Train operation control system, parameter creation system, and parameter creation method

Abstract

To provide a parameter production system which can output a probable prediction diagram.SOLUTION: A train operation management system comprises an arithmetic unit to perform specified processes and a storage device to which the arithmetic unit is accessible. The arithmetic unit has: an input unit to input a plan diagram, an evaluation scenario of the plan diagram, an evaluation index, facility data and a beginning value input of the parameter; a prediction unit for predicting a diagram according to one or more evaluation scenarios and producing a prediction diagram; and a parameter narrowing down unit for comparing the plan diagram with the prediction diagram to narrow down the parameter value satisfying the evaluation index. The operation management system predicts the train diagram using the narrowed down parameter and outputs signals to control track facilities according to the predicted train diagram.SELECTED DRAWING: Figure 1A

Description

[Technical field]

[0001] The present invention relates to a system for creating parameters required for predicting train operations in a train traffic control system. [Background technology]

[0002] Train traffic control is a task that supports transportation by trains by controlling train operating times and routes (hereafter referred to as "paths") based on train operation plans. To improve the efficiency of train traffic control, train traffic control systems with train operation prediction functions have been developed.

[0003] The following prior art is included as background art in this technical field. Patent Document 1 (JP Patent Publication No. 2016-30542 A) describes a train traffic management system that includes an environmental change detection unit that detects where the environment related to the train has changed, a condition storage unit that stores affected area information corresponding to the train's status, an affected area specification unit that specifies the affected area of ​​the environmental change based on the location where the environment has changed and the affected area information stored in the condition storage unit, a condition determination unit that determines constraint conditions for predicting train operation based on the specified affected area, and a prediction unit that predicts train operation based on the determined constraint conditions.

[0004] In addition, in Patent Document 2 (JP Patent Publication No. 2019-93906A), an operation management support device according to an embodiment includes a configuration information storage unit, an input unit, and an identification unit. The configuration information storage unit stores configuration information indicating each configuration provided in an operation management system that manages train operation. The input unit inputs actual timetable data indicating operation results when a train managed by the operation management system that manages train operation is operated according to a route, and predetermined timetable data indicating an operation status when the train runs on schedule along the route. The identification unit identifies a configuration provided in the operation management system that is to be modified to operate the train according to the predetermined timetable data, based on the difference between the actual timetable data and the predetermined timetable data and the configuration information stored in the configuration information storage unit. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2016-30542 A [Patent Document 2] JP 2019-93906 A [Patent Document 3] JP 2012-245801 A [Patent Document 4] JP 2009-96221 A Summary of the Invention [Problem to be solved by the invention]

[0006] In the train operation prediction function, which is one of the functions of the train traffic management system, train operations are represented by a timetable that shows the arrival and departure times at stations on the train's operation route, and future timetables are predicted. In Patent Document 1 (JP 2016-30542 A), parameters necessary for timetable prediction are modeled in the form of standard operation time and intersection interval. In order to predict the timetable plausibly, it is necessary to model signal equipment, vehicles, etc., and input appropriate parameters into the model. However, the correspondence between the control data of the signal equipment, vehicles, etc. and the parameters is not clear, and since there are many parameters, there is a degree of freedom in the values ​​that can be taken, and trial and error is required to create the parameters. In addition, in situations where the operator is not familiar with the train traffic management system or when detailed data of the control system (e.g., operation curves) is difficult to obtain on a new line, trial and error is required to create the parameters.

[0007] For this reason, unless you are thoroughly familiar with the behavior of the train traffic control system, you cannot create plausible parameters, and even if you are familiar with train traffic control systems, it takes time to create parameters because of the trial and error required.In addition, with the conversion of wayside signaling equipment to on-board signaling, it will be possible to update control data by updating software, and it is expected that the frequency of creating parameters to follow the control data will increase, so efficient parameter creation is required.

[0008] As a method for supporting parameter creation, the method described in Patent Document 2 (JP Patent Publication 2019-93906) identifies the parts to be corrected in the configuration of the train traffic control system from the difference between the actual timetable and the specified timetable. This makes it possible to quickly identify the devices that require correction. However, Patent Document 2 does not mention how to correct the identified parts. Furthermore, Patent Document 2 cannot be applied when the actual timetable for a new line is not available.

[0009] An object of the present invention is to create parameters that enable output of a plausible predicted schedule from parameter value candidates with a degree of freedom. [Means for solving the problem]

[0010] A representative example of the invention disclosed in the present application is as follows: That is, a train traffic control system includes a calculation device that executes a predetermined process, and a storage device accessible by the calculation device, the calculation device includes an input unit that receives inputs of a planned timetable, an evaluation scenario for the planned timetable, an evaluation index, equipment data, and initial values ​​of parameters, the calculation device includes a prediction unit that predicts a timetable according to one or more of the evaluation scenarios and creates a predicted timetable, and the calculation device includes a parameter narrowing unit that compares the planned timetable with the predicted timetable and narrows down parameter values ​​that satisfy the evaluation index, and the traffic control system predicts a train timetable using the narrowed down parameters and outputs a signal to control track equipment according to the predicted train timetable. Effect of the Invention

[0011] According to one aspect of the present invention, it is possible to create plausible parameters without trial and error.Objects, configurations and effects other than those described above will become apparent from the following description of the embodiments. [Brief description of the drawings]

