A method for generating train group simulation data based on three-dimensional fusion

Abstract

This invention discloses a method for generating simulated train group data based on three-dimensional fusion, comprising the following steps: S1, defining relevant information on the simulated scheme, route, track, stations, trains, and passenger flow, binding the relationships between the defined entities, and setting the simulation time step; S2, collecting raw train operation data and constructing a Gaussian process regression module to mine operational patterns; S3, utilizing the "seat reuse" principle, introducing a random function to construct a passenger flow generation module; S4, generating simulated data through time and route spatial dimensions; S5, performing safety assessments and integrating operational data for train group operation; S6, supplementing the simulated passenger flow data with train arrival times in the simulated train group timetable; S7, simulating the operation of the train group based on the three-dimensional data and analyzing the operational results of the scheme. This invention accurately and comprehensively generates simulated train group operation data, laying the foundation for constructing a train group simulation operation system and possessing significant practical application value.

Description

Technical Field

[0001] This invention relates to the field of transportation network technology, and in particular to a method for generating train group simulation data based on three-dimensional fusion. Background Technology

[0002] Although urban rail transit is developing rapidly, the current international situation, industrial revolution, and new urbanization have placed new demands and requirements on its development. Therefore, scientifically and effectively simulating and optimizing train operation scheduling schemes is of great research value. In the development of train group simulation operation systems, the comprehensive and accurate generation of the required simulation data is particularly important and is a prerequisite for achieving effective simulation operation.

[0003] Currently, the commonly used method of generating train simulation operation data through train traction calculations mostly yields ideal operating results under preset operating conditions, and it also has insufficient utilization of real-time perceived train operation data and historical data. Furthermore, most studies primarily focus on calculating operation data, with weak connections between operation data and passenger flow data, and lack a comprehensive design approach for generating train group simulation data. Summary of the Invention

[0004] To address the technical problems existing in the prior art, this invention provides a method for generating simulated train group data based on three-dimensional fusion. Based on defined train parameter information and line operation plans, it collects raw train operation data and uses a Gaussian process regression algorithm to generate simulated train group operation data. Considering the principle of "seat reuse," it uses a random function to construct a passenger flow generation model to calculate the number of passengers boarding and alighting at stations, thereby accurately and comprehensively generating simulated data in three dimensions: time axis, line space axis, and passenger flow. Simultaneously, it fully considers the special characteristics of train group simulation compared to single-train simulation, assessing the operational safety of trains departing sequentially on the same line, and ultimately generating a complete train group timetable with a reasonable scheme.

[0005] This invention employs the following technical solution: a method for generating train group simulation data based on three-dimensional fusion, comprising the following steps:

[0006] S1. Define the relevant information of the simulated scheme, route, track, station, train and passenger flow, bind the relationships between the defined entities, and set the simulation time step;

[0007] S2. Collect raw train operation data and construct a Gaussian process regression module to uncover operational patterns;

[0008] S3. Utilize the principle of "seat reuse" to introduce a random function to construct a passenger flow generation module;

[0009] S4. Generate simulation data through time and spatial dimensions of the route;

[0010] S5. Conduct safety assessments and integrate operational data for train group operations;

[0011] S6. Supplement the simulated passenger flow data to the train arrival times in the simulated train schedule.

[0012] S7. Simulate the operation of the train group using three-dimensional data and analyze the results of the operation.

[0013] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0014] 1. Based on defined train parameter information and line operation plans, this invention uses a Gaussian process regression algorithm to generate simulated train group operation data. Considering the principle of "seat reuse," a passenger flow generation model is constructed to calculate the number of passengers boarding and alighting at stations, accurately and comprehensively generating simulated data in three dimensions: time axis, line space axis, and passenger flow. Furthermore, the safety of trains departing from the same line is assessed, and data for subsequent trains is generated only after the preceding train has been assessed and stored. This eliminates unreasonable plans with potential safety hazards as early as possible, avoids generating simulated data for other trains with unreasonable schedules, and prevents waste. Finally, a complete simulated train group operation timetable is generated for easy retrieval and simulation operation in the future.

