting predicted time, thereby correcting the standard regulatory restriction lifting predicted time with the predicted inspection completion time required for inspecting the facilities along the railway line in the restricted section after the operational restriction is lifted. The regulatory information creation unit 233 then confirms 16:04, the time after correcting the standard regulatory restriction lifting predicted time, as the regulatory restriction lifting predicted time.

[0157] This allows the regulatory information creation unit 233 to set an estimated inspection completion time considering the number of inspection personnel and calculate an estimated time for lifting the restrictions.

[0158] Furthermore, the regulatory information creation unit 233 may be equipped with a machine learning device 233a, and the inspection completion time may be predicted by the machine learning device 233a. Figure 21 is a diagram illustrating how the regulatory information creation unit predicts the inspection completion time using a machine learning device in Embodiment 4.

[0159] The machine learning device 233a can predict the inspection completion time for section 1 of the railway line based on the conditions of the inspection planned for the current inspection, using past performance data, information on the shape of section 1 of the railway line, information on the distance to the inspection station, information on the number of inspection personnel planned for the current inspection, and observed values. The information on past performance data includes correlation information that links past observed value data, past inspection personnel plans, and past inspection completion times. For example, it includes information corresponding to Figure 19, which includes location, the type of observed value (precipitation), the number of inspection personnel, and the inspection completion time.

[0160] Figure 22 shows an example of the track shape used by the regulatory information creation unit with a machine learning device in Embodiment 4 when predicting the inspection completion time. Figure 22 shows the shape of a straight track 11. Figure 23 shows another example of the track shape used by the regulatory information creation unit with a machine learning device in Embodiment 4 when predicting the inspection completion time. Figure 23 shows the shape of a track 11 that branches into two midway. Figure 24 shows an example of the station distance DB used by the regulatory information creation unit with a machine learning device in Embodiment 4 when predicting the inspection completion time. The station distance DB 225 in Figure 24 includes data for the section where the inspection is performed and data for the station distance corresponding to that section.

[0161] Since the inspection completion time varies depending on the number of inspectors, if an inspection is conducted with a number of inspectors not recorded in past records, it is necessary to calculate the inspection completion time. While the inspection completion time varies depending on the number of inspectors for similar rainfall amounts, simply increasing the number of inspectors from one to two does not automatically halve the completion time. Furthermore, depending on the shape of the track 11 (e.g., straight tracks 11, branching tracks 11), the inspection completion time may remain unchanged even with an increase in inspectors, or it may decrease. Additionally, past inspection completion times take into account the distance from the inspection station. However, if the distance from the inspection station changes, the inspection completion time will also change.

[0162] Therefore, the machine learning device 233a accumulates past performance data, information on the shape of the track 11, and information on the distance to the inspection station for each section of the track 11, and learns the inspection completion time corresponding to the location, type of observed value, and number of inspection personnel for each section. Then, when the machine learning device 233a receives information on the shape of the track 11 for a section and information on the number of inspection personnel planned for the current inspection, it can retrieve the inspection completion time from past performance data using the shape of the track 11 and the planned number of inspection personnel and distance to the inspection station for the current inspection, and predict the inspection completion time.

[0163] Note that the station distance information only needs to be entered if the station distance changes. For example, the station distance can be used to predict the inspection completion time in cases such as when there is no past data for a new section, when the inspection is large-scale, or when support inspectors are called in from a different station due to personnel shortages, etc. For example, when predicting the inspection completion time in a case where there is no past data for the inspection completion time when there are three inspectors, the station distance will be taken into consideration. This makes it possible to calculate the inspection completion time even when there is no past inspection data or when support inspectors are coming from a different station.

[0164] For example, if an inspector comes to the inspection section from station B instead of station A, which corresponds to past performance, the distance to the inspection will change. Also, if different inspectors are stationed at different stations, the distance to each station may differ. In such cases, the machine learning device 233a will also reflect the distance to each inspector's station in the inspection time.