[0012] [Figure 1A]1 is a diagram showing the overall configuration of a parameter creation system according to an embodiment of the present invention; [Figure 1B] FIG. 2 is a diagram illustrating a physical configuration of the parameter creating system according to the present embodiment. [Diagram 2] FIG. 2 is a diagram showing a line layout represented by facility data of the present embodiment. [Diagram 3] FIG. 2 is a diagram showing a table that is an example of a planned timetable in this embodiment. [Figure 4A] FIG. 13 is a diagram showing a table that is an example of a configuration of provisional parameters in the present embodiment. [Figure 4B] FIG. 13 is a diagram showing a table that is an example of a configuration of provisional parameters in the present embodiment. [Diagram 5] FIG. 13 is a diagram showing a table that is an example of a robustness evaluation scenario configuration in the present embodiment. [Figure 6] FIG. 13 is a diagram showing a table that is an example of the configuration of parameter application priority information in the present embodiment. [Figure 7] FIG. 13 is a diagram showing a table that is an example of the configuration of an improvement history in the present embodiment. [Figure 8A] FIG. 2 is a sequence diagram of a process executed by the parameter generating system of the present embodiment. [Figure 8B] FIG. 2 is a sequence diagram of a process executed by the parameter generating system of the present embodiment. [Figure 9] 3 is a flowchart showing an overall flow of processing by the parameter creating system of the present embodiment. [Figure 10] 13 is a flowchart of a process for calculating a constraint equation for each parameter in the case of a robustness evaluation scenario according to the present embodiment. [Figure 11] 11 is a flowchart of a process (S400) for calculating a representative value from a set range of parameters that summarize a plurality of constraint equations in this embodiment. [Figure 12] FIG. 13 is a diagram showing an example of an input screen for an operator in the present embodiment. [Figure 13] FIG. 13 is a diagram showing an example of an output screen presented to a worker in the present embodiment. [Figure 14] FIG. 2 is a diagram showing a predicted timetable created by the present embodiment. [Figure 15]13 is a graph illustrating adjustments to the running time between stations B and C and the stop time at station C in evaluation scenario 2 in this embodiment. [Figure 16] FIG. 13 is a diagram showing the setting ranges of multiple parameters calculated using the steady scenario and evaluation scenario 2 of this embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0014] FIG. 1A is a diagram showing the overall configuration of a parameter generating system 100. As shown in FIG.

[0015] The parameter creation system 100 is a device that creates data for the train traffic control system 99 to operate. The train traffic control system 99 collects train information from track facilities and transmits information required for train operation to the track facilities and trains. The parameter creation system 100 is positioned as a subsystem of the train traffic control system 99, but may be a system separate from the train traffic control system 99. For example, when the parameter creation system 100 and the train traffic control system 99 are installed in separate computer environments, data may be transferred via a network or a storage medium. In this case, the data received by the operator 98 from the outside may always be the latest data online, and the created data may be reflected in the train traffic control system 99. In addition, when data on actual running performance can be used on an existing line, the actual timetable and the predicted timetable may be compared instead of the planned timetable. When the improvement history 105 is sufficiently stored, adjustment by the operator 98 may be unnecessary. In this configuration, even if regular updates of control data are required due to on-board signaling and automatic driving, the data following the control is automatically updated, and the burden of data creation can be reduced.

[0016] The parameter creation system 100 includes an input unit 101, a prediction unit 102, a parameter narrowing unit 103, a result presentation unit 104, and an improvement history 105. The input unit 101 is a unit that accepts data input from an operator 98. The prediction unit 102 is a unit that predicts a schedule from parameters, and can be realized, for example, by the technology described in JP 2012-245801 A. The parameter narrowing unit 103 is a unit that narrows down likely values ​​from parameters with degrees of freedom. The parameter narrowing unit 103 includes a parameter value candidate creation unit 103A that creates candidates for parameter values, a constraint equation calculation unit 103B that determines whether the schedule prediction result satisfies an evaluation index 109B and calculates a constraint equation that the parameter value satisfies, and a parameter value selection unit 103C that selects one parameter value that satisfies all the constraint equations for one or more evaluation scenarios.

[0017] The result presentation unit 104 is a part that presents the created parameters to the worker 98. The improvement history 105 records feedback from the worker 98 when the results are presented. The parameter creation system 100 receives a planning diagram 107, provisional parameters 108, a robustness evaluation scenario 109A, an evaluation index 109B, and parameter application priority information 110 from the outside. These data 107 to 110 will be described later with reference to Figs. 3 to 6.

[0018] FIG. 1B is a diagram showing the physical configuration of the parameter generating system 100. As shown in FIG.

[0019] The parameter generating system 100 is configured by a computer having a processor (CPU) 1, a memory 2, an auxiliary storage device 3, and a communication interface 4. The parameter generating system 100 may also have an input interface 5 and an output interface 6.

[0020] The processor 1 is a calculation device that executes programs stored in the memory 2. The processor 1 executes various programs to realize the functions of the functional units (e.g., the input unit 101, the prediction unit 102, the parameter narrowing unit 103, the result presentation unit 104, etc.) of the parameter creation system 100. Note that some of the processes performed by the processor 1 by executing the programs may be executed by other calculation devices (e.g., hardware such as ASIC and FPGA).

