Comprehensive high-speed rail late situation prediction deduction system and method based on multi-information cooperation

Abstract

The invention provides a multi-information collaborative comprehensive high-speed rail late situation information deduction method and system. The system integrates a train running process simulation model, a delay information prediction model, a train running diagram deduction model and the like, comprehensive and detailed train delay deduction results are obtained after data of all the models are comprehensively analyzed and processed, and the overall train delay condition is visually displayed. According to the comprehensive high-speed rail late situation information deduction system, deduction of interference events by the comprehensive train operation simulation model, historical train operation data, train operation constraints and other information are obtained, and a more comprehensive late analysis result is formed; the comprehensive train delay situation visual display of the train operation situation, the train total delay information and the train future operation plan under the real-time interference event is realized, richer and clearer decision information is provided for dispatchers, the dispatchers can better cope with delay adjustment under sudden operation interference, and a more scientific and reasonable dispatching scheme is formulated.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of high-speed rail late situation prediction and deduction, and relates to a comprehensive high-speed rail late situation prediction and deduction system based on multi-information cooperation and a method thereof. BACKGROUND

[0002] With the continuous increase of train speed and passenger demand, the density of railway operation is increasing, the buffer time of the line is continuously shortened, and the emergency disposal time of the train is reduced, which requires a more intelligent railway train dispatching command system to improve decision-making efficiency.

[0003] Possible equipment failures and adverse weather during high-speed rail operation may affect the on-time operation of the train, and the dispatcher needs to develop adjustment strategies based on the impact of random disturbances. How to quickly provide comprehensive and integrated train late prediction information for real-time disturbance events is crucial to the decision-making process of train dispatch adjustment. Current train late prediction research mainly focuses on theoretical research of single models, and there is a lack of research on how to integrate data from various deduction models for comprehensive analysis and deduction of late situation after real-time running disturbance events occur in the actual application process. Therefore, the present application proposes a comprehensive high-speed rail late situation prediction and deduction system based on multi-information cooperation, which integrates train operation simulation, neural network fitting and running chart deduction analysis modules for integrated data fusion processing and analysis to conduct comprehensive late deduction analysis and form a more comprehensive train late prediction information display. This allows the dispatcher to more clearly and intuitively understand the train late development after the disturbance event occurs to make more scientific and reasonable decisions. SUMMARY

[0004] To solve the defects in the prior art, the present application discloses a comprehensive high-speed rail late situation prediction and deduction method based on multi-information cooperation, and the technical scheme is as follows: Step S100: input running disturbance event information, train operation history information and train operation diagram, and process them;

[0005] Step S200: build a comprehensive train late situation prediction model that integrates running simulation module, late prediction module and running chart deduction module;

[0006] Step S300: use the three modules in the comprehensive train late situation prediction model to process the input information, output running curve, late prediction result and running chart deduction data;

[0007] Step S400: fuse and analyze the outputs of the model to obtain comprehensive train late situation information output and perform visual display.

[0008] The application also discloses a comprehensive high-speed rail late-situation prediction and deduction system based on multi-information cooperation.

[0009] The input module inputs running interference event information, train running history information and a train running diagram;

[0010] The comprehensive train late-situation prediction model module is constructed, and a comprehensive train late-situation prediction model is constructed by integrating the running process calculation module, the late-situation prediction module and the running diagram deduction module;

[0011] The data processing module processes the input information by using the three modules in the late-situation prediction model;

[0012] The visual display module fuses and analyzes each output obtained by the model to obtain comprehensive train late-situation information output and performs visual display.

[0013] The application discloses a nonvolatile storage medium, characterized in that the nonvolatile storage medium comprises a stored program, wherein the program controls a device where the nonvolatile storage medium is located to execute the method when the program is running.

[0014] The application also discloses a terminal device for comprehensive high-speed rail late-situation prediction and deduction based on multi-information cooperation, characterized in that the terminal device comprises a processor, a memory, a communication interface and a bus; the processor, the memory and the communication interface are connected through the bus and complete communication among each other; the memory stores executable program codes; the processor runs programs corresponding to the executable program codes by reading the executable program codes stored in the memory, so as to execute the method.

