WO2023286425A1 - 運行計画変更支援装置、運行計画変更支援方法、及び列車運行管理システム - Google Patents
運行計画変更支援装置、運行計画変更支援方法、及び列車運行管理システム Download PDFInfo
- Publication number
- WO2023286425A1 WO2023286425A1 PCT/JP2022/019380 JP2022019380W WO2023286425A1 WO 2023286425 A1 WO2023286425 A1 WO 2023286425A1 JP 2022019380 W JP2022019380 W JP 2022019380W WO 2023286425 A1 WO2023286425 A1 WO 2023286425A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- change
- operation plan
- information
- changes
- executed
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 55
- 230000008859 change Effects 0.000 claims abstract description 572
- 230000008569 process Effects 0.000 claims description 49
- 238000011156 evaluation Methods 0.000 claims description 32
- 238000012545 processing Methods 0.000 claims description 26
- 230000000694 effects Effects 0.000 claims description 6
- 230000010365 information processing Effects 0.000 claims description 2
- 238000012549 training Methods 0.000 description 35
- 238000010586 diagram Methods 0.000 description 18
- 238000004891 communication Methods 0.000 description 5
- 230000007423 decrease Effects 0.000 description 5
- 239000010432 diamond Substances 0.000 description 4
- 230000001934 delay Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 229910003460 diamond Inorganic materials 0.000 description 2
- 238000005401 electroluminescence Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000003607 modifier Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
- B61L27/10—Operations, e.g. scheduling or time tables
- B61L27/12—Preparing schedules
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
- B61L27/10—Operations, e.g. scheduling or time tables
- B61L27/14—Following schedules
Definitions
- the present invention relates to an operation plan change support device, an operation plan change support method, and a train operation management system.
- Patent Document 1 there is an operation management system that supports vehicle operation management performed by an operation dispatcher, and a train operation plan is changed.
- a traffic rescheduling necessity judgment model is created based on the train operation prediction unit and past performance diagrams, which are the results of past train operations.
- a traffic rescheduling support processing unit including a traffic rescheduling plan determining unit that creates a traffic rescheduling necessity determination result indicating whether traffic rescheduling is necessary by applying it to a certain day actual timetable and forecast timetable.
- Patent Document 1 the judgment model judges the necessity of traffic rescheduling from the amount of delay, and the combination of multiple types of plan changes, the order of plan changes to be implemented in stages, the midway The presence or absence of possible inconsistencies is not used for judgment. Therefore, with the technology disclosed in Patent Literature 1, it is difficult to create an operation plan change proposal that is widely accepted by operators in response to operation disruptions. In particular, in a situation where the operation schedule is becoming more complicated, it is necessary to implement changes in the operation plan in stages so as not to increase the operation disturbance, and such operation still depends on the knowledge and experience of operators such as dispatchers. The current situation is that the portion is large.
- the present invention has been made in view of such a situation, and its purpose is to provide an operation plan change support device, an operation plan change support method, and an operation plan change support device capable of supporting the creation of an operation plan change proposal to be executed in stages. and to provide a train operation management system.
- One of the present inventions for solving the above-mentioned problems has a processor and a memory, and receives information on train operation contents before a certain point in time and information on changes in the operation plan executed before the point in time, a judgment model generation unit for generating an operation plan change judgment model for outputting information on changes in the operation plan to be executed next to the executed operation plan; Inputting information on the change of the operation plan executed before the specified time into the operation plan change judgment model, and creating information on the content of change of the operation plan based on the information output from the operation plan change judgment model. By repeating this process one or more times, change candidates that are candidates for changes in the operation plan to be executed step by step after the specified time are created, and change candidates that satisfy predetermined conditions are selected from the created change candidates. and an operation plan change proposal creation unit that identifies and creates the identified change candidate as an operation plan change proposal.
- an information processing device receives information on train operation details before a certain point in time and information on changes in the operation plan executed before the point in time, Judgment model generation processing for generating an operation plan change judgment model for outputting information on changes in the operation plan to be executed next to the executed operation plan; Inputting information on the change of the operation plan executed before the specified time into the operation plan change judgment model, and creating information on the content of change of the operation plan based on the information output from the operation plan change judgment model. By repeating this process one or more times, change candidates that are candidates for changes in the operation plan to be executed step by step after the specified time are created, and change candidates that satisfy predetermined conditions are selected from the created change candidates.
- An operation plan change proposal creation process for identifying and creating the identified change candidate as an operation plan change proposal; and an operation plan change support method for executing the operation plan change proposal.
- one of the present inventions for solving the above problems is a processor and a memory, and information on train operation contents before a certain point in time and information on changes in the operation plan executed before the point in time are inputted.
- a determination model generation unit that generates an operation plan change determination model that outputs information on changes in the operation plan to be executed next to the executed operation plan; and inputting information on the change of the operation plan executed before the specified time to the operation plan change judgment model, and based on the information output from the operation plan change judgment model, information on the content of the change of the operation plan
- change candidates that are candidates for changing the operation plan to be executed step by step after the specified time are created, and changes satisfying predetermined conditions are created from each of the created change candidates.
- an operation plan change proposal creation unit that identifies candidates and prepares the identified change candidates as an operation plan change proposal; and an operation plan change support device that includes: and a route control device to control the train operation management system.
- FIG. 1 is a diagram showing an example of the configuration of a train operation management system according to this embodiment.
- FIG. 2 is a diagram showing an example of the configuration of the operation plan change support device.
- FIG. 3 is a diagram showing an example of a change input history DB.
- FIG. 4 is a diagram explaining an example of a plan change rule.
- FIG. 5 is a flowchart for explaining an outline of train operation management processing performed by the train operation management system.
- FIG. 6 is a flowchart illustrating an example of training data creation processing.
- FIG. 7 is a diagram for explaining the details of the new label generation unit.
- FIG. 8 is a flowchart for explaining the details of the operation plan change proposal creation process.
- FIG. 9 is a diagram showing an example of a change proposal screen.
- FIG. 10 is a flowchart for explaining the details of the change application determination process.
- FIG. 11 is a flowchart for explaining the details of the change execution determination process.
- FIG. 1 is a diagram showing an example of the configuration of a train operation management system 10 according to this embodiment.
- the train operation management system 10 includes an operation plan management device 40 that manages information used for managing train operation, such as operation plans (train diagrams, etc.) and operation results of each train 6, and a running of each train 6. , a route control device 60 for controlling the route of each train 6, and an operation plan change support device 100 for supporting change of the operation plan of each train 6. Configured.
- the operation plan management device 40 stores information about the day on which operation management is being performed and information about the previous day and before, regarding information used for managing train operation, such as operation plans, operation results, and operation plan change history. are managed respectively. After a day's worth of train operations are completed, the operation plan management device 40 saves each piece of information including the original operation plan for the day, the operation results for the whole day, and the plan change history for the whole day as past history data in the past history database. In addition, various information is initialized for the operation management of the next day. Specifically, for example, the operation plan management device 40 updates the operation plan to that of the next day, empties the operation record, and empties the plan change history.