[0015] 2. This invention generates all the data for the simulated operation of train groups relatively accurately and comprehensively, laying the foundation for the construction of a train group simulation operation system, facilitating the research on optimizing train group scheduling schemes, and has great practical application value. Attached Figure Description

[0016] Figure 1 This is a flowchart of the method of the present invention;

[0017] Figure 2 This embodiment defines the entity-relationship diagram for each part of the information.

[0018] Figure 3 This is the calculation flowchart in step S3 of this embodiment;

[0019] Figure 4 This is a flowchart of the process of generating train simulation operation data using Gaussian process regression;

[0020] Figure 5 This is a flowchart for security assessment and operational data integration. Detailed Implementation

[0021] The present invention will be further described in detail below with reference to the embodiments and accompanying drawings, but the embodiments of the present invention are not limited thereto.

[0022] Example

[0023] like Figure 1 As shown in the figure, this embodiment presents a method for generating train group simulation data based on three-dimensional fusion, which includes the following steps:

[0024] S1. Define the relevant information of the simulated scheme, route, track, station, train and passenger flow, bind the relationships between the defined entities, and set the simulation time step;

[0025] S2. Collect raw train operation data and construct a Gaussian process regression module to uncover operational patterns;

[0026] S3. Utilize the principle of "seat reuse" to introduce a random function to construct a passenger flow generation module;

[0027] S4. Generate simulation data through time and spatial dimensions of the route;

[0028] S5. Conduct safety assessments and integrate operational data for train group operations;

[0029] S6. Supplement the simulated passenger flow data to the train arrival times in the simulated train schedule.

[0030] S7. Simulate the operation of the train group using three-dimensional data and analyze the results of the operation.

[0031] like Figure 2 As shown, in this embodiment, the definitions of the relevant information in step S1 are as follows:

[0032] The scheme definition includes: scheme number and number of lines;

[0033] The route definition includes: route number, route name, and number of stations;

[0034] The track definition includes: track number and direction of travel;

[0035] The site definition includes: site number, site name, and site latitude and longitude.

[0036] The definition of a train includes: train number, departure time, maximum operating speed, acceleration during acceleration and deceleration, constant speed, number of business class seats and first, second and third class seats, percentage of seats without a seat, and station stop time.

[0037] Passenger flow is defined as follows: passenger flow number, passenger flow time period and corresponding percentage of boarding and alighting tickets, and average ticket redemption rate.

[0038] Furthermore, by setting an appropriate simulation time step, the relationships between entities such as defined schemes and routes are bound together, that is, the routes, tracks, stations, and trains included in each defined scheme are determined.

[0039] Specifically, in this embodiment, the specific process of step S2 is as follows:

[0040] S21. Construct a Gaussian process regression module, using sensors to collect train line spatial dimension operation data at each time step and store it as the module's training dataset, including train constant speed, maximum speed, starting acceleration, inter-station distance and inter-station travel time.

[0041] S22. Using constant speed, maximum speed, starting acceleration, inter-station distance, and inter-station travel time as inputs, determine the kernel function and hyperparameters, and use the Gaussian process regression algorithm to mine the training data to obtain the operating pattern of a single train, and generate the corresponding travel distance of the train at each time step during the inter-station simulation.

[0042] Specifically, in this embodiment, the specific process of step S3 is as follows:

[0043] S31. Based on the passenger capacity of each train, the percentage of boarding tickets, the percentage of alighting tickets, and the average ticket redemption rate corresponding to the operating time period when the train arrives at each station, the benchmark number of passengers boarding at the station is calculated as the product of the train's passenger capacity, the percentage of boarding tickets at that station during that time period, and the average ticket redemption rate.