[0015] Further, the step S200 comprises:

[0016] The step S210 comprises: according to the input train running simulation model, simulating the running of the train under the interference according to the parameters of the train, the traction and braking characteristics and the driving strategy.

[0017] The step S220 comprises: constructing a train late-situation prediction model, learning the feature information related to the late-situation in the historical running data of the train by using a neural network model, fitting the relationship between the late-situation of the target station and the historical running features by using the neural network, and thus predicting the train late-situation.

[0018] The step S230 comprises: constructing a train running diagram deduction model, deducing the influence of the current train late-situation on the subsequent trains according to the predicted late-situation information and the train running constraints, and thus obtaining the overall train running diagram prediction under the interference.

[0019] Further, the step S300 comprises:

[0020] Step S310: input the interference event information into the train simulation model, and obtain the running curve and running time of the train under the interference.

[0021] Step S320: input the actual historical running information of the train and the simulation running time of the train under the interference into the train delay prediction model, and predict the delay time of the train at the future station under the interference.

[0022] Step S330: combine the train operation schedule, the simulation running information of the train, and deduce the train affected by the interference event, and deduce the range of the current train delay propagation according to the predicted delay event obtained by the delay prediction model and the train operation constraint, obtain the overall train delay situation, and draw the prediction situation of the future operation diagram.

[0023] Further, the step S400 comprises:

[0024] Step S410: display the running process information of the train under the interference, including the simulation running curve of the train, the running time of the train, and the delay time of the train under the interference.

[0025] Step S420: combine the future station delay prediction result obtained by the train delay prediction model and the train operation constraint, and output the overall affected train and the running delay information of each station of the train.

[0026] Step S430: obtain the real-time updated future train operation diagram according to the overall running prediction delay information, and display the future train operation diagram.

[0027] Beneficial effects

[0028] The present application realizes the comprehensive train delay situation intuitive display of the train running situation under the real-time interference event, the overall train delay information, and the future train operation plan by constructing the train running simulation model, the train delay prediction model, and the train operation diagram deduction model for the multi-model information collaborative processing, so as to guarantee the dispatcher to make scientific and rapid scheduling decision under the interference situation with more comprehensive information. BRIEF DESCRIPTION OF DRAWINGS

[0029] Figure 1 is a multi-information collaborative comprehensive high-speed rail delay situation prediction and deduction system structure diagram provided by the present application;

[0030] Figure 2 is a multi-information collaborative comprehensive high-speed rail delay situation prediction and deduction system data flow diagram provided by the present application.

[0031] Figure 3 is a multi-information collaborative comprehensive high-speed rail delay situation information deduction system visual interface provided by the present application;

[0032] Figure 4 This invention provides a comprehensive high-speed rail delay situation information deduction system with multi-information collaboration, which displays train simulation operation information.

[0033] Figure 5 This is the result of the operation diagram simulation of a comprehensive high-speed rail delay situation information simulation system with multi-information collaboration provided by the present invention. Detailed Implementation

[0034] This invention proposes a comprehensive high-speed rail delay situation prediction and simulation system based on multi-information collaboration. The overall structure of the system is as follows: Figure 1 As shown, by constructing a train operation simulation model, a train delay prediction model, and a train timetable deduction model, information from multiple models is processed collaboratively to obtain an overall train delay situation deduction. This enables a comprehensive and intuitive display of the train delay situation under real-time interference events, the overall train delay information, and the future train operation plan. This provides dispatchers with richer and more comprehensive information to make scientific and rapid dispatching decisions under interference conditions.

[0035] A comprehensive high-speed rail delay prediction and simulation system based on multi-information collaboration includes the following functional modules:

[0036] Input module: Inputs operational interference event information, train operation history information, and train timetable;

[0037] Module for constructing a comprehensive train delay situation prediction model: Constructing a comprehensive train delay situation prediction model that integrates operation process calculation, delay information prediction, and timetable deduction modules;

[0038] Data processing module: This module uses three modules from the late arrival situation prediction model to process the input information.