- the operation plan management device 40 When the operation plan management device 40 receives an operation plan change proposal from the operation plan change support device 100, the operation plan management device 40 changes the operation plan based on the received operation plan change proposal, and further combines the received operation plan change information with the current time. and store it as a plan change history.
- the train tracking device 50 acquires information on the train status of vehicles from various facilities 5, and based on the acquired information on the status of trains and the operation plan, creates the operation record (running history) of each train 6. The train tracking device 50 transmits the created operation results to the operation plan change support device 100 .
- the route control device 60 automatically controls the running (route) of each train 6 by transmitting instruction information to the train 6 or equipment 4 such as a signal and a switch based on the operation plan of each train 6.
- the operation plan change support device 100 changes the operation plan step by step for the purpose of recovering the train operation corresponding to the trouble when the train operation is hindered by an event such as an accident or natural disaster. is generated based on an operation plan change judgment model described later. A detailed configuration of the operation plan change support device 100 will be described later (FIG. 2).
- a communication line data bus
- a dedicated line a communication line (data bus), a dedicated line, a LAN (Local Area Network), a WAN (Wide Area Network) Network), or a wired or wireless communication network 3 such as the Internet.
- FIG. 2 is a diagram showing an example of the configuration of the operation plan change support device 100.
- the operation plan change support device 100 includes an arithmetic processing unit 11 such as a CPU (Central Processing Unit), a DSP (Digital Signal Processor), a GPU (Graphics Processing Unit), or an FPGA (Field-Programmable Gate Array), and a ROM (Read Only Memory 12 such as RAM (Random Access Memory), storage device 13 such as HDD (Hard Disk Drive) or SSD (Solid State Drive), input device 14 composed of a mouse, keyboard, etc., liquid crystal A display device 15 composed of a display or an organic EL (Electro-Luminescence) display, etc., and a communication device composed of a NIC (Network Interface Card), a wireless communication module, a USB (Universal Serial Interface) module, a serial communication module, or the like. 16.
- NIC Network Interface Card
- the operation plan change support device 100 includes a prediction diagram creation unit 101, a teacher data generation unit 102, an allowable inconsistency storage unit 1025, a judgment model generation unit 103, an operation plan change proposal creation unit 104, a change application judgment unit 105, and Each functional unit (program) of the plan change rule update unit 107 is provided.
- the predictive timetable creation unit 101 uses as input values the operation record of each train (if there is a problem with the operation of the train, information about the problem) and the current operation plan (planned timetable). Predict the operation plan (prediction timetable) of The predictive timetable creation unit 101 is, for example, a simulator that performs a macro-type simulation, and calculates the times of arrival or departure of each train from each station as decision variables. As train operation simulators that perform macro-type simulations, for example, those based on the concept of PERT (Program Evaluation and Review Technique) are known. Note that the predictive timetable creation unit 101 also determines the arrival and departure times of each train at each station based on the actual operation results for the portion before the current time, and outputs the results by including them in the simulation results.
- PERT Program Evaluation and Review Technique
- the predicted timetable creation unit 101 outputs the predicted timetable and information on the inconsistency if there is an inconsistency (course competition) in the operation of trains in the predicted timetable.
- Inconsistency refers to a situation in which trains cannot run due to conflicts between train routes. It is a contradiction of order.
- the training data generation unit 102 converts information (i.e., information on the order of changes in the operation plan) about the stepwise changes in the operation plan that were examined (inputted) and executed by operators such as dispatchers in the past to the operation plan change determination model. Generate as training data.
- the training data generation unit 102 regarding a trouble that occurred in the past, determines the operation details of the train before the trouble occurred, the change in the operation plan executed before the trouble occurred, and the executed operation plan Information relating to the changes in the operation plan executed in the next step (specifically, the contents of the changes and whether or not the changes were actually executed after consideration) are generated in association with each other.
- the operation plan change determination model is a trained model configured as a neural network consisting of multiple input/output layers, but may be other types of trained models.
- the permissible inconsistency storage unit 1025 stores changes in operation plans that have been executed step by step in the past, and in which train inconsistencies have occurred due to the changes, but the inconsistencies have been resolved by changes in subsequent stages. information (hereinafter referred to as allowable inconsistency information).
- the judgment model generation unit 103 generates an operation plan change judgment model based on the training data generated by the training data generation unit 102 . That is, the operation plan change judgment model is input with information on the details of train operation before a certain time and information on changes to the operation plan executed before that time, and the operation plan to be executed next to the executed operation plan. Prints information about changes in The information on changes in the operation plan executed before the above time includes information on the type and number of changes in the operation plan executed before the above time.
- the change of the operation plan may be made by combining a plurality of change elements (for example, it consists of each change element such as change of departure/arrival time and change of track number for a certain train). .
- the operation plan change support device 100 sets changes in an operation plan made up of these multiple change elements as changes in the same operation plan (hereinafter referred to as a change group).
- the operation plan change proposal creation unit 104 creates an operation schedule (prediction schedule) or an operation plan change judgment model based on the new obstacle, regarding the obstacle specified by the user or the delay that naturally occurs due to commuter rush hour (hereinafter referred to as a new obstacle).
- a new obstacle By sequentially inputting the operation schedule (prediction schedule) calculated from , into the operation plan change judgment model, information on the change of the operation plan is created at least once or more, and it is executed step by step after the time of the new trouble.
- Change candidates that are candidates for changing the operation plan are created, change candidates that satisfy a predetermined condition are specified from the created change candidates, and the specified change candidates are created as an operation plan change proposal.
- the operation plan change proposal creation unit 104 calculates the evaluation value of the operation plan (predicted timetable) when the change indicated by each change candidate is applied, and determines whether the calculated evaluation value is the optimum value. Then, when it is determined that the evaluation value is the optimum value, each of the change candidates is specified (as a change candidate that satisfies the predetermined condition). Predetermined conditions to be satisfied include cancellation of inconsistencies, constraints on operation (time required for train turnaround at station, conditions on departure order of trains, etc.), and plan change rules to be described later.
- the change application determination unit 105 creates a plurality of combinations (patterns) of the change elements in the change candidate, and determines the operation plan for each of the created combinations.
- a change in the evaluation value that can express the effect of the change is calculated, and based on the calculated change in the evaluation value, a combination of change elements to be identified as a change candidate is determined from among the plurality of combinations.
- the change application determination unit 105 determines whether or not the inconsistency due to the change indicated by the change candidate created by the operation plan change proposal creation unit 104 will be resolved at a later stage based on the allowable inconsistency information. If it is determined that the inconsistency will be resolved at a later stage, the created change candidate is identified (as a change candidate that satisfies the above predetermined condition).
- the plan change rule update unit 107 generates or updates a plan change rule, which is a rule determined in advance by an administrator or the like and applied when an operation plan is changed.
- the plan change rule is, for example, a rule for forcibly resolving the delay or inconsistency when there is a train delay or inconsistency in the operation schedule. Rules that can resolve delays or inconsistencies even when they are out of control.