[0044] S32. Utilizing the "seat reuse" principle, empty seats can be allocated an additional number of tickets to the station to allow more people to board. The newly allocated tickets are converted into additional boarding passengers according to the average ticket redemption rate. The remaining tickets are allocated to the additional allocation of tickets at the next station. Similarly, each station also has tickets that were not converted into additional boarding passengers at the previous station, which need to be combined with the additional allocation of tickets at that station. Finally, the number of passengers boarding the train at the station is calculated as the sum of the base number of passengers boarding at the station, the additional number of passengers boarding, and the passenger flow fluctuation range. The number of passengers disembarking is the product of the number of passengers on the train and the proportion of passengers disembarking.

[0045] S33. Calculate the number of passengers boarding and alighting at each station using recursion. The calculation process is as follows: Figure 3 As shown, where i represents the number of trains, j represents the number of time periods, k represents the number of stations, and P ijk 上 T ijk Q ijk R ijk This represents the number of passengers boarding the i-th train at station k during time period j, the number of passengers on board, the number of additional passengers boarding, and the ticket amount that could not be converted into additional passengers.

[0046] Specifically, in this embodiment, step S4 generates simulated operation data for each train in terms of time and line space dimensions using a Gaussian process regression algorithm. For previously generated simulated data using the Gaussian process regression algorithm, the data is named and stored in the Gaussian process regression operation database using the train's number and the names of the two stations between them. This data is then directly retrieved when simulated data for the same train between the same stations needs to be generated again, avoiding waste caused by repeated calculations. Figure 4 As shown, the specific process is as follows:

[0047] S41. Set the station number n=1, retrieve the train number and the names of the nth and n+1th stations from the database. For the station between which simulated operation data is to be generated, check if the simulation data previously generated for the train between the stations exists in the module's operation database. If it does, retrieve it directly; otherwise, check if the corresponding raw data is stored in the training database. If raw data exists, input the corresponding constant speed, maximum speed, starting acceleration, station distance, and travel time, and call the Gaussian process regression algorithm to generate simulated operation data between the stations. Mark the data and store it in the operation database. If raw data does not exist, ask the user to provide the raw data of the train between the stations, retrain, and generate simulated data, which is then stored in the operation database. With the simulated data, the system calculates the coordinate data of the train at different time steps between the stations, and then accumulates the train's travel time between stations in sequence. Combined with the train's dwell time at the station, the arrival time of the train at the station can be obtained.

[0048] S42. Set n = n + 1, and determine whether the station number exceeds the total number of stations N. If so, the loop ends and the train simulation operation data is generated. Otherwise, continue to generate the operation data between the next station of the train. In this way, the train simulation operation data is generated completely from the time and line space dimensions.

[0049] Specifically, in this embodiment, step S5 uses the train's maximum operating speed v m Train deceleration acceleration a m and safe braking time Calculate the emergency braking distance and safe distance of the train. The safe distance d between this train and other trains during operation 安 The minimum relatively safe departure time interval t for trains traveling in the same direction is determined based on actual needs. 安 Modify this setting as needed; for example Figure 5 As shown, the specific process of step S5 is as follows:

[0050] S51. Sort all defined trains according to their departure time and set the train departure sequence number n = 1;

[0051] S52. Generate the simulated operation data of the nth departing train according to step S3 and fill it into the train group operation timetable of the plan.

[0052] S53. Set n = n + 1, generate simulated operation data for the nth train. If the (n-1)th and nth trains do not travel on the same line, directly fill the data of the nth train into the train group timetable. If the two trains are bound to the same line, then judge the safety of the two trains' operation.

[0053] S54. Determine whether the destination of the nth train is before the starting station of the (n-1)th train, or whether the time interval between the departures of the two trains is greater than or equal to t. 安 If either of these conditions is met, the data of the generated nth train is entered into the train group's timetable; otherwise, during the period from the departure of the nth train to the end of the journey of either train n-1 or n, it is determined whether the distance between the two trains at each time step is greater than or equal to the safe distance d of the nth train. 安 If so, the data of the nth train generated is filled into the train group timetable of the scheme; otherwise, it is determined that the scheme has safety hazards and the user is reminded to redefine the simulation information.