[0039] Visualization module: It integrates and analyzes the various outputs obtained from the model to obtain comprehensive train delay situation information and displays it visually.

[0040] Based on this comprehensive high-speed rail delay situation prediction and simulation system with multi-information collaboration, this invention also discloses a comprehensive high-speed rail delay situation prediction and simulation method with multi-information collaboration, which specifically includes the following steps:

[0041] Step S100: Input the operation interference event information, train operation history information and train operation diagram.

[0042] Step S110: Determine the origin and destination of the line, collect historical information of trains, and select relevant trains with high frequency of delays and stations with a large number of passenger operations as objects for delay prediction based on the delay statistics.

[0043] Step S120: Determine the characteristic information related to the delay, including the train's planned arrival and departure times at each station, actual arrival and departure times, delay times of adjacent trains, weather conditions, and other information.

[0044] Step S200: Construct a comprehensive train delay situation prediction model that integrates three modules: operation process calculation, delay information prediction, and operation diagram simulation.

[0045] Step S210: Construct a train operation simulation model, and simulate the train's operation under disturbance based on the train's parameters, traction and braking characteristics, and driving strategy.

[0046] The simulation model consists of a train parameter interface, a track information interface, an operating environment simulation, and train operation status calculations. The functions of each component are as follows:

[0047] (1) Train parameter interface: This interface obtains parameters such as the weight, length, maximum acceleration, and maximum speed of the target train to construct the dynamic model of the train.

[0048] (2) Line information interface: This interface mainly obtains information such as the gradient, curvature of curves, location of phase separation zones and length of each block section at various locations on the line, in order to simulate the train operation process.

[0049] (3) Operation environment simulation: This unit mainly constructs the operation environment of the train during operation, including the location of the station, the operation type of the station and the temporary speed limit information of the train section. The temporary speed limit information includes the start and end points of the speed limit, as well as the start and end times of the speed limit.

[0050] (4) Train operation status calculation: This unit mainly constructs a train dynamics model based on the train and line parameter information and operating environment obtained from various interfaces, performs simulation of the train's operation process under the set interference environment, and outputs the train's running time and the delay time caused by the interference event. The specific calculation of the train's running time and delay time is shown in Equation (1) and Equation (2):

[0051] 1) Calculation of running time:

[0052] The running time is calculated using the "distance-step" concept, which involves taking a small distance as the step size and assuming that the net force on the train is constant within this step size. Based on this, the train's acceleration, speed, and travel time are calculated. The total running time of the train is obtained by adding the travel times obtained from multiple step sizes. The specific calculations are shown in formulas (1) to (6). (1)

[0053] In equation (1), and The train is at its position and The acceleration at that point, in m / s² 2 m represents the train's mass in kg; k is the slewing coefficient, indicating the effect of horizontal deviation on acceleration during train operation, with a value ranging from 1.0 to 1.2, used to correct for train acceleration when operating on curves. The maximum permissible acceleration of a train is expressed in m / s². 2 ; The maximum permissible impact rate for the train, expressed in m / s. 3 ; For the train at the previous distance interval The runtime is measured in seconds. For the train in position The net force at a given location, expressed in N, is calculated using the following formula: (2)

[0054] In equation (2), , , , These are the traction force (calculated based on the train traction characteristic curve), braking force (calculated based on braking system parameters), basic resistance, and gradient resistance experienced by the train at position i+1, respectively. and It depends on the operating conditions of the train. , The train is operating under maximum traction conditions; when , The train is under maximum braking conditions. , At that time, the train was in coasting mode; when and Take a certain constant such that At that time, the train was in cruise mode. (3)

[0055] In equation (3), and The train is at its position and The velocity at that location is expressed in m / s. For the train in position The speed limit value at that location, in m / s.

[0056] (4)

[0057] In equation (4), The train's arrival location At that moment, The train's arrival location The time is expressed in seconds (s). and The train is at its position and The velocity at that location is expressed in m / s. For the train in position The acceleration at that point is expressed in m / s².

[0058] (5)

[0059] In equation (5), It is the total travel time of the train within the current section, that is, the total distance traveled by the train within the current section. The sum of internal running times.