- the operation plan change support device 100 includes a change input history DB 200, a plan change teacher data DB 215, a change judgment model DB 220, a plan change rule DB 230, an inconsistency history DB 240, an allowable inconsistency list DB 250, a train schedule DB 260, and a running record DB 270.
- each data of the operation plan change proposal DB 280 are stored. Note that these data are stored as a database here, but the storage format of the data is not particularly limited.
- the change input history DB 200 stores the history of step-by-step changes to the operation plan input by operators such as dispatchers in the past.
- FIG. 3 is a diagram showing an example of the change input history DB 200. As shown in FIG.
- the change input history DB 200 has data items of an obstacle 201 in which information about the obstacle is set and a plan change input 202 in which input information about the change of the operation plan regarding the obstacle 201 is set.
- the failure 201 includes a date 203 in which the date of occurrence of the failure is set, a failure occurrence time 204 that is the time when the failure occurred, a failure end time 205 that is the time when the failure ended, and a trouble ending time 205. It has each data item of the trouble station 206 which is the place (station etc.) which occurred.
- the plan change input 202 includes a train ID 207 in which the ID of the train whose operation plan is to be changed due to the trouble 201 (change target train) is set, and the station whose operation plan is to be changed (change target station).
- a related train 210 to which an ID is set, a train ID 207, a station ID 208, a change type 209, a change content 211 to which specific content of a change in the operation plan specified by the related train 210 is set, and a change content 211 are set.
- the change type 209 is set with, for example, information such as a change in train arrival/departure order at a station and a change in train departure/arrival number track.
- the change input history DB 200 has a plurality of records for failures on the same date. May exist. Note that the change input history DB 200 may be set automatically, or may be input by an operator such as a dispatcher.
- plan change training data DB 215 stores the training data generated by the training data generation unit 102.
- the change judgment model DB 220 stores the operation plan change judgment model generated by the judgment model generation unit 103 .
- the plan change rule DB 230 stores plan change rules.
- the plan change rule DB 230 associates and stores train operation details and corresponding change details when an operation plan is changed.
- FIG. 4 is a diagram explaining an example of a plan change rule. If a train arriving at a station is delayed and other trains arrive at that station late 231, the order of arrival and departure of both trains at that station is changed.
- the plan change rule stores information including various order information and delay information between trains before changing the order of arrival and departure, and various orders between trains (including related trains) after change.
- the inconsistency history DB 240 stores information on the history of the occurrence and resolution of inconsistencies in each of the past train operation details and the predicted train operation details (prediction timetable). do.
- the allowable inconsistency list DB 250 stores a history of inconsistencies (allowable inconsistency information) of inconsistencies in the inconsistency history DB 240 that have occurred but have since been resolved.
- the train schedule DB 260 stores information on past operation plans (past operation schedules) and predicted operation details (prediction timetables).
- the travel record DB 270 stores the past travel history (operation record) of each train.
- the operation plan change proposal DB 280 stores the operation plan change proposal created by the operation plan change proposal creation unit 104 .
- Each function of the operation plan change support device 100 described above is realized by the arithmetic processing device 11 reading and executing each program stored in the memory 12 or the storage device 13 . Further, the above program can be distributed by being recorded on a recording medium, for example. Next, processing performed by the train operation management system 10 will be described.
- FIG. 5 is a flowchart explaining an overview of train operation management processing performed by the train operation management system 10.
- the operation plan change support device 100 executes training data creation processing for creating training data for an operation plan change determination model in advance (s1).
- the operation plan change support device 100 may execute the training data creation process s1 at a predetermined timing (for example, at a predetermined time such as after the end of daily operation, at a predetermined time interval), and the change input history DB 200 may be executed when is updated.
- the operation plan change support device 100 After that, the operation plan change support device 100 generates an operation plan change judgment model based on the teaching data created in s1.
- the operation plan change support device 100 generates a new operation plan (operation plan change proposal) using the generated operation plan change determination model when troubles such as delays and vehicle failures occur in daily train operation.
- An operation plan change proposal creation process s3 to be created is executed (s3).
- the operation plan change support device 100 displays the operation plan change proposal created in s3 on the display device 15 and requests approval input from the operator or the like. When an approval input is obtained, the operation plan change support device 100 transmits the created operation plan change proposal to the operation plan control device 40 .
- the operation plan management device 40 changes the operation plan based on the received operation plan change proposal, and further stores the received operation plan change proposal and the current time as a set of plan change history.
- the route control device 60 controls the trains 6 and the equipment 5 by transmitting instruction information to each train 6 and the equipment 5 based on the operation plan changed by the operation plan management device 40 (s5).
- FIG. 6 is a flowchart for explaining an example of the training data creation processing s1.
- the training data generation unit 102 acquires information (hereinafter referred to as target failure information) about one failure (hereinafter referred to as target failure) that occurred in the past from the change input history DB 200, and information (hereinafter referred to as target failure information) and corresponding operation plan change information ( hereinafter referred to as plan change information) is extracted (s11).
- the training data generation unit 102 selects all records with the same trouble date 203 or trouble 201 from the change input history DB 200, and acquires the contents of the selected records.
- the training data generation unit 102 classifies changes in each operation plan in the plan change information extracted in s11 into a plurality of groups (change groups) and orders the change groups (s13).
- the training data generation unit 102 orders the changes in each operation plan according to the order of execution of changes in the operation plan (the chronological order in which the operation plan management device 40 instructs the route control device 60 to control). At this time, the training data generation unit 102 classifies changes in each operation plan into a plurality of groups for each train to be changed, station to be changed, and target type. Change plan (i.e. change group). In determining the change group, changes that do not depend on the control order of running of other trains can be made to belong to the same group, but each operation plan change may be made into one change group. It is also assumed that one or more operation plan changes belong to one change group.
- the training data generation unit 102 creates train operation details (predicted timetable) when the target failure occurs (s15).
- the training data generation unit 102 generates the target trouble information, the operation record up to the occurrence of the target trouble (running record DB 270), and the train schedule (train diagram DB 260) that is the operation plan after the occurrence of the target trouble.
- a predicted timetable is created by inputting to the predicted timetable creation unit 101 .
- the training data generation unit 102 selects a change group that has not been selected so far and has the highest order (higher order change group) from among the change groups classified in s13 (s17).
- the training data generation unit 102 creates a predicted timetable when the change group (selection group) selected in s17 is applied (s19, s21).
- the teacher data generating unit 102 inputs the current predicted timetable (predicted timetable created in s15 or updated in the previous time in s21) and changes in the operation plan indicated by the selected group to the predicted timetable creation unit 101. Update forecast diamonds.
- the training data generation unit 102 changes the operation plan, which is the feature quantity in the training data of the operation plan change judgment model, based on the information of the predicted timetable before application (the predicted timetable before executing s19 and s21). Information on the operation details and operation plan of each previous train is calculated (s23).