[0165] Therefore, the machine learning device 233a does not need to consider the station distance when calculating the estimated inspection completion time if the station distance corresponding to the past inspection performance data for the restricted traffic section is the same as the station distance for the restricted traffic section obtained from the station distance DB 225. In other words, the station distance is considered only when the station distance in the past inspection performance data for the restricted traffic section is different from the station distance for the restricted traffic section obtained from the station distance DB 225, and the estimated inspection completion time corresponding to the number of inspectors in the inspection personnel plan is calculated.

[0166] According to Embodiment 4, the regulatory information creation unit 233 can set an estimated inspection completion time considering the number of inspection personnel and calculate an estimated time for lifting the restrictions.

[0167] Furthermore, according to Embodiment 4, the regulatory information creation unit 233, equipped with the machine learning device 233a, predicts the inspection completion time by combining past performance data with conditions such as the shape of the track 11, the number of inspection personnel, and the distance to the inspection station for the current inspection, thereby enabling highly accurate predictions of the inspection completion time. In addition, if there is no data that matches the shape of the track 11, the number of inspection personnel, and the distance to the inspection station planned for the current inspection, the disaster prevention information processing unit 23, equipped with the machine learning device 233a, predicts the inspection completion time corresponding to conditions similar to those in question. As a result, the regulatory information creation unit 233 can obtain a more accurate predicted inspection completion time by reflecting the tacit knowledge of the inspectors regarding the variation in inspection time due to conditions such as the shape of the track 11, the number of inspection personnel, and the distance to the inspection station.

[0168] Embodiment 5. Embodiment 5 describes a case in which, in the operation management support system 1 according to Embodiment 1, information on the predicted time of lifting restrictions is transmitted from the railway disaster prevention information system server 2S to the operation management system server 3S.

[0169] Figure 25 shows the processing of the railway disaster prevention information system server in Embodiment 5. The restriction information creation unit 233 of the railway disaster prevention information system server 2S transmits the calculated information on the predicted time of restriction lifting to the restriction information notification unit 234. When the restriction information notification unit 234 receives the information on the predicted time of restriction lifting, it transmits the information on the predicted time of restriction lifting to the operation management data acquisition unit 331 of the operation management processing unit 33 of the operation management system server 3S. The operation management data acquisition unit 331 receives the information on the predicted time of restriction lifting.

[0170] Furthermore, the regulation information creation unit 233 of the railway disaster prevention information system server 2S transmits the calculated information on the predicted time of lifting the restrictions to WEB9. Specifically, transmitting to WEB9 means displaying it on the display unit 9a of a device that displays WEB9. Examples of display units 9a that display WEB9 include the screen of a terminal such as a mobile device owned by a user of the railway, signage, and electronic display boards. The transmission of information on the predicted time of lifting restrictions is done to inform general users of the railway of the predicted time when the operational restrictions will be lifted.

[0171] There are no restrictions on how the information regarding the predicted time of lifting restrictions is used in the operation management system 3 and WEB9. For example, the operation management system server 3S can use the information regarding the predicted time of lifting restrictions to create a timetable, but the way in which the operation management system server 3S utilizes this information is not limited to this. For example, the operation management system server 3S can send the predicted time of lifting restrictions to WEB9 as the time when train service will resume at station XX to inform passengers.

[0172] According to the above-described embodiment 5, users of the railway can easily confirm the highly accurate time for resuming operations by, for example, looking at the time for resuming operations displayed on the display unit 9a of the device that displays WEB9.

[0173] Embodiment 6. Embodiment 6 describes a case in which the operation management support system 1 according to Embodiment 1 transmits a predicted timetable from the operation management system server 3S to the train 6a, WEB 9, and passenger information system 8.

[0174] Figure 26 shows the processing of the operation management system server in Embodiment 6. The diagram prediction unit 333 of the operation management processing unit 33 of the operation management system server 3S acquires information on the predicted time of restriction lifting received by the operation management data acquisition unit 331 from the railway disaster prevention information system server 2S. The diagram prediction unit 333 creates a predicted diagram 322 using the information on the predicted time of restriction lifting. The predicted diagram 322 created by the diagram prediction unit 333 is a predicted diagram 322 with high prediction accuracy because it is created using information on the predicted time of restriction lifting with high prediction accuracy.