[0054] S55. After completing the safety assessment of the nth train, set n = n + 1. If n is greater than the total number of trains in the plan, then the data of all trains in the plan will pass the assessment and be filled into the timetable. Otherwise, continue to assess the safety of the nth train until all trains have been assessed.

[0055] Specifically, in this embodiment, the specific process of step S6 is as follows:

[0056] S61. Input the arrival time of each train at each station obtained in step S4 into the passenger flow generation module in sequence. Based on the percentage of boarding tickets, the percentage of alighting tickets, the average ticket redemption rate and the passenger capacity of the train in the corresponding time period, generate simulated data of the train passenger flow dimension in step S3, that is, the number of passengers getting on and off the train at the next station, and supplement the corresponding data position in the simulated timetable of the train group.

[0057] S62. The system generates all simulation data for the operation plan from three dimensions: time, route space, and passenger flow.

[0058] Specifically, in this embodiment, the specific process of step S7 is as follows:

[0059] S71. The earliest departure time of the train is taken as the starting point of the overall time axis of the scheme. The time difference between adjacent simulated data of the train is used as the time iteration interval. Each iteration will trigger the trigger function to respond. The trigger function contains the judgment of the departure time of the remaining trains. If the judgment time reaches the departure time of a certain train, a separate time axis timing trigger is created for the train at that time node, and its starting point is the current train departure time. If the judgment result is that the departure time of the train has not yet arrived, the time continues to iterate until the last train arrives at the station and the iteration ends, and the time axis is released.

[0060] S72. After determining the departure time of a train on the overall timeline, a separate timeline corresponding to the currently departing train is created. The private timeline starts with the current train's departure time and ends with the train's arrival time at the last station. The time iteration interval is consistent with the overall timeline, and the iteration of the sub-timelines is synchronized with the overall timeline. In each iteration, the system updates the train's latitude and longitude position, speed, acceleration, and other data on each operation chart, and determines whether it is the train's arrival time. If the result is yes, the passenger flow information on the train is updated; otherwise, the time continues to iterate. After the train arrives at the last station, the system releases the timeline, thereby realizing the simulated operation of the train group.

[0061] S73. Construct a train operation plan evaluation module, where users set evaluation weights and use the average effective occupancy rate of trains, passenger volume, and average passenger capacity of trains as indicators to compare and evaluate the simulation results of each plan.

[0062] S74. After the train dispatching scheme simulation is completed, the system can quickly retrieve historical data from the database and reproduce the data in the form of various charts. By using parameter display and graphic display, the system can simultaneously present the operating status of different trains in the train group at a certain historical moment, and realize the review function.

[0063] The above embodiments are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the above embodiments. Any changes, modifications, substitutions, combinations, or simplifications made without departing from the spirit and principle of the present invention shall be considered equivalent substitutions and shall be included within the protection scope of the present invention.

Claims

1. A method for generating train group simulation data based on three-dimensional fusion, characterized in that, Includes the following steps: S1. Define the relevant information of the simulated scheme, route, track, station, train and passenger flow, bind the relationships between the defined entities, and set the simulation time step; S2. Collect raw train operation data and construct a Gaussian process regression module to uncover operational patterns; S3. Utilize the "seat reuse" principle to introduce a random function to construct a passenger flow generation module; S4. Generate simulation data through time and spatial dimensions of the route; S5. Conduct safety assessments and integrate operational data for train group operations; S6. Supplement the simulated passenger flow data to the train arrival times in the simulated train schedule. S7. Simulate the operation of the train group using three-dimensional data and analyze the operation results of the scheme; The specific process of step S2 is as follows: S21. Construct a Gaussian process regression module, using sensors to collect train line spatial dimension operation data at each time step and store it as the module's training dataset, including train constant speed, maximum speed, starting acceleration, inter-station distance and inter-station travel time. S22. Using constant speed, maximum speed, starting acceleration, inter-station distance, and inter-station travel time as inputs, determine the kernel function and hyperparameters, and use the Gaussian process regression algorithm to mine training data to obtain the single train operation pattern, and generate the corresponding travel distance of the train at each time step during inter-station simulation. The three dimensions are time, route space, and passenger flow.