- This feature amount is a feature amount at each station of each train, and each change target station of each train (for example, a change target train or related trains arriving and departing before and after the change target train) before the change of the operation plan related to the selected group , and information on changes in each operation plan executed before changing the operation plan related to the selected group (for example, the type of change in the operation plan that executed the change, and the change in what stage each change is information, which is not set if the change is the first (first stage) change.
- each change target station of each train for example, a change target train or related trains arriving and departing before and after the change target train
- information on changes in each operation plan executed before changing the operation plan related to the selected group for example, the type of change in the operation plan that executed the change, and the change in what stage each change is information, which is not set if the change is the first (first stage) change.
- this feature amount is, for example, trouble information of a target trouble corresponding to the selected group acquired from the change input history DB 200, or an inconsistency before the operation plan change related to the selected group acquired from the inconsistency history DB 240. Contains alignment information.
- this feature amount includes, for example, the number of times the change target train related to the selected group has become a change target train in the past, which is calculated from the change input history DB 200. Also, this feature amount includes, for example, information on the number of times the same type of change in the operation plan as the change in the operation plan related to the selected group was made in the past, which is calculated from the change input history DB 200 .
- the training data generation unit 102 generates information on changes in the actually executed operation plan among the changes in the operation plan indicated by the selected group as information to be output labels in the training data of the operation plan change determination model ( s23).
- the training data generation unit 102 stores information on changes applicable to the operation plan related to the selected group and information on whether or not the change has actually been made, as the change content 211 and execution presence/absence 212 of the change input history DB 200 . obtained respectively from Changes that are applicable to the operation plan but do not exist in the change input history DB 200 are not actually changed, so the output label is "not".
- the training data generation unit 102 compares the predicted timetables before and after the update specified or calculated in s19 and s21, and if the inconsistency is resolved before and after the change of the operation plan related to the selected group,
- the content of the inconsistency resolution is stored in the allowable inconsistency list DB 250 as allowable inconsistency information (s25).
- the training data generation unit 102 acquires all inconsistent information from the information output when creating the predicted timetable before executing s19 and s21.
- the training data generation unit 102 acquires all mismatch information from the information output when the predicted timetable is created after executing s19 and s21. Then, the training data generation unit 102 compares the acquired mismatch information, and stores the mismatch information resolved by executing s19 and s21 in the allowable mismatch list DB 250 .
- FIG. 7 is a diagram illustrating an example of allowable inconsistency information.
- the departure and arrival track numbers of the two trains such as the track number order in which train A arrives after train B departs, the departure order in which train B departs after train A departs, and train A departs after arriving at station P. sequence conflict between arrival and departure events). If the departure and arrival platforms of these two trains become different 402 due to a change in the operation plan, the inconsistency 401 is resolved.
- the permissible inconsistency information stores such inconsistency 401 and inconsistency-resolved trains 403, a set of station arrival and departure events, and their order relationships, respectively.
- the training data generation unit 102 selects that change group, and performs the processes from s17 onwards. is repeated (s27).
- the teacher data generation unit 102 repeats the above processing for all troubles stored in the change input history DB 200.
- the teaching data creation processing s1 ends.
- the judgment model generation unit 103 updates the operation plan change judgment model by inputting the training data generated in the training data creation process s1 into the operation plan change judgment model and performing machine learning.
- FIG. 8 is a flowchart for explaining the details of the operation plan change proposal creation process s3.
- the operation plan change proposal creation process s3 is started automatically or by a user's designation, for example, when a new problem occurs in train operation.
- the operation plan change proposal creation unit 104 sets information about the newly occurring trouble (hereinafter referred to as "new trouble") (s31). For example, the operation plan change proposal creation unit 104 may receive input of information on new troubles from the user, or automatically generate information on new troubles based on information acquired from a predetermined monitoring system or the train tracking device 50. may be generated.
- the operation plan change proposal creation unit 104 creates prediction information (prediction timetable) of the train operation details after the occurrence of the new trouble (s33). Specifically, the operation plan change proposal creation unit 104 creates a prediction timetable based on the information on the new trouble set in s31, the operation results (running result DB 270) up to the occurrence of the new trouble, and the current operation timetable. By inputting in 101, a predicted timetable is created.
- the operation plan change proposal creation unit 104 uses the predicted timetable generated in s33 (or the predicted timetable calculated in s41 to be described later) to determine the feature amount of the operation plan change judgment model (feature amount similar to the feature amount calculated in s23). Calculate (s35). Specifically, the operation plan change proposal creation unit 104 extracts the feature quantity at each station of each train based on the data extracted from the predicted timetable.
- the operation plan change proposal creation unit 104 inputs the feature amount calculated in s35 to the operation plan change judgment model, thereby obtaining information related to the change of the operation plan output from the operation plan change judgment model (that is, applicable operation (s37).
- the change application determination unit 105 executes a change application determination process s39 for determining an operation plan that satisfies a predetermined condition and is actually changed among the changes (change candidates) of the operation plan output in s37. Details of the change application determination processing s39 will be described later.
- the operation plan change proposal creation unit 104 creates a next-stage forecast timetable based on the change (change group) of the operation plan determined in the change application determination process s39 (s41). For example, the operation plan change proposal creation unit 104 inputs the information of the operation plan to which the change in the operation plan determined by the change application determination process s39 is applied to the current forecast timetable, and the operation results to the forecast timetable creation unit 101. Create a forecast diagram.
- the operation plan change proposal creation unit 104 calculates the evaluation value of the predicted timetable created in s41 (s43). For example, the operation plan change proposal creation unit 104 calculates the total delay time by totaling the delay arrival and departure times of all trains at all stations in the predicted timetable.
- the operation plan change proposal creation unit 104 may calculate other types of evaluation values, such as the number of suspended trains of all trains, the transport volume of all trains, the impact on operations, and the original schedule from the time of a new failure. or a combination thereof. Fluctuations in the evaluation values before and after the change in the predicted timetable represent the effect of the change in the operation plan.
- the operation plan change proposal creation unit 104 determines whether the current evaluation value indicates the optimum value (whether it converges to the optimum value ), the change (change candidate) of each operation plan determined so far in the change application determination process s39 is identified (confirmed) as a change of the operation plan constituting the operation plan change proposal (s45). .
- the change (change candidate) of each operation plan determined in the change application determination process s39 is confirmed as the change of the operation plan constituting the operation plan change proposal.
- the proposed change in operation plan creating unit 104 executes the processing in s47. If the change in the operation plan determined in s39 is not identified as a change in the operation plan that constitutes the proposed change in operation plan (s45: No), the proposed change in operation plan creation unit 104 uses the diagram prediction result created in s41. A change candidate for a new operation plan based on the premise is created, that is, the processes after s35 are repeatedly executed.
- the operation plan change proposal creation unit 104 confirms whether or not train delays or inconsistencies remain in the predicted timetable as a result of changes in each operation plan determined in the processes up to this point. If a match remains, force further changes to the current trip plan to eliminate the delay or mismatch.
- the operation plan change proposal creation unit 104 refers to the plan change rule DB 230 to search for a change in the operation plan corresponding to the operation details extracted from the predicted timetable, and the searched operation plan change is applied to the prediction. Applies to diamonds.