[0175] The predicted timetable 322 created by the operation management system server 3S is normally transmitted to train 6a and used for the operation of train 6a. In embodiment 6, the timetable prediction unit 333 also transmits the created predicted timetable 322 to WEB9 and the passenger information system 8 in addition to train 6a.

[0176] If the passenger information system 8 presents departure and arrival times to the user based on a forecast timetable 322 created using information on the predicted time when restrictions will be lifted, which is based solely on weather forecast information, the message might be something like, "Train service will resume around 8:00."

[0177] Railway users can easily check the departure and arrival times of train 6a at each station with high prediction accuracy by checking the predicted timetable 322 announced by the passenger information system 8 via the notification unit 8b. When the passenger information system 8 presents train departure and arrival times to the user based on the predicted timetable 322 created using information on the predicted time when restrictions will be lifted with high prediction accuracy, it can present the user with more detailed train departure and arrival times, such as "The train is scheduled to arrive at XX station at 8:45." This allows the user to obtain more detailed information, such as what time train 6a will arrive at the station where they are currently located. It is possible that train 6a may be crowded and unavailable immediately after its resumption of service, but by having the passenger information system 8 announce a more accurate predicted timetable 322 to the user, the user can also check the arrival time of train 6a after 8:45.

[0178] Furthermore, railway users can easily check the predicted departure and arrival times for each train 6a at each station with high prediction accuracy by looking at the predicted timetable 322 displayed on the display unit 9a of a device that displays WEB9, for example, similar to when the passenger information system 8 notifies the predicted timetable 322.

[0179] Next, the processing of the operation management processing unit 33 of the operation management system server 3S in Embodiment 6 will be described. Figure 27 is a flowchart showing an example of the processing procedure of the operation management processing unit of the operation management system server in Embodiment 6.

[0180] In step S710, the diagram prediction unit 333 of the operation management processing unit 33 reads the information on the "predicted start time of restrictions" and the "predicted end time of restrictions" created by the restriction information creation unit 233 of the disaster prevention information processing unit 23 of the railway disaster prevention information system server 2S. The operation management data acquisition unit 331 of the operation management processing unit 33 receives the information on the "predicted start time of restrictions" and the "predicted end time of restrictions" created by the restriction information creation unit 233 of the disaster prevention information processing unit 23 from the railway disaster prevention information system server 2S and stores it in the operation management storage unit 32. The diagram prediction unit 333 reads the information on the "predicted start time of restrictions" and the "predicted end time of restrictions" from the operation management storage unit 32. After that, the process proceeds to step S720.

[0181] In step S720, the diagram prediction unit 333 obtains "platform congestion level" information from the station system 5 via the operation management data acquisition unit 331. Then, the process proceeds to step S730.

[0182] In step S730, the diagram prediction unit 333 acquires "train congestion level" information from the train system 6 via the operation management data acquisition unit 331. Then, the process proceeds to step S740.

[0183] In step S740, the timetable prediction unit 333 creates a predicted timetable 322. The timetable prediction unit 333 retrieves the operation timetable 321 stored in the operation management memory unit 32, and uses the operation timetable 321, the "platform congestion level" information, and the "train congestion level" information to create the predicted timetable 322. If train 6a and the platform are crowded, it will take time for passengers to board and alight from train 6a. Therefore, the timetable prediction unit 333 adjusts the time in the operation timetable 321 according to the platform congestion level and the train congestion level to create the predicted timetable 322. After that, the process proceeds to step S750.

[0184] In step S750, the diagram prediction unit 333 transmits the predicted diagram 322 not only to train 6a but also to WEB9 and the passenger information system 8. The predicted diagram 322 may be transmitted to at least one of WEB9 and the passenger information system 8.

[0185] According to the embodiment 6 described above, railway users can easily check the departure and arrival times of trains 6a at each station with high prediction accuracy by checking the predicted timetable 322 announced by the passenger information system 8, or by looking at the predicted timetable 322 displayed on the display unit 9a of the device that displays the WEB 9.