[0060] 2) Calculation of delay time: (6)

[0061] In equation (6), It is the total travel time of the train within the current section, that is, the actual total travel time of the train within the current section. Minimum travel time between train sections The difference, the minimum running time of the train. It was calculated under undisturbed conditions.

[0062] Step S220: Construct a train delay prediction model. Use a neural network model (such as LSTM) to learn the temporal features in historical operation data. Through the structure of input layer, hidden layer (128 nodes), and output layer (linear activation function), train the model with mean squared error as the loss function to fit the relationship between the delay of the target station and historical features. Use the neural network model to learn the feature information related to delay in the historical operation data of trains. Fit the relationship between the delay of the target station and historical operation features through the neural network to predict train delays.

[0063] The main units of the train delay prediction model include a historical operation information interface module, a delay feature processing module, a neural network prediction module, and a delay prediction output module.

[0064] (1) Operation Information Interface Module: This module mainly obtains the actual arrival time, actual departure time, delay time, and operation type of the target train and the preceding train at historical stations. At the same time, it receives the delay time information generated under interference events obtained from the train operation simulation model, providing data support for the delay prediction of the target train at the next station.

[0065] (2) Late arrival feature processing module: This module mainly processes the acquired historical information, filters out erroneous information, selects feature information for late arrival prediction, and processes the feature information into the corresponding data structure according to the requirements of neural network input.

[0066] (3) Neural Network Prediction Module: This module mainly constructs a neural network model for predicting train delays. It can identify features related to delays in train operation information, capture the temporal relationship in train operation information, and predict the train's delay time at the next station.

[0067] Step S230: Construct a train timetable prediction model. Based on the predicted delay information and train operation constraints, predict the impact of the current train delay on subsequent trains, thereby obtaining the overall train timetable prediction under interference conditions.

[0068] The main units of the real-time train timetable simulation model include the actual planned timetable interface module, the future timetable prediction module, and the train delay status display module.

[0069] (1) Actual planned operation diagram interface module: This module is mainly used to transmit the actual planned operation diagram information of the train, providing a basis for real-time updates of the future train operation diagram based on the train's delay situation.

[0070] (2) Train delay situation information receiving module: This module mainly receives train delay prediction situation information, providing conditions for future timetable prediction and overall analysis.

[0071] (3) Train operation condition judgment module: This module mainly analyzes whether the trains fail to meet the relevant operation conditions due to delays, thereby determining the range of delay propagation. The relevant operation constraints involved are shown in equations (7) to (8).

[0072] 1) Arrival time constraint: (7)

[0073] This constraint ensures that the train's arrival time is no earlier than the sum of the scheduled arrival time and the delay time.

[0074] 2) Departure time constraints: (8)

[0075] This constraint ensures that the train's departure time is no earlier than the scheduled departure time.

[0076] 3) Arrival time interval constraint: (9)

[0077] This constraint ensures that the arrival time interval between any two trains is not less than the minimum safe interval.

[0078] 4) Departure time interval constraint: (10)

[0079] This constraint ensures that the departure time interval between any two trains is not less than the minimum safe interval.

[0080] (4) Future train schedule prediction module: This module mainly combines the actual planned train schedule, train delay information at future stations, and train operation conditions to deduce the overall impact on trains in order to predict future train schedules.

[0081] Step S300: Use the three modules in the late arrival situation prediction model to process the input information.

[0082] Step S310: Input the interference event information into the train simulation model, including the train's running process curve and running time under interference conditions.

[0083] Step S320: Input the actual historical train operation information and the simulated train operation time under interference conditions into the train delay prediction model to predict the delay time at future stations under train interference scenarios.

[0084] Step S330: Combine the train operation plan and train simulation operation information to deduce the trains affected by the interference event, and based on the predicted delay events obtained from the delay prediction model and the train operation constraints, deduce the current train delay propagation range, obtain the overall train delay situation, and draw the future operation diagram prediction situation.

[0085] Step S400: Perform fusion analysis on the various outputs obtained from the model to obtain comprehensive train delay situation information and display it visually.