- the operation plan change proposal creation unit 104 receives input from the user for further changes to the operation content (s49). Note that the operation plan change proposal creation unit 104 may store the input change in the plan change rule DB 230 as a new plan change rule.
- the operation plan change proposal creation unit 104 integrates the change details of the train operation plan determined in the processes up to this point and generates an operation plan change proposal.
- the operation plan change proposal creation unit 104 creates change groups for the generated operation plan change proposals in the same manner as in the process of s13 in the teaching data creation process, and displays each change group on a predetermined screen (change proposal screen) ( s51). The user corrects the operation plan change proposal as necessary while viewing the change proposal screen.
- the teacher data generation unit 102 acquires the forecasted timetable (operation plan) corrected as described above, and updates the teacher data based on the acquired forecasted timetable.
- the operation plan change proposal creation process s3 ends.
- FIG. 9 is a diagram showing an example of a change proposal screen 300. As shown in FIG.
- the change proposal screen 300 has an operation plan change display field 301 , a change execution designation field 302 , and a re-proposal field 303 .
- the operation plan change display column 301 a list of changes (change groups) of the operation plan at each stage constituting the operation plan change proposal generated by the operation plan change proposal creation processing s3 is displayed in accordance with the order of the change groups (that is, (according to the order of train or equipment control). Specifically, in the operation plan change display column 301, the content 311 of the change of each operation plan in the change group 310, the change target train 312 in the change of each operation plan, and the prediction after applying the change of each operation plan The number of discrepancies 313 that exist in the timetable and the increase or decrease in delay time 314 after applying each schedule change are displayed.
- the operation plan change display column 301 also includes an adoption availability selection column 315 that is selected by the user when each change group (or each change in the change group) is adopted to confirm the change of the operation plan.
- the user designates the change group to be discarded by deselecting the adoption/non-adoptability selection field 315. Note that when the user deselects the adoption/non-adoption selection column 315, the adoption/non-adoption selection column 315 of the (lower) change group (or changes within the change group) after the deselected change group is displayed. is automatically deselected.
- the re-suggestion field 303 is for the change selected in the adoption/non-adoption selection field 315 from among the change groups (or changes within the change group) displayed in the operation plan change display field 301. is determined, the user designates a case in which the process of the operation plan change proposal creation unit 104 is to be executed again without making changes that are not selected in the adoption possibility selection column 315 .
- FIG. 10 is a flowchart for explaining details of the change application determination processing s39.
- the change application determination unit 105 extracts change candidates determined to require change in s37 and satisfying the constraint conditions.
- the change application determination unit 105 selects the change candidate that has the highest order among the change candidates that have not been selected so far (the change candidate that is associated with the running station of the train that requires the fastest train control). change candidate) is selected (s71).
- the change application determination unit 105 selects the change candidate select one of the possible combinations (s73) (if there is only one change candidate, select one of them).
- the change application determination unit 105 executes the following processes of s75 to s79 for the selected combination.
- the change application determination unit 105 determines the evaluation value of the predicted timetable before applying the selected combination candidate (hereinafter referred to as the selected combination candidate) in s73 (hereinafter referred to as the pre-application timetable) and the prediction value after applying the selected combination candidate.
- An evaluation value of diamond (hereinafter referred to as diamond after application) is calculated (s75).
- the change application determination unit 105 calculates inconsistency information (number of inconsistencies) in the pre-application timetable and inconsistency information (inconsistency number) in the post-application timetable.
- the change application determination unit 105 selects the selected combination candidate based on the increase or decrease in the evaluation value due to the change in the operation plan related to the selected combination candidate and the increase or decrease in the number of inconsistencies related to the selected combination candidate calculated in S75.
- a change execution determination process s77 for determining whether or not to determine as a change candidate is executed. Details of the change execution determination process s77 will be described later.
- the change application determination unit 105 executes the above processing of s73 to s77 for all combinations of change candidates related to the running station of the train selected in s71 (s79).
- the change application determination unit 105 identifies the combination of change candidates with the highest evaluation value among the combinations of change candidates determined in s77 (s81).
- the change application determination unit 105 selects a change candidate related to the train station of the next order (next higher rank) and repeats the processes of s71 to s81 (s83).
- the change application determination unit 105 determines the change candidate extracted at the beginning of the change application determination process s39 up to the change candidate related to the running station of the train with the lowest rank (that is, all the change candidates from the highest rank to the lowest rank) s71.
- the change application determination processing s39 ends.
- FIG. 11 is a flowchart for explaining details of the change execution determination process s77.
- the change application determination unit 105 determines the effect of the selected combination candidate by determining the number of inconsistencies in the predicted timetable and the increase or decrease in the evaluation value, and determines whether or not to determine the operation plan related to the selected combination candidate as a change candidate. judge.
- the change application determination unit 105 determines that the number of inconsistencies in all trains of the predicted timetable decreases due to the change in the operation plan related to the selected combination candidate (the number of inconsistencies in the timetable after application becomes the number of inconsistencies in the timetable before application). or the number of inconsistencies of all trains in the predicted timetable has not increased or decreased due to changes in the operation plan related to the selected combination candidate, but the evaluation value of the predicted timetable has improved. It is determined whether or not the condition is satisfied (s91).
- the change application determination unit 105 executes the process of s93; to run.
- the change application determination unit 105 determines the selected combination candidate as a change candidate, and the change execution determination process s77 ends.
- the change application determination unit 105 determines whether the number of inconsistencies in all trains of the predicted timetable has increased and the evaluation value of the predicted timetable has improved due to the change in the operation plan related to the application of the selected combination candidate. Determine whether or not
- the change application determination unit 105 executes the process of s99 if the above condition is satisfied (s95: Yes), and executes the process of s97 if the above condition is not satisfied (s95: No). .
- the change application determination unit 105 determines not to finalize the selected combination candidate as a change candidate (exclude it from the change candidates), and the change execution determination process s77 ends.
- the change application determination unit 105 determines that the number of discrepancies in the train operation related to the selected combination candidate has increased due to the change in the operation plan related to the selected combination candidate, that is, the train operation related to the selected combination candidate has been changed. Determine if any interfering inconsistencies occur.
- the change application determination unit 105 executes the process of s97, and the number of inconsistencies in train operations related to the candidate selection combination does not increase (s99: No), the change application determination unit 105 executes the process of s101.
- the change application determination unit 105 determines whether or not the inconsistencies that have increased due to the change in the operation plan related to the selected combination candidates are resolvable inconsistencies. For example, the change application determination unit 105 determines whether or not the inconsistency has been resolved in the past by searching the permissible inconsistency information in the inconsistency permission list DB 250 . Further, for example, the change application determination unit 105 repeats cancellation and generation (at least a predetermined number of ) is inconsistent.
- the change application determination unit 105 executes the process of s93 and performs the change execution determination process s77. is terminated, and if the inconsistency increased due to the change in the operation plan related to the selected combination candidate is unresolvable inconsistency (s101: No), the change application determination unit 105 executes the process of s97. The change execution determination process s77 ends.