[0021] The memory 2 includes a ROM, which is a non-volatile storage element, and a RAM, which is a volatile storage element. The ROM stores unchanging programs (e.g., BIOS) and the like. The RAM is a high-speed, volatile storage element such as a DRAM (Dynamic Random Access Memory), and temporarily stores programs executed by the processor 1 and data used when the programs are executed.

[0022] The auxiliary storage device 3 is, for example, a large-capacity non-volatile storage device such as a magnetic storage device (HDD) or a flash memory (SSD). The auxiliary storage device 3 also stores data (for example, improvement history 105) used by the processor 1 when executing a program, and the program executed by the processor 1. That is, the program is read from the auxiliary storage device 3, loaded into the memory 2, and executed by the processor 1 to realize each function of the parameter creation system 100.

[0023] The communication interface 4 is a network interface device that controls communication with other devices (for example, a train traffic control system 99) in accordance with a predetermined protocol.

[0024] The input interface 5 is an interface to which input devices such as a keyboard 7 and a mouse 8 are connected and which receives input from an operator. The output interface 6 is an interface to which output devices such as a display device 9 and a printer (not shown) are connected and which outputs the results of program execution in a format that can be viewed by an operator. Note that a user terminal connected to the parameter creation system 100 via a network may provide the input device and the output device. In this case, the parameter creation system 100 may have a web server function and the user terminal may access the parameter creation system 100 using a predetermined protocol (e.g., http).

[0025] The program executed by the processor 1 is provided to the parameter creating system 100 via a removable medium (such as a CD-ROM or a flash memory) or a network, and is stored in a non-volatile auxiliary storage device 3, which is a non-transitory storage medium. For this reason, it is preferable that the parameter creating system 100 has an interface for reading data from the removable medium.

[0026] The parameter generating system 100 is a computer system configured on one physical computer, or on multiple logically or physically configured computers, and may operate on a virtual computer constructed on multiple physical computer resources. For example, the input unit 101, the prediction unit 102, the parameter narrowing unit 103, and the result presentation unit 104 may each operate on separate physical or logical computers, or may be combined to operate on a single physical or logical computer.

[0027] FIG. 2 is a diagram showing a track layout represented by the facility data 106.

[0028] The facility data 106 includes stations, track numbers, signals, and line shapes. In the figure, there are stations A, B, and C, track numbers are represented by #1 and #2, and signals are represented by 8111, 8121, 8211, 8212, 8311, and 8321. Figure 2 shows a line shape that ends at station C and has a turn-back operation.

[0029] FIG. 3 is a diagram showing table T01, which is an example of the configuration of the planned timetable 107. Although each data is shown in a table format in FIG. 3 to FIG. 6, the data may be configured in a format other than a table. The planned timetable 107 (table T01) records the arrival and departure platform numbers and arrival and departure times for each station related to train operation, and includes a serial number T01a, which is identification information for a row record, a (train number) platform number T01b, which is identification information for a train, a station T01c, a platform T01d, an arrival time T01e, and a departure time T01f. In addition to the data shown in table T01, the planned timetable 107 may also include the interval width of the planned timetable (the minimum time interval set when creating the planned timetable).

[0030] 4A and 4B are diagrams showing a table T02 which is an example of the configuration of the provisional parameters 108. The provisional parameters 108 are composed of parameters (e.g., running time) set between the departure station T02c and the arrival station T02d shown in FIG. 4A, and parameters (e.g., turn back time, continuing interval, crossing obstacle interval) set for the station T02e and the platform shown in FIG. 4B. The tables shown in FIG. 4A and FIG. 4B may be configured separately as shown, or may be configured together. These provisional parameters may be created for each train type and vehicle performance. The provisional parameters 108 (table T02) include a serial number T02a, a parameter type T02b, a parameter section (departure station T02c, arrival station T02d, station T02e), and a provisional value T02f.

[0031] When the train traffic control system 99 is already in operation and there is a parameter serving as a basis, the provisional parameter 108 is set to the value of the parameter as an initial value. When there is no parameter serving as a basis, a default value determined by the parameter specification is set. Examples of these parameters include the stop time, turn back time, continuing interval, and crossing obstacle interval described in a publicly known document (JP Patent Publication No. 2009-96221). Of these, the stop time and turn back time are set for a station, and the continuing interval and crossing obstacle interval are set between stations. For example, in the line shown in FIG. 2, the continuing interval is the time interval between the preceding train and the following train at station B, and the crossing obstacle interval is the time interval that must be secured between the preceding and succeeding trains when passing through a junction installed at station A or station C. The parameter values ​​may be continuous values ​​such as hours and minutes, or discrete values ​​such as the necessity of securing these intervals.

[0032] 5 is a diagram showing Table T03, which is an example of the configuration of the robustness evaluation scenario 109A. The robustness evaluation scenario 109A expresses the robustness taken into consideration when creating a planned timetable, in terms of the allowable delay from each point. The robustness evaluation scenario 109A (Table T03) includes a serial number T03a, a station T03b where an expected delay occurs, an expected delay time T03c, and a station T03d where the expected delay, which is entered in the delay-occurring station, is recovered (a state in which the departure time of the predicted timetable and the planned timetable match).

[0033] 6 is a diagram showing table T04, which is an example of the configuration of parameter application priority information 110. Parameter application priority information 110 (table T04) is used when apportioning parameter adjustment amounts among a plurality of parameters. The parameter adjustment amount may be determined by a method of quantifying a ratio including a slack time specific to a parameter type. Parameter application priority information 110 (table T04) includes a serial number T04a, a parameter type T04, and a priority order T04c.