[0086] Step S410: Display the progress of train operation information under interference, including the train's simulated operation curve, train operation time, and the delay time caused by the interference.

[0087] Step S420: Combine the future station delay prediction results obtained from the train delay prediction model with the train operation constraints to output the overall affected trains and their respective station operation delay information.

[0088] Step S430: Based on the overall operational delay forecast information, the future train operation map is updated in real time and displayed intuitively.

[0089] Example

[0090] This embodiment exemplifies the specific process and results of performing delay situation simulation analysis using the system provided by this invention. The specific design steps of the system are as follows:

[0091] Step S100: Design a comprehensive high-speed rail delay situation information inference system with multi-information collaboration. Data flow is as follows: Figure 2 As shown.

[0092] according to Figure 2 The external data required for the high-speed rail train delay situation visualization software includes the actual operation plan of the CTC system, actual train operation data, track conditions, train parameters, and interference scenario information. The actual operation plan of the CTC system is connected to the delay situation prediction system via a data interface to simulate the propagation of delays between trains, resulting in a projected display of the future timetable. The actual train operation data, after data processing, extracts delay-related input features to input into the delay prediction neural network model. Track conditions, train parameters, and interference scenarios are used to construct a train operation simulation model to obtain information on delays caused by operational interference. The actual delay data and delay information caused by operational interference are fused and input into the high-speed rail delay situation prediction system according to a specified format. The system's built-in delay prediction algorithm predicts train delays and performs timetable analysis based on train operation constraints. The resulting operational situation information, delay prediction results, and future timetable are then visualized and output.

[0093] Step S200: Design a visualization interface for a comprehensive high-speed rail delay situation information simulation system that integrates multiple information collaborations, such as... Figure 3 As shown.

[0094] according to Figure 3 A comprehensive high-speed rail delay situation information simulation system with multi-information collaboration features a visual interface consisting of a train section parameter setting panel, a train speed limit information setting panel, a train timetable information setting panel, a train operation process curve calculation and display panel, and a dynamic train timetable display panel. The main functions of each part are as follows:

[0095] (1) Train section parameter setting panel, used to set information such as starting point, total length of section, maximum speed limit, and station speed limit;

[0096] (2) Train speed limit information setting panel, used to set the number of speed limit sections, the start and end points of each speed limit section and the speed limit value.

[0097] (3) Train timetable information setting panel, used to set the date of the train timetable to be retrieved, the time range of the timetable to be displayed, the up and down selection, and the current time;

[0098] (4) Train operation process curve calculation and display panel, used to display the VT diagram, ST diagram and VS diagram of the train operation process, and calculate the initial delay information of each station generated by the slow train under the speed limit.

[0099] (5) The dynamic display panel of the train timetable is used to show the impact of the speed limit conditions set on the overall train operation, including the train numbers that will be affected by the speed limit, the delay information of each station affected by the speed limit, and the predicted train timetable after the impact.

[0100] Step S300: Select the intercity route from Beijing to Tianjin, and use the high-speed rail situation information simulation system to conduct a high-speed rail delay situation simulation analysis. Specific results are as follows: Figure 4 As shown.

[0101] Step S310: Input the starting position, ending position, maximum speed limit, station speed limit, and minimum interval time of the line through the train section parameter setting panel. The starting position is 0, the ending position is 118100m, the initial speed limit is 350km / h, the station speed limit is 80km / h, and the minimum interval time is 3min.

[0102] Step S320: Input and set the information of the speed limit section through the train section parameter setting panel. First, input the number of speed limit sections "1", and click "Confirm". After clicking "Confirm", the system will pop up a corresponding pop-up window based on the number of speed limit sections to further input the speed limit section information. Set the starting position of the speed limit section to 35000m, the ending position to 45000m, and the speed limit value to 120km / h.

[0103] Step S330: Set the date of the train schedule to be retrieved through the train schedule input panel, such as "10-08". Enter the "start time" and "end time" to display the time range of the train schedule. At the same time, select the direction of train operation to be displayed, "up" or "down", and set the current time. The current time is the time when the speed limit is issued. Different times when the speed limit is issued will affect the range of trains affected.