- the operation plan change support device 100 of the present embodiment uses the information on the details of the operation of the train before a certain time point and the information on the change of the operation plan executed before that as the feature amount, and then executes An operation plan change judgment model is generated with information on changes in the operation plan as an output value, and when a problem occurs, a new problem such as delay information that occurs naturally during commuter rush hour or a user-specified problem is used in the operation plan.
- An operation plan change judgment model is generated with information on changes in the operation plan as an output value, and when a problem occurs, a new problem such as delay information that occurs naturally during commuter rush hour or a user-specified problem is used in the operation plan.
- each candidate for changing the operation plan to be executed step by step after the new failure. is created, and a change candidate that satisfies a predetermined condition is created as an operation plan change proposal from each of the created change candidates.
- the operation plan change support device 100 of the present embodiment provides an operation plan change judgment model that outputs information on the necessity of changing the stepwise operation plan that should be made in response to a failure that has occurred.
- Candidates for the operation plan are specified using the above, and a change that satisfies a predetermined condition from those candidates is taken as an operation plan change proposal. In this way, by modeling the know-how of changing the operation plan step by step for troubles that occurred in the past by dispatchers, it is possible to appropriately change the operation plan and recover from the trouble. .
- the operation plan change support device 100 of the present embodiment can support creation of an operation plan change proposal that is executed step by step.
- the operation plan change judgment model uses as input values the type and number of changes in the operation plan executed before a certain point in time, and outputs appropriate changes in the operation plan that are executed step by step with high accuracy. be able to.
- the operation plan change support device 100 creates new operation details (each train in the forecast timetable) based on information on changes in the operation plan output from the operation plan change determination model. Operation details) are sequentially input to the operation plan change judgment model. In this way, by sequentially calculating the operation details of the train at each stage from the operation plan change judgment model and the forecast timetable, changes in the operation plan of the train to be executed can be predicted appropriately.
- the operation plan change support device 100 of the present embodiment calculates the evaluation value of the operation plan when the change indicated by each change candidate is applied, and when it is determined that the calculated evaluation value is the optimum value (optimal value), each change candidate is specified as a change candidate as an operation plan change proposal.
- the operation plan change support device 100 of the present embodiment can change a plurality of operation plans for the same train at the same station, and change the same operation plan for trains with consecutive departure orders at the same station. , changes that do not depend on the control order related to running between trains are set as changes to the operation plan to be executed at the same time. In this way, by grouping changes in the operation plan of each train, it is possible to efficiently discover step-by-step changes in the operation plan that can eliminate problems.
- the operation plan change support device 100 of the present embodiment creates a plurality of combinations of change elements in the change candidates, and calculates the change in the evaluation value based on the change for each of the created multiple combinations. Determine the combinations of modifiers to identify as candidates. This makes it possible to specify the most effective combination of change factors even when change candidates consist of a plurality of elements and there are various change patterns of the operation plan.
- the change candidate is changed as the operation plan change proposal. If it is identified as a candidate and determined not to be resolved, it is excluded from the change candidates. In this way, for example, even if an inconsistency occurs due to a change candidate at a certain stage, if it is resolved later, by accepting the inconsistency and adopting the change candidate, a change that can be used as an operation plan change plan The selection of candidates is increased, making it easier to identify appropriate itinerary changes.
- the operation plan change support device 100 of the present embodiment displays each change in the operation plan change proposal on the screen in the order of stepwise execution. Thereby, the user can confirm the change of the operation plan at each stage to be executed.
- the train operation management system 10 of this embodiment also includes a route control device 60 that controls trains or train equipment based on the created operation plan change plan. As a result, even when a trouble occurs and the operation plan is changed step by step, appropriate train operation control can be performed to restore the operation.