2. The method for generating train group simulation data based on three-dimensional fusion according to claim 1, characterized in that, The definitions of relevant information in step S1 are as follows: The scheme definition includes: scheme number and number of lines; The route definition includes: route number, route name, and number of stations; The track definition includes: track number and direction of travel; The site definition includes: site number, site name, and site latitude and longitude. The definition of a train includes: train number, departure time, maximum operating speed, acceleration during acceleration and deceleration, constant speed, number of business class seats and first, second and third class seats, percentage of seats without a seat, and station stop time. Passenger flow is defined as follows: passenger flow number, passenger flow time period and corresponding percentage of boarding and alighting tickets, and average ticket redemption rate.

3. The method for generating train group simulation data based on three-dimensional fusion according to claim 1, characterized in that, The specific process of step S3 is as follows: S31. Based on the passenger capacity of each train, the percentage of boarding tickets, the percentage of alighting tickets, and the average ticket redemption rate corresponding to the operating time period when the train arrives at each station, the benchmark number of passengers boarding at the station is calculated as the product of the train's passenger capacity, the percentage of boarding tickets at that station during that time period, and the average ticket redemption rate. S32. Utilizing the "seat reuse" principle, empty seats can be allocated an additional number of tickets to the station to allow more people to board. The newly allocated tickets are converted into additional boarding passengers according to the average ticket redemption rate. The remaining tickets are allocated to the additional allocated tickets of the next station. Each station's additional allocated tickets are combined with the additional allocated tickets of that station. The final calculated number of passengers boarding the train at each station is the sum of the base number of passengers boarding at the station, the additional number of passengers boarding, and the passenger flow fluctuation range. The number of passengers disembarking is the product of the number of passengers on the train and the proportion of passengers disembarking. S33. Calculate the number of passengers getting on and off the train at each station by recursion.

4. The method for generating train group simulation data based on three-dimensional fusion according to claim 1, characterized in that, Step S4 generates simulated operation data for each train in terms of time and track space using the Gaussian process regression algorithm. For previously generated simulated data using the Gaussian process regression algorithm, the data is named and tagged with the train number and the names of the two stations between them, and stored in the Gaussian process regression operation database. This database is directly accessed when simulated data for the same train between the same stations needs to be generated again. The specific process is as follows: S41. Set the station number n=1, retrieve the train number and the names of the nth and n+1th stations from the database. For the station between which simulated operation data is to be generated, check if the simulation data previously generated for the train between the stations exists in the module's operation database. If it does, retrieve it directly; otherwise, check if the corresponding raw data is stored in the training database. If raw data exists, input the corresponding constant speed, maximum speed, starting acceleration, station distance, and travel time, and call the Gaussian process regression algorithm to generate simulated operation data between the stations. Mark the data and store it in the operation database. If raw data does not exist, ask the user to provide the raw data of the train between the stations, retrain, and generate simulated data, which is then stored in the operation database. With the simulated data, the system calculates the coordinate data of the train at different time steps between the stations, and then accumulates the train's travel time between stations in sequence. Combined with the train's dwell time at the station, the arrival time of the train at the station can be obtained. S42. Set n=n+1, check if the station number exceeds the total number of stations N. If so, the loop ends and the train simulation operation data is generated. Otherwise, continue generating the train's operation data for the next station, thus generating complete simulated train operation data from both time and line space dimensions.