[0186] Embodiment 7. Embodiment 7 describes a case in which, in the operation management support system 1 according to Embodiment 1, the restriction information creation unit 233 of the disaster prevention information processing unit 23 of the railway disaster prevention information system server 2S creates information on operation restrictions for the following day or later.

[0187] Figure 28 shows an example of the usage environment in which the operation management support system is used in Embodiment 7. Figure 29 shows an example of the flow of information related to the railway disaster prevention information system in Embodiment 7. Figure 30 shows the processing of the railway disaster prevention information system server in Embodiment 7.

[0188] In Embodiment 7, the disaster prevention information data acquisition unit 231 performs the same processing as in Embodiments 1 to 4 described above.

[0189] In Embodiment 7, the regulation information creation unit 233 receives various information, including weather information (including weather forecast information), observed values ​​from the measuring instrument 7, inspection history along the line, personnel plan for inspections, and distance to the station, in the same manner as in Embodiments 1 to 4 described above. The regulation information creation unit 233 creates operation regulation information in the same manner as in Embodiments 1 to 4 described above. That is, in Embodiment 7, the regulation information creation unit 233 predicts the predicted time for lifting restrictions on the following day and onward, in the same manner as in Embodiments 1 to 4 described above, and creates information on the predicted time for lifting restrictions on the following day and onward. The predicted time for lifting restrictions on the following day and onward is information on the restriction time on the following day and onward.

[0190] Furthermore, in Embodiment 7, the regulation information creation unit 233 creates operational restriction information for the following day and beyond based on various information such as weather forecast information, observed values ​​from measuring instrument 7, inspection history along the line, personnel plan for inspections, distance to the station, and predicted time for lifting restrictions on the following day and beyond. The created operational restriction information for the following day and beyond is then transmitted to the diagram prediction unit 333 and WEB9 of the operation management processing unit 33 of the operation management system server 3S. In other words, the operational restriction information for the following day and beyond, created using the predicted time for lifting restrictions on the following day and beyond with high prediction accuracy, is transmitted from the regulation information creation unit 233 to the operation management system server 3S and WEB9 via the regulation information notification unit 234.

[0191] Information on train service restrictions for the following day and beyond, created using information on predicted times for lifting restrictions for the next day and beyond with high prediction accuracy, is more accurate. In Figure 29, for ease of understanding, connecting lines are shown from the restriction information creation unit 233 to the diagram prediction unit 333 and WEB9.

[0192] Next, the processing of the regulatory information creation unit 233 of the disaster prevention information processing unit 23 of the railway disaster prevention information system server 2S in Embodiment 7 will be described. Figure 31 is a flowchart showing an example of the processing procedure of the regulatory information creation unit of the disaster prevention information processing unit of the railway disaster prevention information system server in Embodiment 7.

[0193] In step S810, the regulatory information creation unit 233 reads weather forecast information for the following day and beyond from the external weather information DB 223. Then, it proceeds to step S820.

[0194] In step S820, the regulatory information creation unit 233 determines whether the weather forecast information read for the following day or later is such that it will result in the suspension of operations or operational restrictions such as speed limits.

[0195] If the weather forecast information for the day following the day after

[0196] In step S830, the regulation information creation unit 233 sets the regulation zone, which is the section where train operations will be restricted, and the predicted start time of the restriction, based on the weather forecast information for the following day and beyond that has been read, as train operations restrictions for the following day and beyond. The regulation zone is the section along the line that is determined to be a restricted section where train operations will be restricted, based on the weather forecast information for the following day and beyond that has been read. The process then proceeds to step S840.

[0197] In step S840, the regulatory information creation unit 233 determines the predicted time for lifting the restrictions on the following day or later, in the same manner as in the embodiments 1 to 4 described above. Then, the process proceeds to step S850.

[0198] In step S850, the regulation information creation unit 233 transmits information about the section where the traffic restriction will occur, information about the predicted start time of the restriction, and information about the predicted end time of the restriction to the traffic management system 3 as traffic restriction information for the following day or later.