[0034] FIG. 7 is a diagram showing a table T05 which is an example of the configuration of the improvement history 105. The improvement history 105 is used for creating the next parameter that accumulates feedback from the worker 98 when the result is presented. The improvement history 105 (table T05) includes a serial number T05a, a parameter type T05b, a departure station T05c and a destination station T05d of the section of the parameter, a proposed setting range T05e, a proposed representative value T05f, an improvement type T05g, and an improvement instruction T05h. The setting range T05e indicates a parameter setting range that has a degree of freedom due to narrowing down the parameter. The representative value is a setting value selected from the setting range. The method of selecting the setting value will be described later. The improvement type T05g is recorded as "approval" when a representative value is adopted as a parameter, "selection" when a value other than the representative value is selected from the setting range, and "new" when a value is specified from outside the setting range or a parameter type other than the presented one is specified. In the improvement instruction T05h, when the improvement type T05g is selected or new, the selected or specified value is recorded and provided to the train traffic control system 99.

[0035] 8A and 8B are sequence diagrams of the processing executed by the parameter creation system 100, where FIG. 8A shows the entire processing, and FIG. 8B shows the forecast diagram generation processing based on a steady scenario and the forecast diagram generation processing based on the robustness evaluation scenario 109A.

[0036] An operator 98 inputs input data including facility data 106, planned timetable 107, provisional parameters 108, and robustness evaluation scenario 109A into an input unit 101. Parameter application priority information 110 is created and incorporated by a developer of the parameter creation system 100. The input unit 101 registers the input data in predetermined databases 106 to 110. Upon completing the data registration, the input unit 101 transmits to a parameter narrowing-down unit 103 an address where the registered data is stored.

[0037] The parameter narrowing unit 103 sends the planned schedule 107 and the provisional parameters 108 to the prediction unit 102. The prediction unit 102 predicts a schedule using the data sent from the parameter narrowing unit 103. When the schedule prediction using the provisional parameters 108 is completed, the parameter narrowing unit 103 creates parameters 111 that have been adjusted based on the planned schedule.

[0038] The parameter narrowing unit 103 acquires a forecasted timetable (a timetable predicted from the current time calculated using parameters) created by the prediction unit 102 using the planned timetable 107, parameters 111 adjusted in the planned timetable, and the robustness evaluation scenario 109A. The parameter narrowing unit 103 uses the forecasted timetable, the planned timetable 107, the improvement history 105, and parameter application priority information 110 to calculate parameter setting ranges and representative values, and sends them to the result presentation unit 104.

[0039] The result presenting unit 104 presents to the operator 98 the comparison result between the planned schedule 107 and the forecast schedule, the comparison result between the provisional parameters 108 and the parameter setting ranges and representative values, and the applied robustness evaluation scenario 109A.

[0040] The operator 98 instructs the adjustment method for the presented results on the output screen. The result presentation unit 104 stores the instruction from the operator 98 in the improvement history 105, creates adjusted parameters 111 based on the instruction, and presents them to the operator 98.

[0041] FIG. 9 is a flowchart showing the overall flow of processing by the parameter generating system 100 of this embodiment.

[0042] First, input data is registered in the facility data 106, the planned timetable 107, the provisional parameters 108, the robustness evaluation scenario 109A, and the parameter application priority information 110 (S201).

[0043] Next, a timetable is predicted using the provisional parameters 108 (S202). After that, for the arrival and departure times at each station, trains whose predicted timetable created in step S202 is later than the planned timetable by more than the increment of the planned timetable are extracted (S203). Early departures are prohibited on railways, so delayed trains are extracted. For example, if the increment of the planned timetable is 5 seconds, and a train's departure time from Station A on the planned timetable is 12:00:00 and arrival time at Station B is 12:03:00, and the predicted timetable's departure time from Station A is 12:00:00 and arrival time at Station B is 12:03:05, this train is a train to be extracted. In addition, if trains depart from platforms 1 and 2 at Station A at the same time toward the same track, this train is a train to be extracted because the departure time of one of the trains will be delayed. Since differences less than the planned timetable increment are included within the range of rounding error, the number of times predictions need to be made can be reduced by extracting trains that are slower than the planned timetable increment.

[0044] Then, for all the extracted trains (S204a to S204b), a steady scenario (a scenario in which trains run according to the planned schedule without delay) is used to change parameters related to the locations where differences occur, and the schedule is predicted (S300). Details of the process S300 will be described with reference to Fig. 10. Also, the process of calculating constraint equations indicating the value ranges for each parameter for each scenario will be described with reference to Fig. 10.

[0045] The constraint equations for each parameter created for each train among multiple robustness evaluation scenarios are compiled to create a representative value (S400). Details of process S400 will be described with reference to FIG. 11. The representative value of the parameter that matches the planned timetable is saved as the adjusted parameter 111 in the planned timetable. In addition, by recording the parameter type that has changed in the predicted timetable in the timetable prediction and the part of the timetable where the change occurred, process S300 using the robustness evaluation scenario 109A is efficiently executed. The repetitive process of processes S204a to S204b may be performed in parallel for each train to shorten the time required for timetable prediction.