5. The method for generating train group simulation data based on three-dimensional fusion according to claim 1, characterized in that, Step S5 uses the train's maximum operating speed Train deceleration and safe braking time Calculate the emergency braking distance and safe distance of the train. = As a safe distance between this train and other trains during operation The minimum relatively safe departure time interval for trains traveling in the same direction should be determined based on actual needs. Modify this setting as needed; the specific process of step S5 is as follows: S51. Sort all defined trains according to their departure time and set the train departure sequence number n=1; S52. Generate the simulated operation data of the nth departing train and fill it into the train group operation timetable of the plan; S53. Set n=n+1, generate simulated operation data for the nth train. If the (n-1)th and nth trains do not travel on the same line, directly fill the data of the nth train into the train group timetable. If the two trains are bound to the same line, then judge the safety of the two trains' operation. S54. Determine whether the destination of the nth train is before the starting station of the (n-1)th train, or whether the time interval between the departures of the two trains is greater than or equal to [the specified value]. If either of these conditions is met, the data of the generated nth train will be filled into the train group's timetable. Otherwise, during the period from the departure of the nth train to the end of the journey of either the (n-1)th or nth train, determine whether the distance between the two trains at each time step is greater than or equal to the safe distance of the nth train. If so, the data of the nth train generated is filled into the train group timetable of the scheme; otherwise, it is determined that the scheme has safety hazards and the user is reminded to redefine the simulation information. S55. After completing the safety assessment of the nth train, set n=n+1. If n is greater than the total number of trains in the plan, then the data of all trains in the plan will pass the assessment and be filled into the timetable. Otherwise, continue to assess the safety of the nth train until all trains have been assessed.

6. The method for generating train group simulation data based on three-dimensional fusion according to claim 1, characterized in that, The specific process of step S6 is as follows: S61. Input the arrival time of each train at each station into the passenger flow generation module in sequence. Based on the percentage of boarding tickets, the percentage of alighting tickets, the average ticket redemption rate and the passenger capacity of the train in the corresponding time period, generate simulated data of the train passenger flow dimension, that is, the number of passengers boarding and alighting at the next station, and supplement the corresponding data position in the simulated timetable of the train group. S62. The system generates all simulation data for the operation plan from three dimensions: time, route space, and passenger flow.

7. The method for generating train group simulation data based on three-dimensional fusion according to claim 1, characterized in that, The specific process of step S7 is as follows: S71. The earliest departure time of the train is taken as the starting point of the overall time axis of the scheme. The time difference between adjacent simulated data of the train is used as the time iteration interval. Each iteration will trigger the trigger function to respond. The trigger function contains the judgment of the departure time of the remaining trains. If the judgment time reaches the departure time of a certain train, a separate time axis timing trigger is created for the train at that time node, and its starting point is the current train departure time. If the judgment result is that the departure time of the train has not yet arrived, the time continues to iterate until the last train arrives at the station and the iteration ends, and the time axis is released. S72. After determining the departure time of a train on the overall timeline, a separate timeline corresponding to the currently departing train is created. The private timeline starts at the current train's departure time and ends at the time the current train arrives at the last station. The time iteration interval is consistent with the overall timeline, and the iteration of the sub-timelines is synchronized with the overall timeline. In each iteration, the system updates the train's latitude and longitude position, speed, and acceleration data on each operation chart, and determines whether it is the train's arrival time. If the result is yes, the passenger flow information on the train is updated; otherwise, the time continues to iterate. After the train arrives at the last station, the system releases the timeline, realizing the simulated operation of the train group. S73. Construct a train operation plan evaluation module, where users set evaluation weights and use the average effective occupancy rate of trains, passenger volume, and average number of passengers carried by trains as indicators to compare and evaluate the simulation results of each plan. S74. After the train dispatching scheme simulation is completed, the system retrieves historical data from the database and reproduces the data in the form of various charts. The system uses parameter display and graphic display to simultaneously present the operating status of different trains in the train group at a certain historical moment, realizing the review function.

Images