- the present invention is not limited to the above embodiments, and can be implemented using arbitrary constituent elements within the scope of the gist of the present invention.
- the embodiments and modifications described above are merely examples, and the present invention is not limited to these contents as long as the features of the invention are not impaired.
- the present invention is not limited to these contents.
- Other aspects conceivable within the scope of the technical idea of the present invention are also included in the scope of the present invention.
- part of each function provided by each device of the embodiment may be provided in another device, or functions provided by another device may be provided in the same device.
- the operation plan change determination model is configured as one learned model, but may be configured as a plurality of learned models.
- an operation plan change judgment model may be provided for each type of change in the operation plan, or an operation plan change judgment model may be different depending on what stage the change in the operation plan is made in stages. good.
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
Description
本出願は、2021年7月13日に出願された日本特許出願第2021-115476号の優先権を主張し、その内容を参照することにより、本出願に取り込む。
列車の運行管理の業務の一つに運行計画変更業務があり、これを支援する運行計画変更支援システムがある。運行計画変更支援システムに関する技術としては、現在時刻までに得られている各列車の走行実績と運行計画とに基づいて現在時刻以降の各列車の運行状況を予測し、遅延が見込まれる場合には、運行計画変更案を自動で作成して運行管理を担当するオペレータに提示することで、運行計画変更業務を支援するものが知られている。
上記した以外の課題、構成及び効果は、以下の実施形態の説明により明らかにされる。
次に、運行計画変更支援装置100の構成について説明する。
図2は、運行計画変更支援装置100が備える構成の一例を示す図である。運行計画変更支援装置100は、CPU(Central Processing Unit)、DSP(Digital Signal Processor)、GPU(Graphics Processing Unit)、又はFPGA(Field-Programmable Gate Array)等の演算処理装置11と、ROM(Read Only Memory)、RAM(Random Access Memory)等のメモリ12と、HDD(Hard Disk Drive)、又はSSD(Solid State Drive)等の記憶装置13と、マウスやキーボード等で構成される入力装置14と、液晶ディスプレイ又は有機EL(Electro-Luminescence)ディスプレイ等で構成される表示装置15と、NIC(Network Interface Card)、無線通信モジュール、USB(Universal Serial Interface)モジュール、又はシリアル通信モジュール等で構成される通信装置16とを備える。
すなわち、運行計画変更判断モデルは、ある時点以前の列車の運行内容に関する情報、及びその時点の前に実行した運行計画の変更の情報が入力され、その実行した運行計画の次に実行する運行計画の変更の情報を出力する。なお、上記時点の前に実行した運行計画の変更の情報としては、上記時点の前に実行した運行計画の変更の種類及び回数の情報が含まれる。
図3は、変更入力履歴DB200の一例を示す図である。変更入力履歴DB200は、支障に関する情報が設定される支障201、及び、支障201に関する運行計画の変更に関する入力情報が設定される計画変更入力202の各データ項目を有する。
図4は、計画変更ルールの一例を説明する図である。ある駅に到着している列車の遅延のために、他の列車のその駅への到着が遅延している場合231、両列車の当該駅への到着順序及び出発順序を変更する。計画変更ルールは、到着順序や出発順序の変更前の各列車間の各種順序情報と遅延情報、変更後の各列車(関係列車を含む)間の各種順序とを含む情報を記憶する。
次に、列車運行管理システム10が行う処理について説明する。
図6は、教師データ作成処理s1の一例を説明するフロー図である。
教師データ生成部102は、変更入力履歴DB200から、過去に起きた一つの支障(以下、対象支障という)の情報(以下、対象支障情報という)及び、これに対応した運行計画の変更の情報(以下、計画変更情報という)を抽出する(s11)。具体的には、教師データ生成部102は、変更入力履歴DB200から、支障年月日203又は支障201が同一のレコードを全て選択し、選択したレコードの内容を取得する。
ここで図7は、許容不整合情報の一例を説明する図である。まず、2つの列車の発着番線の競合が不整合401(B列車出発後にA列車が到着する番線使用順序、A列車出発後にB列車が出発する出発順序、A列車はP駅到着後に出発するといった着発事象間の順序の矛盾)として発生している。運行計画の変更により、これらの2つの列車の発着番線が異なるものとなった場合402、不整合401は解消される。許容不整合情報は、このような不整合401及び不整合が解消された状態403の列車、駅の着発事象の集合、及びその順序関係をそれぞれ記憶する。
図8は、運行計画変更案作成処理s3の詳細を説明するフロー図である。運行計画変更案作成処理s3は、例えば、列車の運行に関して新規に支障が発生した場合に、自動的に又はユーザからの指定により開始される。
図9は、変更提案画面300の一例を示す図である。変更提案画面300は、運行計画変更表示欄301と、変更実行指定欄302と、再提案欄303とを有する。
次に、図10は、変更適用判断処理s39の詳細を説明するフロー図である。
図11は、変更実行判断処理s77の詳細を説明するフロー図である。変更適用判断部105は、予測ダイヤにおける不整合の数及び評価値の増減を判定することで、選択組み合わせ候補の効果を判定し、選択組み合わせ候補に係る運行計画を変更候補として決定するか否かを判定する。
Claims (11)
- プロセッサ及びメモリを有し、
ある時点以前の列車の運行内容に関する情報、及び前記時点の前に実行した運行計画の変更の情報が入力され、前記実行した運行計画の次に実行する運行計画の変更の情報を出力する運行計画変更判断モデルを生成する判断モデル生成部と、
ユーザから指定された時点以前の列車の運行内容に関する情報、及び前記指定された時点の前に実行した運行計画の変更の情報を前記運行計画変更判断モデルに入力し、前記運行計画変更判断モデルから出力された情報に基づいて運行計画の変更内容の情報を作成することを1回以上繰り返すことにより、前記指定された時点以降に段階的に実行する運行計画の変更のそれぞれの候補である変更候補を作成し、作成した各変更候補から所定条件を満たす変更候補を特定し、特定した変更候補を運行計画変更案として作成する運行計画変更案作成部と、
を備える運行計画変更支援装置。 - 前記運行計画変更案作成部は、前記作成した各変更候補が示す変更が適用された場合の運行計画の評価値を算出し、算出した評価値が最適値であるか否かを判定し、当該評価値が最適値であると判定した場合に、前記各変更候補を前記所定条件を満たす変更候補として特定する、
請求項1に記載の運行計画変更支援装置。 - 前記判断モデル生成部は、列車間の走行に係る制御順序に依存しない、複数の運行計画の変更同士を、同時に実行する運行計画の変更として設定する、請求項1に記載の運行計画変更支援装置。
- 前記判断モデル生成部は、同一の列車に対して同一の駅で行う複数の運行計画の変更、又は、同一の駅における出発順序が連続した列車に対する同一の運行計画変更を、同時に実行する運行計画の変更として設定する、請求項3に記載の運行計画変更支援装置。
- 前記変更候補は、運行計画の変更を構成する複数の変更要素を組み合わせてなり、
前記変更候補における変更要素の組み合わせを複数作成し、作成した複数の組み合わせのそれぞれに対して、変更の効果を表す評価値の変動を算出し、算出した評価値の変動に基づき、前記複数の組み合わせのうち前記変更候補として特定する変更要素の組み合わせを決定する変更適用判断部をさらに備える、
請求項2に記載の運行計画変更支援装置。 - 過去に段階的に実行した各運行計画の変更のうち、その変更により列車の不整合が発生したがその後の段階の変更により当該不整合が解消した運行計画の変更の情報を記憶する許容不整合記憶部と、
前記記憶した情報に基づき、前記作成した変更候補が示す変更による不整合が後の段階で解消されるか否かを判定し、当該不整合が後の段階で解消されると判定した場合に、前記作成した変更候補を、前記所定条件を満たす変更候補として特定し、当該不整合が後の段階で解消されないと判定した場合に、前記作成した変更候補を、前記所定条件を満たさない変更候補として特定する変更適用判断部とをさらに備える、
請求項2に記載の運行計画変更支援装置。 - 前記判断モデル生成部は、ある時点以前の列車の運行内容に関する情報、前記時点の前に実行した運行計画の変更の種類又は回数のうち少なくともいずれかの情報、及び、前記時点で生じている列車の不整合の情報が入力され、前記実行した運行計画の次に実行する運行計画の変更の情報を出力する運行計画変更判断モデルを生成する、
請求項1に記載の運行計画変更支援装置。 - 前記運行計画変更案作成部は、
ユーザから指定された時点以前の列車の運行内容に関する情報、及び前記指定された時点の前に実行した運行計画の変更の情報を前記運行計画変更判断モデルに入力し、
前記運行計画変更判断モデルから出力された運行計画の変更の情報に基づき作成された新たな運行内容に関する情報、及び、前記運行計画変更判断モデルから出力された運行計画の変更の情報を、前記運行計画変更判断モデルにさらに入力することにより、前記変更候補を作成する、
請求項1に記載の運行計画変更支援装置。 - 前記運行計画変更案における各変更を、段階的に実行される順に画面に表示する表示部をさらに備える、請求項1に記載の運行計画変更支援装置。
- 情報処理装置が、
ある時点以前の列車の運行内容に関する情報、及び前記時点の前に実行した運行計画の変更の情報が入力され、前記実行した運行計画の次に実行する運行計画の変更の情報を出力する運行計画変更判断モデルを生成する判断モデル生成処理と、