[0046] After that, the departure time of a certain train is delayed by a value written in the robustness evaluation scenario 109A (S205). By inserting a delay, the slack time included in the planned timetable is eliminated, and a predicted timetable calculated by a combination of parameters can be obtained. Then, for each evaluation scenario of the robustness evaluation scenario 109A (S206a to S206b), a timetable prediction in a delayed state is performed, and a constraint equation expressing the range that the parameters can take is calculated (S300). The calculated constraint equations for each evaluation scenario are compiled, and a setting range and a representative value are created (S400). The iterative process of process S206 may be performed in parallel for each evaluation scenario to shorten the time required for timetable prediction.

[0047] The created setting range and representative value are presented to the operator 98 on an output screen displayed together with the provisional parameters 108 (S207). The operator 98 inputs feedback on the improvement method for the presented parameters, and the input feedback is recorded in the improvement method. By enriching the improvement history 105, the amount of data on which the representative value is determined increases, the need to check the parameter values ​​decreases, and the accuracy of the automatically adjusted parameters can be improved.

[0048] FIG. 10 is a flowchart of the process of calculating the constraint equations for each parameter in the case of the robustness evaluation scenario 109A, showing the process S300 in detail.

[0049] First, a timetable is predicted using given parameters (S301). A predicted timetable created using the planned timetable in FIG. 3 and each of the scenarios in FIG. 5 is shown in FIG. 14. The timetable shown in FIG. 14 includes arrival times T06e and departure times T06f of each train at each station using the steady-state scenario, arrival times T06g and departure times T06h of each train at each station using evaluation scenario 1, and arrival times T06i and departure times T06j of each train at each station using evaluation scenario 2. In evaluation scenario 1, predictions are made under the condition that the departure time at Station A is delayed by 90 seconds at #2. In evaluation scenario 2, predictions are made under the condition that the departure time at Station B is delayed by 30 seconds at #4.

[0050] After that, the planned schedule and the predicted schedule are compared to determine the parameter adjustment target (S302). If the departure time and arrival time of each station do not match between the planned schedule and the predicted schedule, it is determined that there is a difference, and the parameters are changed. The parameters to be changed are selected as the station where the difference first occurred on the train's route (hereinafter referred to as the difference origin station) and the parameters for the section between stations with the difference origin station as the departure station or arrival station. For example, in the case of the linearity of FIG. 2, when the timetable difference occurs from the arrival at station B, the parameters related to the departure from station A, which is immediately before the difference occurrence origin, to the arrival at station B, which is the origin of the difference occurrence (in the parameters of FIG. 4, #1 set between stations A and B, #12 set at the branch between stations A and B, and #9 and #10 set at the interval between the trains before and after stations A and B) are applicable. In the case of the stationary scenario, the parameters at the point where the difference occurs are comprehensively selected. In the case of the robustness evaluation scenario 109A, continuous values ​​that were effective in the processing in the stationary scenario may be extracted. In this case, the parameters that cause changes in the predicted schedule can be efficiently found, and the number of timetable predictions can be reduced.

[0051] Using the extracted parameters, a repeat process is performed for each parameter and for each set of parameters (S303a to S303b). The set of parameters is all possible combinations of the extracted parameters, and the repeat process is performed for all these combinations. For example, if a repeat interval is required, a combination of the repeat intervals can occur, but if an interval is not required, a combination of the repeat intervals cannot occur. The repeat process may be performed in parallel to reduce calculation time. The reason for performing the repeat process for all combinations is that there are parameter types that are in a relationship where a change is not reflected in the predicted timetable unless a certain parameter type is changed. For example, if the repeat interval, which is the time interval between the departure of a preceding train and the arrival of the train at a certain station, determines the predicted arrival time of the following train, the predicted arrival time at the station will not change even if the running time between the stations arriving at the aforementioned station is shortened.

[0052] Next, the amount of change in the parameter is determined. The equipment data 106 of the section of the applied robustness evaluation scenario 109A (the section from station T03b to station T03d) is referred to, and it is determined whether there is a linear shape that is a bottleneck in operation, such as an intersection or a single-track section (S304). The presence or absence of a bottleneck can be determined by whether a bottleneck such as a single track or a passing is on the operating line of the train. In the example of evaluation scenario 2, since a single-track section exists at station B, the determination is YES. If the determination is YES, a first setting value is set as the increment for adjusting the parameter (S305). If the determination is NO, a second setting value is set as the increment for adjusting the parameter (S306). Note that the first setting value is set in advance to a value smaller than the second setting value. For example, it is preferable to set the minimum value of the parameter specification as the first setting value, and set the increment of the planned timetable as the second setting value. Since an intersection occurs at a point where multiple trains cross and become a bottleneck in operation management, the possibility of creating parameters that can output a plausible predicted timetable is increased by finely adjusting the parameters. However, since the amount of calculations required would be large if the minimum values ​​in the specifications were used everywhere, it is advisable to adjust the parameters in large increments except for bottleneck locations. This reduces the time required to calculate the parameters while maintaining the plausibility of the forecast schedule.

[0053] In the case of robustness evaluation scenario 109A, the determined parameter step size is subtracted from the given parameter (S307), and if the parameter is equal to or greater than 0 (S308), a timetable is predicted (S309). If the parameter is less than 0, the parameter to be subjected to the repeated process is changed. This process is repeated until the predicted timetable recovers to the assumed point of robustness evaluation scenario 109A (S310). The reason for subtracting is that, for parameters for which data is designed in units of time, predictions made under conditions that delay departure times do not predict an increase in the overall required time.