[0104] Step S360: After selecting the different train operation curves to be calculated and plotted, such as "VT," "ST," "VS," "AS," or "AT," click the "Calculate Train Operation Status" button to obtain different train operation curve diagrams. After clicking the "Calculate Train Operation Status" button, a pop-up window will first appear indicating "Save Successful," stating that "Position and running time data have been saved to the file: position_runtime_data_limited.txt." This file records the running time of the trains reaching various positions under the influence of the set speed limit conditions, obtained from simulation calculations. The first column records the specific position in "km," and the second column records the running time corresponding to each position in "s." After clicking the "Confirm" button in the pop-up window, the operation curves will be displayed in the right column of the main interface. Simultaneously, the "Initial Delays Caused by Passing Through Speed ​​Limit Sections" column below will output the initial delay time information caused by the train slowing down upon entering the speed limit section. Specific results are as follows... Figure 4 As shown.

[0105] Step S370: After obtaining the initial delay information of trains affected by the speed-limited section by calculating the train operation status, select the train running direction, and then click the "Display Train Timetable" button to obtain the overall train timetable affected by the speed limit. The specific results are as follows: Figure 5 As shown, the blue section represents the planned train routes, while the red section represents the stations and subsequent routes of trains predicted to be delayed due to speed restrictions, indicating a change in the original plan. The right-hand column displays the train numbers affected by speed restrictions, including trains passing through the speed-restricted section at the current time and trains delayed due to the delay of preceding trains, along with specific predicted delay information for each train at each station.

[0106] In summary, this invention proposes a comprehensive high-speed rail delay situation information simulation system based on multi-information collaboration. This system integrates models such as train operation simulation, delay information prediction, and train timetable simulation. After comprehensive analysis and processing of data from each model, it obtains comprehensive and detailed train delay simulation results and visualizes the overall train delay situation. This comprehensive high-speed rail delay situation information simulation system obtains multiple information, including the simulation of interference events by the comprehensive train operation model, historical train operation data, and train operation constraints, forming a more comprehensive delay analysis result. It provides a comprehensive and intuitive display of the train operation situation under real-time interference events, overall train delay information, and future train operation plans, offering dispatchers richer and clearer decision-making information. This enables them to better respond to delay adjustments under sudden operational interference and formulate more scientific and reasonable dispatching schemes.

[0107] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A comprehensive high-speed rail delay situation prediction and simulation method based on multi-information collaboration, characterized by: Includes the following steps: Step S100: Input the operation interference event information, train operation history information and train operation diagram, and process them; Step S200: Construct a comprehensive train delay situation prediction model that integrates the operation simulation module, the delay prediction module, and the timetable deduction module; Step S300: Use the three modules in the integrated train delay situation prediction model to process the input information and output the running curve, delay prediction results and running diagram simulation data; Step S400: Perform fusion analysis on the various outputs obtained from the model to obtain comprehensive train delay situation information and display it visually.

2. The comprehensive high-speed rail delay prediction and simulation method based on multi-information collaboration as described in claim 1, characterized in that, Step S100 further includes the following: Step S110: Determine the origin and destination of the line, collect historical information of trains, and select relevant trains with high frequency of delays and stations with a large number of passenger operations as objects for delay prediction based on the delay statistics. Step S120: Determine the characteristic information related to the delay, including the train's planned arrival and departure times at each station, actual arrival and departure times, delay times of adjacent trains, weather conditions, and other information.

3. The comprehensive high-speed rail delay prediction and deduction method based on multi-information collaboration according to claim 1, characterized in that, Step S200 further includes the following: Step S210: Construct a train operation simulation model based on the input, and simulate the train's operation under disturbance based on the train's parameters, traction and braking characteristics, and driving strategy; Step S220: Construct a train delay prediction model, use a neural network model to learn the feature information related to delays in the historical operation data of trains, and fit the relationship between the delay of the target station and the historical operation features through the neural network to predict the train delay. Step S230: Construct a train timetable prediction model. Based on the predicted delay information and train operation constraints, predict the impact of the current train delay on subsequent trains, thereby obtaining the overall train timetable prediction under interference conditions.