[0199] In the above-described embodiment 7, improved operational restriction information for the following day and beyond can be created using information including the predicted time for lifting restrictions for the following day and beyond, which is operational restriction information created in the same manner as in embodiments 1 to 4 described above and with improved prediction accuracy. By transmitting this improved operational restriction information for the following day and beyond to the operational management system server 3S, the improved operational restriction information for the following day and beyond is useful for creating the predicted timetable 322 in the operational management system server 3S. Furthermore, by transmitting this improved operational restriction information for the following day and beyond to WEB9, railway users can check the detailed train 6a schedule for the following day and beyond by viewing the improved operational restriction information for the following day and beyond displayed on, for example, the display unit 9a of a device that displays WEB9.

[0200] This will allow railway users to understand the operating status of train 6a on the section they wish to use, and to know what restrictions will actually be in place on that section, making it easier to plan their schedules. This will improve convenience for railway users.

[0201] Embodiment 8. Embodiment 8 describes a case in which, in the operation management support system 1 according to Embodiment 1, the timetable prediction unit 333 of the operation management processing unit 33 of the operation management system server 3S transmits the predicted timetable 322 for the following day and beyond to the train 6a and the passenger information system 8. Figure 32 is a diagram showing the processing of the operation management system server in Embodiment 8.

[0202] In Embodiment 8, the train schedule prediction unit 333 receives the train schedule information for the following day and beyond, created in Embodiment 7, from the train schedule information creation unit 233 via the train schedule data acquisition unit 331. The train schedule prediction unit 333 uses the train schedule information for the following day and beyond to create a predicted train schedule 322 for the following day and beyond. The train schedule prediction unit 333 transmits the information of the created predicted train schedule 322 for the following day and beyond to train 6a and the passenger information system 8. A predicted train schedule 322 for the following day and beyond, created using highly accurate train schedule information for the following day and beyond, is a highly accurate predicted train schedule. In other words, the train schedule prediction unit 333 transmits a predicted train schedule 322 for the following day and beyond with high prediction accuracy to train 6a and the passenger information system 8.

[0203] In the above-described embodiment 8, a highly accurate predicted timetable 322 for the following day and beyond, created using highly accurate operational restriction information for the following day and beyond, is transmitted to the passenger information system 8. This allows the passenger information system 8 to notify and provide highly accurate operational status information for the following day and beyond to users of the railway. As a result, users of the railway can more easily plan their schedules for the following day by being able to understand the operational status of trains for the following day and beyond, leading to improved convenience.

[0204] Next, the hardware configurations of the control units 200 according to Embodiments 1 to 8 will be described. The control units 200 according to Embodiments 1 to 8 correspond to the disaster prevention information processing unit 23 and disaster prevention information control unit 24 of the railway disaster prevention information system server 2S, and to the disaster prevention information processing unit 23 and operation management control unit 34 of the operation management system server 3S, respectively. The functions of the control units 200 according to Embodiments 1 to 8 are realized by processing circuits. The processing circuits may be dedicated hardware or processing units that execute programs stored in a storage device.

[0205] When the processing circuit is dedicated hardware, the processing circuit may be a single circuit, a complex circuit, a programmed processor, a parallel programmed processor, an application-specific integrated circuit, a field-programmable gate array, or a combination thereof. Figure 33 shows a configuration in which each function of the control unit according to Embodiments 1 to 8 is realized in hardware. The processing circuit 201 incorporates a logic circuit 201a that realizes the function of the control unit 200.

[0206] If the processing circuit 201 is a processing unit, the functions of the control unit 200 are realized by software, firmware, or a combination of software and firmware.