[0054] In the case of a stationary scenario, the processing in the loop of S303a to S303b may be executed in two stages: processing with the interval between preceding and following trains as the increment width for the purpose of changing the train order, and processing with the planned timetable increment width for the purpose of matching with the planned timetable. This can shorten the time required for timetable prediction, allowing parameters to be adjusted efficiently.

[0055] For each parameter and for each group of parameters, parameter values ​​for outputting a predicted timetable that will recover train delays according to robustness evaluation scenario 109A and the predicted timetable are extracted (S311). Based on the extracted parameter values, a constraint equation indicating the value range for each parameter and group of parameters is found (S312). If parameter values ​​that can recover train delays according to robustness evaluation scenario 109A cannot be found, the provisional parameter values ​​are left as they are. It is advisable to set a flag to indicate that parameter values ​​that can recover train delays have not been found.

[0056] Here, an example will be described with reference to Fig. 15. A graph 700 shows adjustments to the running time between stations B and C and the stop time at station C in evaluation scenario 2.

[0057] In evaluation scenario 2, a delay of up to 30 seconds at Station B is acceptable. In other words, the planned timetable is set to include a 30-second slack time between the departure time from Station B and the departure time from Station C, which is the recovery point. If the entire 30 seconds of slack time is used up only in the running time between Stations B and C, the possible range for the running time between Stations B and C will be 90 seconds or less, which is 30 seconds shorter than the 120 seconds (702) adjusted in the planned timetable. Similarly, the possible range for the stop time at Station C will be 30 seconds or less, which is 30 seconds shorter than the 60 seconds (703) adjusted in the planned timetable. A line segment 701 can be drawn connecting points 702 and 703. Therefore, in order for the parameters alone to not exceed the parameters adjusted in the planned timetable, the running time between stations B and C is set to 120 seconds or less, and the stop time at station C is set to 60 seconds or less; when the parameters are combined, the sum of the running time between stations B and C and the stop time at station C is calculated to be 150 seconds or less.

[0058] FIG. 11 is a flowchart of the process (S400) of calculating a representative value from the set range of parameters that summarize a plurality of constraint equations.

[0059] First, the constraint equations for multiple parameters are compiled to calculate the setting range (S401). An example of using the stationary scenario and evaluation scenario 2 is shown in Figure 16. The range of possible values ​​is narrowed down based on the relationships between parameters in multiple scenarios. The example of the part already described in T07i is the applicable range of the stationary scenario and robustness evaluation scenario 109A in Figure 15.

[0060] Next, the process branches into a stationary scenario and a robustness evaluation scenario 109A. In the case of only the stationary scenario, the median value of each parameter is set as a representative value (S408), and the process S400 ends.

[0061] In the case of the robustness evaluation scenario 109A, the improvement history 105 is referred to and it is judged whether there are any parts with the same planned schedule, combination of setting ranges, or ranges that are very similar (S402). If such an improvement history 105 exists, a slack time allocation ratio for each parameter is created from the improvement history 105 (S403). The slack time allocation ratio is a ratio for allocating slack time in a constraint equation calculated by each scenario. If such an improvement history 105 does not exist, the parameter application priority information 110 is referred to and it is judged whether the parameter exists (S404). If such parameter application priority information 110 exists, a slack time allocation ratio for each parameter is created from the parameter application priority information 110 (S405). If a slack time allocation ratio is created from the improvement history 105 or a parameter, the value of each parameter is subtracted by the allocated slack time from the maximum value of the setting range of the parameter combination for which the allocation ratio was determined (S406). By using such a proportional allocation ratio for the slack time, it is possible to suppress bias toward parameters with slack time and to increase the possibility that constraints due to control that cannot be grasped in detail are reflected in the parameters.

[0062] If the target location does not exist in either the improvement history 105 or the parameter application priority information 110, a value that minimizes the difference between the parameters that need to be adjusted and the parameters that have been adjusted in the planned timetable is adopted. For example, assume that the constraint equation between the evaluation scenarios in process S401 is obtained as the constraint equation shown in T07i of FIG. 16. The constraint equations are summarized to become the graph shown in FIG. 15. In process S402, it is determined whether the parameter exists in T05 of FIG. 7. This time, #201, #202, and #207 of T07 are the targets, and since the combination of the parameters and the departure and arrival stations does not exist in T05, none of them apply. Therefore, NO is determined in S402, and the process moves to process S404. In process S404, it is determined whether the parameter exists in T04 of FIG. 6. Since the parameters for the stop time and the running time are included in T04, YES is determined in S404. In process S405, a margin time allocation ratio of 4:5 is created for the stopping time and the traveling time. In process S406, the parameter value that gives a ratio of 4:5 on the line segment between points 702 and 703 in Fig. 15 is set as the representative value. This process is executed in a multidimensional space with multiple parameters as axes, and the margin time allocation ratio between the multiple parameters is determined.

[0063] FIG. 12 is a diagram showing an example of an input screen 500 for the operator 98 .