ユーザから指定された時点以前の列車の運行内容に関する情報、及び前記指定された時点の前に実行した運行計画の変更の情報を前記運行計画変更判断モデルに入力し、前記運行計画変更判断モデルから出力された情報に基づいて運行計画の変更内容の情報を作成することを1回以上繰り返すことにより、前記指定された時点以降に段階的に実行する運行計画の変更のそれぞれの候補である変更候補を作成し、作成した各変更候補から所定条件を満たす変更候補を特定し、特定した変更候補を運行計画変更案として作成する運行計画変更案作成処理と、
を実行する運行計画変更支援方法。 - プロセッサ及びメモリを有し、
ある時点以前の列車の運行内容に関する情報、及び前記時点の前に実行した運行計画の変更の情報が入力され、前記実行した運行計画の次に実行する運行計画の変更の情報を出力する運行計画変更判断モデルを生成する判断モデル生成部と、
ユーザから指定された時点以前の列車の運行内容に関する情報、及び前記指定された時点の前に実行した運行計画の変更の情報を前記運行計画変更判断モデルに入力し、前記運行計画変更判断モデルから出力された情報に基づいて運行計画の変更内容の情報を作成することを1回以上繰り返すことにより、前記指定された時点以降に段階的に実行する運行計画の変更のそれぞれの候補である変更候補を作成し、作成した各変更候補から所定条件を満たす変更候補を特定し、特定した変更候補を運行計画変更案として作成する運行計画変更案作成部と、を備える運行計画変更支援装置と、
前記作成した運行計画変更案に基づき、列車又は列車の設備を制御する進路制御装置とを有する、列車運行管理システム。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2022312793A AU2022312793A1 (en) | 2021-07-13 | 2022-04-28 | Device for assisting with changing operation plan, method for assisting with changing operation plan, and train operation management system |
EP22841772.1A EP4371849A1 (en) | 2021-07-13 | 2022-04-28 | Device for assisting with changing operation plan, method for assisting with changing operation plan, and train operation management system |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2021-115476 | 2021-07-13 | ||
JP2021115476A JP7476142B2 (ja) | 2021-07-13 | 2021-07-13 | 運行計画変更支援装置、運行計画変更支援方法、及び列車運行管理システム |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023286425A1 true WO2023286425A1 (ja) | 2023-01-19 |
Family
ID=84919294
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2022/019380 WO2023286425A1 (ja) | 2021-07-13 | 2022-04-28 | 運行計画変更支援装置、運行計画変更支援方法、及び列車運行管理システム |
Country Status (4)
Country | Link |
---|---|
EP (1) | EP4371849A1 (ja) |
JP (2) | JP7476142B2 (ja) |
AU (1) | AU2022312793A1 (ja) |
WO (1) | WO2023286425A1 (ja) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH10250581A (ja) * | 1997-03-12 | 1998-09-22 | Mitsubishi Electric Corp | 列車運転整理装置 |
JP2011031697A (ja) * | 2009-07-31 | 2011-02-17 | Hitachi Ltd | 運行管理方法,運行管理装置,走行制御装置 |
JP2014019182A (ja) * | 2012-07-12 | 2014-02-03 | Hitachi Ltd | 列車運行指令装置 |
JP2018079874A (ja) * | 2016-11-18 | 2018-05-24 | 東日本旅客鉄道株式会社 | 乗務員配置管理支援システム |
JP2019166931A (ja) * | 2018-03-22 | 2019-10-03 | 株式会社日立製作所 | 列車運行管理システムおよび列車運行管理方法 |
JP2021115476A (ja) | 2020-01-21 | 2021-08-10 | 大阪ガスケミカル株式会社 | 臭気物質吸着剤 |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4191497B2 (ja) | 2003-01-21 | 2008-12-03 | 財団法人鉄道総合技術研究所 | 運転整理案作成情報及び運転整理案作成装置 |
-
2021
- 2021-07-13 JP JP2021115476A patent/JP7476142B2/ja active Active
-
2022
- 2022-04-28 EP EP22841772.1A patent/EP4371849A1/en active Pending
- 2022-04-28 AU AU2022312793A patent/AU2022312793A1/en active Pending
- 2022-04-28 WO PCT/JP2022/019380 patent/WO2023286425A1/ja active Application Filing
-
2024
- 2024-04-16 JP JP2024066284A patent/JP2024088805A/ja active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH10250581A (ja) * | 1997-03-12 | 1998-09-22 | Mitsubishi Electric Corp | 列車運転整理装置 |
JP2011031697A (ja) * | 2009-07-31 | 2011-02-17 | Hitachi Ltd | 運行管理方法,運行管理装置,走行制御装置 |
JP2014019182A (ja) * | 2012-07-12 | 2014-02-03 | Hitachi Ltd | 列車運行指令装置 |
JP2018079874A (ja) * | 2016-11-18 | 2018-05-24 | 東日本旅客鉄道株式会社 | 乗務員配置管理支援システム |
JP2019166931A (ja) * | 2018-03-22 | 2019-10-03 | 株式会社日立製作所 | 列車運行管理システムおよび列車運行管理方法 |
JP2021115476A (ja) | 2020-01-21 | 2021-08-10 | 大阪ガスケミカル株式会社 | 臭気物質吸着剤 |
Also Published As
Publication number | Publication date |
---|---|
JP7476142B2 (ja) | 2024-04-30 |
JP2023012060A (ja) | 2023-01-25 |
AU2022312793A1 (en) | 2024-02-01 |
JP2024088805A (ja) | 2024-07-02 |
EP4371849A1 (en) | 2024-05-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6605929B2 (ja) | 資源運用計画支援装置および資源運用計画支援方法 | |
JP4241584B2 (ja) | 車両基地構内入換シーケンス作成装置、方法及びプログラム | |
Lapouchnian et al. | Re-designing process architectures towards a framework of design dimensions | |
JP6038693B2 (ja) | 進路制御装置、進路制御方法、および進路制御プログラム | |
AU2024201401A1 (en) | Vehicle operation planning assistance apparatus and vehicle operation planning assistance method | |
WO2023286425A1 (ja) | 運行計画変更支援装置、運行計画変更支援方法、及び列車運行管理システム | |
JP7195757B2 (ja) | 運行管理システム | |
JP5096698B2 (ja) | スケジュール修正装置 | |
JP7403421B2 (ja) | 運行計画変更支援装置、判断モデル作成装置、判断モデル作成プログラム、及び列車運行管理システム | |
US11836657B2 (en) | Resource management planning support device, resource management planning support method, and programs | |
JP2017154536A (ja) | 乗務員運用管理システムおよび乗務員運用管理方法 | |
JP2022046957A5 (ja) | ||
Zhan et al. | Handling uncertainty in train timetable rescheduling: A review of the literature and future research directions | |
JP6298515B2 (ja) | 進路制御装置および進路制御方法 | |
JP2021075161A5 (ja) | ||
JPH07182177A (ja) | 知識獲得支援システム | |
JP2022114172A (ja) | 解析装置及び解析方法 | |
WO2023276428A1 (ja) | 運転整理システム、及び運転整理案の生成方法 | |
WO2023100417A1 (ja) | 運行計画作成システム、運行計画作成方法、運行計画作成プログラム、及び輸送計画システム | |
JP6603542B2 (ja) | 車両運用業務支援装置 | |
JP2023004628A (ja) | 生産計画変更支援装置、生産計画変更支援方法、そのプログラム、および生産管理システム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22841772 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2022312793 Country of ref document: AU Ref document number: AU2022312793 Country of ref document: AU |
|
ENP | Entry into the national phase |
Ref document number: 2022312793 Country of ref document: AU Date of ref document: 20220428 Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2022841772 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2022841772 Country of ref document: EP Effective date: 20240213 |