[0207] Figure 34 shows a configuration in which the functions of each control unit according to Embodiments 1 to 8 are implemented by software. The processing circuit 201 includes a processor 211 that executes program 201b, a random access memory 212 used by the processor 211 as a work area, and a storage device 213 that stores program 201b. The functions of the control unit 200 are realized when the processor 211 loads program 201b stored in the storage device 213 onto the random access memory 212 and executes it. The software or firmware is written in a programming language and stored in the storage device 213. The processor 211 can be a central processing unit, but is not limited to that. The storage device 213 can be a semiconductor memory such as RAM (Random Access Memory), ROM (Read Only Memory), flash memory, EPROM (Erasable Programmable Read Only Memory), or EEPROM (Electrically Erasable Programmable Read Only Memory). The semiconductor memory may be non-volatile memory or volatile memory. Furthermore, the storage device 213 can be a magnetic disk, flexible disk, optical disk, compact disk, minidisc, or DVD (Digital Versatile Disc) in addition to semiconductor memory. The processor 211 may output data such as calculation results to the storage device 213 for storage, or it may store such data in an auxiliary storage device (not shown) via the random access memory 212. By integrating the processor 211, random access memory 212, and storage device 213 onto a single chip, the functions of the control unit 200 can be realized by a microcomputer.

[0208] The processing circuit 201 realizes the functions of the control unit 200 by reading and executing the program 201b stored in the memory device 213. The program 201b can also be described as instructing the computer to execute the procedures and methods for realizing the functions of the control unit 200.

[0209] Furthermore, the processing circuit 201 may implement some of the functions of the control unit 200 using dedicated hardware, and some of the functions of the control unit 200 using software or firmware.

[0210] Thus, the processing circuit 201 can realize each of the above-mentioned functions through hardware, software, firmware, or a combination thereof.

[0211] Furthermore, program 201b includes a train operation support program. According to the train operation support program, a train operation support program is implemented that causes a computer to perform the following steps: determine the section of track where train operations will be restricted based on weather forecast information, and predict the restriction time in the restricted section based on weather forecast information and information on the inspection history of facilities along the railway line.

[0212] The configurations shown in the above embodiments are examples only, and it is possible to combine them with other known technologies, combine different embodiments, and omit or modify parts of the configuration without departing from the gist of the invention.

[0213] The various aspects of this disclosure are summarized below as an appendix.