[0064] The input screen 500 includes a planned timetable input section 510, a parameter input section 520, a robustness evaluation scenario input section 530, and a confirmation button 501. The planned timetable input section 510 includes a timetable line display section 511, a planned timetable input section 512, and a planned timetable interval input section 513. Data input to the planned timetable input section 512 is recorded in the planned timetable 107. After the planned timetable is input, the planned timetable is drawn in the line display section 511. The parameter input section 520 includes a station-to-station parameter input section 521 and a station parameter input section 522. Data input to the parameter input section 520 is recorded in the provisional parameters 108. The robustness evaluation scenario input section 530 includes an individual setting 531 and a collective setting 532. The robustness evaluation scenario 109A is input in the individual setting 531 or the collective setting 532. The data entered in the batch setting 532 is expanded for each station, and when recorded in the robustness evaluation scenario 109A, it is converted to the format of T03 in Fig. 5. When the confirm button 550 is operated with all data entered, a data registration event occurs. If the entered data is insufficient, an error message is displayed to the operator 98 indicating the insufficient data, and the operator is prompted to make corrections.

[0065] FIG. 13 is a diagram showing an example of an output screen 600 presented to the worker 98. As shown in FIG.

[0066] The output screen 600 includes a predicted timetable line display section 610, a parameter display section 620, a robustness evaluation scenario selection section 630, a redraw button 640, and a confirm button 650. The parameter display section 620 displays the improvement history 105 (table T05 shown in FIG. 7). The predicted timetable line display section 610 draws the data selected in the robustness evaluation scenario selection section 630. For example, when the second evaluation scenario is selected in the robustness evaluation scenario selection section 630, a delay is drawn as in a line 611 during a train stop at station B #1. The predicted timetable line display section 610 draws a predicted timetable that outputs the result selected in the width drawing in the parameter display section 620. For example, when the second parameter is selected in the parameter display section 620, detailed data 613 of the running time between stations B and C is popped up. This allows the operator 98 to know the basis for the proposed parameters.

[0067] As described above, the train traffic control system 99 according to the embodiment of the present invention includes an input unit 101 that receives inputs of the planned timetable 107, robustness evaluation scenario 109A, evaluation index 109B, equipment data 106, and initial values ​​of parameters, a prediction unit 102 that predicts a timetable according to one or more evaluation scenarios and creates a predicted timetable, and a parameter narrowing unit 103 that compares the planned timetable 107 with the predicted timetable and narrows down parameter values ​​that satisfy the evaluation index, and predicts a train timetable using the narrowed down parameters and outputs signals to control track equipment according to the predicted train timetable. Therefore, even in a situation where the operator 98 is not familiar with the detailed operation of the train traffic control system 99 or in a situation where detailed data on the control system is not available, plausible parameters can be created from candidates for parameter values ​​with a degree of freedom. This allows the train traffic control system 99 to be released early and changes in operation mode and equipment to be quickly followed, making it possible to facilitate traffic control operations.

[0068] Furthermore, the robustness evaluation scenario 109A includes the delay occurrence point and the delay time, and the evaluation index 109B includes at least one of the delay recovery point and the total delay time, so that parameters can be created without trial and error, reducing the burden on the operator 98.

[0069] In addition, the parameter narrowing unit 103 sequentially executes a procedure of narrowing down parameter values ​​to create a first parameter as a first evaluation index with a total delay time of 0 in a first evaluation scenario in which no delayed trains are defined, and a means of narrowing down parameter values ​​to create a second parameter as one or more second evaluation indexes with delay recovery points in one or more second evaluation scenarios in which any delayed train, any delay occurrence point, and any delay time are defined. This makes it possible to efficiently narrow down the parameters to be changed by determining which ones to change, and shortens the time required to propose parameters.

[0070] Furthermore, the parameter narrowing unit 103 has a parameter value candidate creation unit 103A, a constraint equation calculation unit 103B, and a parameter value selection unit 103C, and for each evaluation scenario, the parameter value candidate creation unit 103A creates parameter value candidates, the prediction unit 103 creates a predicted timetable based on the planned timetable 107, robustness evaluation scenario 109A, and the parameter value candidates, the constraint equation calculation unit 103B determines whether the predicted timetable satisfies the evaluation index and calculates the constraint equations which the parameter values ​​satisfy, and the parameter value selection unit 103C selects one parameter value that satisfies all the constraint equations for one or more robustness evaluation scenarios, so that parameter values ​​independent of the operator 98 can be calculated.

[0071] In addition, the parameter value selection unit 103C creates a second parameter by apportioning the delay time using an adjustment amount for the required time from the delay occurrence point of the delayed train specified in the evaluation scenario to the delay recovery point specified in the evaluation index, thereby reducing the possibility of violating control constraints.

[0072] Furthermore, since the parameter value selection unit 103C calculates the proportionate distribution ratio based on the parameter improvement history 105 generated by the execution result, the accuracy of similar parameters can be improved by execution.

[0073] Furthermore, the parameter value selection unit 103C calculates the proportion of the slack time based on the weight of the slack time proportion set for each parameter type, so that the accuracy of the parameter can be improved by reflecting the slack time proportion tendency specific to the parameter.

[0074] In addition, the parameter value candidate creation unit 103C sets small increments for parameter change at points where the linearity becomes a bottleneck in operation, and creates parameter value candidates. This changes the precision of the parameter values ​​between areas where parameters are created precisely and areas where parameters are created roughly, thereby reducing the amount of computer resources and enabling efficient narrowing down of parameter values.