4. The comprehensive high-speed rail delay situation prediction and deduction method based on multi-information collaboration according to claim 1, characterized in that: Step S300 further includes the following: Step S310: Input the interference event information into the train simulation model, including the train's running process curve and running time under interference conditions; Step S320: Input the actual historical train operation information and the simulated train operation time under interference conditions into the train delay prediction model to predict the delay time at future stations under train interference scenarios. Step S330: Combine the train operation plan and train simulation operation information to deduce the trains affected by the interference event, and based on the predicted delay events obtained from the delay prediction model and the train operation constraints, deduce the current train delay propagation range, obtain the overall train delay situation, and draw the future operation diagram prediction situation.

5. The comprehensive high-speed rail delay situation prediction and deduction method based on multi-information collaboration according to claim 1, characterized in that: Step S400 further includes the following: Step S410: Display the progress of train operation information under interference, including the train's simulated operation curve, train operation time, and the delay time caused by the interference. Step S420: Combine the future station delay prediction results obtained from the train delay prediction model with the train operation constraints to output the overall affected trains and their respective station operation delay information; Step S430: Based on the overall operational delay forecast information, the future train operation map is updated in real time and displayed intuitively.

6. The comprehensive high-speed rail delay situation prediction and deduction method based on multi-information collaboration according to claim 3, characterized in that: Step S210 further includes the following: The simulation model consists of train parameter interface, track information interface, operating environment simulation, and train operating status calculation: (1) Train parameter interface: This interface obtains the target train's weight, length, maximum acceleration, and maximum speed parameters to construct the train's dynamic model; (2) Line information interface: This interface mainly obtains information on the gradient, curvature of curves, location of phase separation zones and length of each block section at various locations on the line in order to simulate the train operation process. (3) Operation environment simulation: This unit mainly constructs the operation environment of the train during operation, including the location of the station, the operation type of the station and the temporary speed limit information of the train section. The temporary speed limit information includes the start and end points of the speed limit, as well as the start and end times of the speed limit. (4) Train operation status calculation: This unit mainly constructs a train dynamics model based on the train and line parameter information and operating environment obtained from various interfaces, performs simulation of the train operation process under the set interference environment, and outputs the train running time and the delay time caused by the interference event; the specific calculation of the train running time and delay time is shown in Equation (1) and Equation (2): 1) Running time calculation: The running time is calculated by taking a small distance as a step size, within which the net force on the train is assumed to be constant. Based on this, the train's acceleration, speed, and travel time are calculated. The total running time of the train is obtained by adding the travel times obtained from multiple step sizes. The specific calculations are shown in formulas (1) to (6): （1） In equation (1), and The train is at its position and The acceleration at that point, in m / s² 2 ; m is the train mass in kg; k is the slewing coefficient (an acceleration correction factor caused by track curvature during train operation, usually taken as 1.0-1.2), indicating the effect of horizontal deviation on acceleration during train operation. The maximum permissible acceleration of a train is expressed in m / s². 2 ; The maximum permissible impact rate for the train, expressed in m / s. 3 ; For the train at the previous distance interval The runtime, in seconds; For the train in position The net force at a given location, expressed in N, is calculated using the following formula: （2） In equation (2), , , , These are the traction force, braking force (calculated based on the train's traction / braking characteristic curve), basic resistance, and gradient resistance experienced by the train at position i+1, respectively. and It depends on the operating conditions of the train. , The train is operating under maximum traction conditions; when , The train is under maximum braking conditions. , At that time, the train was in coasting mode; when and Take a certain constant such that At that time, the train was in cruise control mode; （3） In equation (3), and The train is at its position and The velocity at that location is expressed in m / s. For the train in position The speed limit value at the location (dynamically obtained from the route database), in m / s; （4） In equation (4), The train's arrival location At that moment, The train's arrival location The time is expressed in seconds (s). and The train is at its position and The velocity at that location is expressed in m / s. For the train in position The acceleration at that point, expressed in m / s². （5） In equation (5), It is the total travel time of the train within the current section, that is, the total distance traveled by the train within the current section. The sum of internal running times; 2) Calculation of delay time: （6） In equation (6), It is the total travel time of the train within the current section, that is, the actual total travel time of the train within the current section. Minimum travel time between train sections The difference, the minimum running time of the train. It was calculated under undisturbed conditions.