[0214] (Note 1) A restricted area determination unit that determines the restricted area where train operations will be restricted based on weather forecast information, A regulation information creation unit that predicts the time of regulation for the restricted section of the railway line based on the aforementioned weather forecast information and the inspection history information of the facilities along the line, A vehicle operation management support system characterized by having the following features. (Note 2) The aforementioned regulatory information creation unit, Based on the aforementioned weather forecast information, the predicted time for lifting the standard restrictions is calculated. The predicted time for lifting the standard restriction is corrected based on the inspection completion time included in the inspection history information, and the restriction time is predicted. The operation management support system described in Appendix 1, characterized by the above. (Note 3) The regulatory information creation unit corrects the predicted standard restriction lifting time based on the number of inspectors who will be inspecting the facilities along the railway line, and predicts the restriction time. The operation management support system described in Appendix 2, characterized by the above. (Note 4) The aforementioned regulatory information creation unit, Based on the aforementioned weather forecast information, the predicted time for lifting the standard restrictions is calculated. To predict the time of restriction by correcting the predicted time of lifting the standard restriction based on the observed values ​​of measuring instruments that measure the environment along the railway line of the aforementioned train, A traffic management support system characterized by any one of the features described in Appendix 1 to 3. (Note 5) The aforementioned regulatory information creation unit, if the railway tracks are installed over a river located in the aforementioned restricted section of the railway, The predicted time for lifting the regulation is to be predicted by correcting the predicted time for lifting the regulation based on the time it takes for the water level to fall below a predetermined regulatory standard value, including the predicted water level of the river. The operation management support system described in Appendix 4, characterized by the above. (Note 6) The aforementioned regulatory information creation unit, Based on the aforementioned weather forecast information, the predicted time for lifting the standard restrictions is calculated. In the aforementioned restricted train section, the inspection completion time is predicted based on a machine learning device that has learned related information including data from measuring instruments that measure the environment along the train line, data from the personnel plan for inspections, and data from the inspection completion time. Based on the predicted inspection completion time, the standard restriction lifting prediction time is corrected to predict the restriction time. A traffic management support system characterized by any one of the features described in Appendix 1 to 5. (Note 7) The regulatory information creation unit transmits the regulatory time information to the World Wide Web. A traffic management support system characterized by any one of the features described in Appendix 1 to 6. (Note 8) The system includes a predictive timetable creation unit that creates a predictive timetable showing a predicted train operation plan after the lifting of the aforementioned operational restrictions, based on the information regarding the aforementioned restricted time. A traffic management support system characterized by any one of the features described in Appendix 1 to 7. (Note 9) The predictive timetable creation unit transmits the predictive timetable to at least one of the World Wide Web and the passenger information system that provides passengers with information regarding the operation of the trains. The operation management support system described in Appendix 8, characterized by the above. (Note 10) The aforementioned regulatory information creation unit creates traffic regulations for the following day and onward based on the information regarding the aforementioned regulatory times for the following day and onward. A traffic management support system characterized by any one of the appendices 1 to 9. (Note 11) The aforementioned regulatory information creation unit transmits information on the train operation restrictions for the following day and beyond to at least one of the World Wide Web and the passenger information system that provides passengers with information on the operation of the trains. The operation management support system described in Appendix 10, characterized by the above. (Note 12) The system includes a predictive timetable creation unit that creates a predictive timetable for the following day and beyond, showing a predicted train operation plan after the lifting of the aforementioned operational restrictions, based on information regarding the aforementioned restricted times for the following day and beyond. A traffic management support system characterized by any one of the appendices 1 to 11. (Note 13) The aforementioned predictive timetable creation unit transmits the predictive timetable for the following day and beyond to the World Wide Web and the passenger information system that provides passengers with information regarding the operation of the trains. The operation management support system described in Appendix 8, characterized by the above. (Note 14) A step of determining the section of the train service that will be restricted based on weather forecast information, The steps include predicting the time of restriction in the restricted section of the railway line based on the weather forecast information and the inspection history information of the facilities along the line, A method for supporting operation management, characterized by including the following: (Note 15) A step of determining the section of the train service that will be restricted based on weather forecast information, The steps include predicting the time of restriction in the restricted section of the railway line based on the weather forecast information and the inspection history information of the facilities along the line, A traffic management support program characterized by having a computer execute the following. [Explanation of symbols]

[0215] 1 Operation Management Support System, 2 Railway Disaster Prevention Information System, 2S Railway Disaster Prevention Information System Server, 3 Operation Management System, 3S Operation Management System Server, 4 Weather Forecast System, 5 Station System, 6 Train System, 6a Train, 7,7a Measuring Instruments, 8 Passenger Information System, 8a Information Acquisition Unit, 8b Notification Unit, 9 WEB, 9a Display Unit, 11 Track, 12 River, 13 Station, 14 Notification Transmission Server, 21 Disaster Prevention Information Communication Unit, 22 Disaster Prevention Information Storage Unit, 23 Disaster Prevention Information Processing Unit, 24 Disaster Prevention Information Control Unit, 31 Operation Management Communication Unit, 32 Operation Management Storage Unit, 33 Operation Management Processing Unit, 34 Operation Management Control Unit, 41 Weather Forecast Information Communication Unit, 51 Platform Congestion Calculation Unit, 61 Train Congestion Calculation Unit, 200 Control Unit, 201 Processing Circuit, 201a Logic Circuit, 201b Program, 211 Processor, 212 Random access memory, 213 Storage device, 221 Inspection history database, 222 Observation value database, 223 External weather information database, 224 Personnel planning database, 225 Station distance database, 231 Disaster prevention information data acquisition unit, 232 Restricted section determination unit, 233 Restriction information creation unit, 233a Machine learning device, 234 Restriction information notification unit, 321 Operation schedule, 322 Prediction schedule, 331 Operation management data acquisition unit, 332 Schedule creation unit, 333 Schedule prediction unit, 1101, 1102, 1103 Train.