[0075] The present invention is not limited to the above-described embodiments, and includes various modified examples and equivalent configurations within the spirit of the appended claims. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to those including all of the configurations described. Furthermore, a part of the configuration of one embodiment may be replaced with the configuration of another embodiment. Furthermore, the configuration of another embodiment may be added to the configuration of one embodiment. Furthermore, a part of the configuration of each embodiment may be added, deleted, or replaced with another configuration.

[0076] In addition, each of the above-mentioned configurations, functions, processing units, processing means, etc. may be realized in hardware, for example by designing some or all of them as an integrated circuit, or may be realized in software by a processor interpreting and executing a program that realizes each function.

[0077] Information such as programs, tables, and files that realize each function can be stored in a storage device such as a memory, a hard disk, or an SSD (Solid State Drive), or in a recording medium such as an IC card, an SD card, or a DVD.

[0078] In addition, the control lines and information lines shown are those considered necessary for the explanation, and do not necessarily show all the control lines and information lines necessary for implementation. In reality, it can be considered that almost all components are connected to each other. [Explanation of symbols]

[0079] 98 Workers 99 Train Operation Control System 100 Parameter Creation System 101 Input section 102 Prediction Department 103 Parameter Refinement Section 104 Results presentation section 105 Improvement History 106 Facility Data 107 Planned Schedule 108 Provisional parameters 109A Robustness Evaluation Scenarios 109B Evaluation Metrics 110 Parameter application priority information 500 Input screen 600 output screens 700 Graph showing the constraint equation calculation image for the running time between stations B and C and the stop time at station C

Claims

1. A train traffic control system, A computing device that executes a predetermined process and a storage device that can be accessed by the computing device, an input unit for receiving inputs of a planned timetable, an evaluation scenario for the planned timetable, evaluation indexes, equipment data, and initial values ​​of parameters; A prediction unit in which the calculation device predicts a schedule according to one or more of the evaluation scenarios and creates a predicted schedule; the calculation device has a parameter narrowing unit that compares the planned schedule with the forecast schedule and narrows down parameter values ​​that satisfy the evaluation index; The train traffic control system is characterized in that it predicts a train schedule using the narrowed-down parameters, and outputs a signal to control track equipment in accordance with the predicted train schedule.

2. The train traffic management system according to claim 1, The evaluation scenario includes a delay occurrence point and a delay time, A train operation management system characterized in that the evaluation index includes at least one of a delay recovery point and a total delay time.

3. The train traffic management system according to claim 1, The parameter narrowing unit In a first evaluation scenario in which no delayed trains are determined, the parameter values ​​are narrowed down to create a first parameter as a first evaluation index in which the total delay time is zero; A train operation management system characterized by narrowing down the parameter values ​​and creating a second parameter in one or more second evaluation scenarios in which any delayed train, any delay occurrence point, and any delay time are defined, using a delay recovery point as one or more second evaluation indexes.

4. The train traffic management system according to claim 1, the parameter narrowing down unit includes a parameter value candidate generating unit, a constraint equation calculating unit, and a parameter value selecting unit; For each of the evaluation scenarios, the parameter value candidate creation unit creates parameter value candidates; the prediction unit creates a predicted schedule based on the planned schedule, the evaluation scenario, and the parameter value candidates; the constraint equation calculation unit determines whether the predicted schedule satisfies the evaluation index, and calculates a constraint equation that is satisfied by parameter values; A train traffic control system characterized in that the parameter value selection unit selects one parameter value that satisfies all of the constraint equations for one or more of the evaluation scenarios.

5. The train traffic management system according to claim 4, A train operation management system characterized in that the parameter value selection unit creates a second parameter by apportioning the delay time based on an adjustment amount for the time required from the delay occurrence point of the delayed train specified in the evaluation scenario to the delay recovery point specified in the evaluation index.

6. The train traffic management system according to claim 5, A train operation management system characterized in that the parameter value selection unit calculates the allocation ratio based on a parameter improvement history generated by the execution result.

7. The train traffic management system according to claim 5, A train traffic control system, characterized in that the parameter value selection unit calculates the proportionate ratio based on the weight of the allocation of the leeway time set for each type of parameter.

8. The train traffic management system according to claim 4, A train operation management system, characterized in that the parameter value candidate creation unit sets small increments for parameter change at points where the linearity becomes a bottleneck in operation, and creates parameter value candidates.

9. A parameter creation system, comprising: A computing device that executes a predetermined process and a storage device that can be accessed by the computing device, an input unit for receiving inputs of a planned timetable, an evaluation scenario for the planned timetable, evaluation indexes, equipment data, and initial values ​​of parameters; A prediction unit in which the calculation device predicts a schedule according to one or more of the evaluation scenarios and creates a predicted schedule; A parameter creation system characterized in that the calculation device has a parameter narrowing unit that compares the planned schedule with the forecast schedule and narrows down parameter values ​​that satisfy the evaluation index.

10. A parameter creation method executed by a parameter creation system, comprising: The parameter creation system includes a calculation device that executes a predetermined process and a storage device that is accessible by the calculation device, The parameter creation method includes: an input step in which the calculation device receives input of a planned timetable, an evaluation scenario for the planned timetable, evaluation indexes, equipment data, and initial values ​​of parameters; A prediction step in which the calculation device predicts a schedule according to one or more of the evaluation scenarios and creates a predicted schedule; The parameter creation method further comprises a parameter narrowing step in which the calculation device compares the planned schedule with the forecast schedule and narrows down parameter values ​​that satisfy the evaluation index.

Images