7. The comprehensive high-speed rail delay situation prediction and deduction method based on multi-information collaboration according to claim 3, characterized in that: Step S220 further includes the following: constructing a train delay prediction model, using a neural network model to learn the feature information related to delays in the historical operation data of the train, and fitting the relationship between the delay of the target station and the historical operation features through the neural network, thereby predicting train delays; The main units of the train delay prediction model include a historical operation information interface module, a delay feature processing module, a neural network prediction module, and a delay prediction output module. (1) Operation Information Interface Module: This module mainly obtains the actual arrival time, actual departure time, delay time, and operation type of the target train and the preceding train at historical stations. At the same time, it receives the delay time information generated under interference events obtained from the train operation simulation model, providing data support for the delay prediction of the target train at the next station. (2) Late arrival feature processing module: This module mainly processes the acquired historical information, filters out erroneous information, selects feature information for late arrival prediction, and processes the feature information into the corresponding data structure according to the requirements of neural network input; (3) Neural Network Prediction Module: This module mainly constructs a neural network model for predicting train delays. It can identify features related to delays in train operation information, capture the temporal relationship in train operation information, and predict the train's delay time at the next station.

8. The comprehensive high-speed rail delay situation prediction and deduction method based on multi-information collaboration according to claim 3, characterized in that: Step S230 further includes the following: The main units of the real-time train timetable simulation model include the actual planned timetable interface module, the future timetable prediction module, and the train delay status display module. (1) Actual planned operation diagram interface module: This module is mainly used to transmit the actual planned operation diagram information of the train, providing a basis for real-time updating of the future operation diagram of the train in combination with the train delay situation; (2) Train delay situation information receiving module: This module mainly receives train delay prediction situation information, providing conditions for the prediction and overall analysis of future train schedules; (3) Train operation condition judgment module: This module mainly analyzes whether the trains fail to meet the relevant operation conditions due to delays, thereby determining the range of delay propagation. The relevant operation constraints involved are shown in equations (7) to (8): 1) Arrival time constraint: （7） This constraint ensures that the train's arrival time is no earlier than the sum of the scheduled arrival time and the delay time; 2) Departure time constraints: （8） This constraint ensures that the train's departure time is no earlier than the scheduled departure time; 3) Arrival time interval constraint: （9） This constraint ensures that the arrival time interval between any two trains is not less than the minimum safe interval. 4) Departure time interval constraint: （10） This constraint ensures that the departure time interval between any two trains is not less than the minimum safe interval; (4) Future train schedule prediction module: This module mainly combines the actual planned train schedule, the train delay information at future stations, and the train operation conditions to deduce the overall impact on the train in order to predict the future train schedule.

9. A comprehensive high-speed rail delay situation prediction and simulation system based on multi-information collaboration, characterized by: Input module: Inputs operational interference event information, train operation history information, and train timetable; Model building module: Constructs a comprehensive train delay situation prediction model that integrates operation simulation module, delay prediction module and timetable deduction module; Data processing module: Utilizes the three modules in the integrated train delay situation prediction model to process the input information and output the running curve, delay prediction results, and running diagram simulation data; Visualization module: It integrates and analyzes the various outputs obtained from the model to obtain comprehensive train delay situation information and displays it visually.

10. A non-volatile storage medium, characterized in that, The non-volatile storage medium includes a stored program, wherein the program, when executed, controls the device where the non-volatile storage medium is located to perform the method described in any one of claims 1 to 8.

11. A comprehensive high-speed rail delay situation prediction and simulation terminal device based on multi-information collaboration, characterized in that, The terminal device includes: a processor, a memory, a communication interface, and a bus; the processor, the memory, and the communication interface are connected through the bus and communicate with each other; the memory stores executable program code; the processor reads the executable program code stored in the memory to run a program corresponding to the executable program code, so as to perform the method as described in any one of claims 1-9 above.

Images