Claims

1. A restricted area determination unit that determines the restricted area where train operations will be restricted based on weather forecast information, A regulation information creation unit that predicts the time of regulation for the restricted section of the railway line based on the aforementioned weather forecast information and the inspection history information of the facilities along the line, A vehicle operation management support system characterized by having the following features.

2. The aforementioned regulatory information creation unit, Based on the aforementioned weather forecast information, the predicted time for lifting the standard restrictions is calculated. The predicted time for lifting the standard restriction is corrected based on the inspection completion time included in the inspection history information, and the restriction time is predicted. The operation management support system according to claim 1, characterized by the following:

3. The regulatory information creation unit predicts the regulatory time by correcting the standard regulatory lifting prediction time based on the number of inspectors who will be inspecting the facilities along the railway line. The operation management support system according to claim 2, characterized by the following:

4. The aforementioned regulatory information creation unit, Based on the aforementioned weather forecast information, the predicted time for lifting the standard restrictions is calculated. To predict the time of restriction by correcting the predicted time of lifting the standard restriction based on the observed values ​​of measuring instruments that measure the environment along the railway line of the aforementioned train, The operation management support system according to claim 1, characterized by the following:

5. The aforementioned regulatory information creation unit, if the railway tracks are installed over a river located in the aforementioned restricted section of the railway, The predicted time for lifting the regulation is to be predicted by correcting the predicted time for lifting the regulation based on the time it takes for the water level to fall below a predetermined regulatory standard value, including the predicted water level of the river. The operation management support system according to claim 4, characterized by the above.

6. The aforementioned regulatory information creation unit, Based on the aforementioned weather forecast information, the predicted time for lifting the standard restrictions is calculated. In the aforementioned restricted train section, the inspection completion time is predicted based on a machine learning device that has learned related information including data from measuring instruments that measure the environment along the train line, data from the personnel plan for inspections, and data from the inspection completion time. Based on the predicted inspection completion time, the standard restriction lifting prediction time is corrected to predict the restriction time. The operation management support system according to claim 1, characterized by the following:

7. The regulatory information creation unit transmits the regulatory time information to the World Wide Web. A traffic management support system according to claim 1 or 2, characterized by the above.

8. The system includes a predictive timetable creation unit that creates a predictive timetable showing a predicted train operation plan after the lifting of the aforementioned operational restrictions, based on the information regarding the aforementioned restricted time. The operation management support system according to claim 1, characterized by the following:

9. The predictive timetable creation unit transmits the predictive timetable to at least one of the World Wide Web and the passenger information system that provides passengers with information regarding the operation of the trains. The operation management support system according to claim 8, characterized by the following:

10. The aforementioned regulatory information creation unit creates traffic regulations for the following day and onward based on the information regarding the aforementioned regulatory times for the following day and onward. A traffic management support system according to claim 1 or 2, characterized by the above.

11. The aforementioned regulatory information creation unit transmits information on the train operation restrictions for the following day and beyond to at least one of the World Wide Web and the passenger information system that provides passengers with information on the operation of the trains. The operation management support system according to claim 10, characterized by the above.

12. The system includes a predictive timetable creation unit that creates a predictive timetable for the following day and beyond, showing a predicted train operation plan after the lifting of the aforementioned operational restrictions, based on information regarding the aforementioned restricted times for the following day and beyond. A traffic management support system according to claim 1 or 2, characterized by the above.

13. The aforementioned predictive timetable creation unit transmits the predictive timetable for the following day and beyond to the World Wide Web and the passenger information system that provides passengers with information regarding the operation of the trains. The operation management support system according to claim 8, characterized by the following:

14. A step of determining the section of the train service that will be restricted based on weather forecast information, The steps include predicting the time of restriction in the restricted section of the railway line based on the weather forecast information and the inspection history information of the facilities along the line, A method for supporting operation management, characterized by including the following:

15. A step of determining the section of the train service that will be restricted based on weather forecast information, The steps include predicting the time of restriction in the restricted section of the railway line based on the weather forecast information and the inspection history information of the facilities along the line, A traffic management support program characterized by having a computer execute the following.

Images