A method for adaptive adjustment of train diagram based on automatic coupling and uncoupling of trains

Abstract

The present invention discloses a method for adaptively adjusting an operation diagram based on automatic coupling and disassembly of trains, which relates to the technical field related to rail transit management, and obtains a preset rail operation diagram. Passenger flow prediction is performed for multiple stations in a first preset time zone, and a train coupling and disassembly scheme is fitted based on the prediction results to generate a first coupling and disassembly operation diagram. The first coupling train combination and the first coupling time located at the first coupling position are extracted. Delay prediction is performed on the trains in the first coupling train combination, and the first train combination delay prediction result is generated to perform coupling scheduling fitting, generate the first coupling scheduling fitting result, adjust the first coupling and disassembly operation diagram, and generate a first updated coupling and disassembly operation diagram. The method solves the technical problem that the train dispatching system in the prior art lacks the ability to perform real-time adaptive adjustment on the coupling and disassembly operation diagram when processing coupling and disassembly operations in a complex environment, resulting in low train dispatching efficiency and poor passenger experience.

Description

Technical Field

[0001] The present application relates to the technical field related to rail transit management, and in particular to a method for adaptively adjusting an operation diagram based on automatic coupling and decoupling of trains. Background Art

[0002] The coupling and uncoupling of trains refers to the process of connecting two or more trains together to form a longer train, or splitting a long train into two or more short trains in urban rail transit. With the continuous expansion of the rail transit network and the complexity of the train dispatching system, the coupling and uncoupling of trains has become an important means to improve the efficiency of rail transportation. By coupling and uncoupling trains, the rail transit system can flexibly dispatch train formations according to passenger flow demand in different time periods to meet the travel needs of passengers. However, the current train dispatching system lacks sufficient resilience when dealing with sudden factors such as unstable passenger flow and weather changes. The traditional train coupling and uncoupling operation diagram generation method mainly relies on historical data and preset dispatching rules. It is impossible to dynamically adjust the train formation plan according to real-time passenger flow and delay information during the train operation, resulting in low dispatching efficiency and reduced passenger satisfaction.

[0003] Therefore, in the prior art, when the train dispatching system handles coupling and uncoupling operations in complex environments, it lacks the ability to make real-time adaptive adjustments to the coupling and uncoupling operation diagram, resulting in technical problems such as low train dispatching efficiency and poor passenger experience. Summary of the invention

[0004] This application provides a method for adaptively adjusting the running diagram based on automatic coupling and uncoupling of trains, which solves the technical problem that the train dispatching system in the prior art lacks the ability to adaptively adjust the running diagram of coupling and uncoupling in real time when processing coupling and uncoupling operations in complex environments, resulting in low train dispatching efficiency and poor passenger experience. The application achieves the technical effect of dynamically adjusting the train coupling and uncoupling running diagram in a complex environment and improving the adaptability and operating efficiency of the train dispatching system under complex operating conditions.

[0005] The present application provides a method for adaptively adjusting a train operation diagram based on automatic coupling and uncoupling of trains, the method comprising: obtaining a preset track operation diagram, wherein the preset track operation diagram includes initial operation routes of multiple trains. Performing passenger flow prediction for the initial operation routes of the multiple trains in a first preset time zone, fitting train coupling and uncoupling schemes for the multiple trains based on the prediction results, and generating a first coupling and uncoupling operation diagram. Extracting a first coupling train combination and a first coupling time located at a first coupling position based on the first coupling and uncoupling operation diagram. Taking the first coupling time as a prediction node, performing delay prediction on the trains in the first coupling train combination, and generating a first train combination delay prediction result. Performing coupling and uncoupling scheduling fitting under a delay state based on the first train combination delay prediction result, and generating a first coupling and uncoupling scheduling fitting result. Adjusting the first coupling and uncoupling operation diagram according to the first coupling and uncoupling scheduling fitting result, and generating a first updated coupling and uncoupling operation diagram; and identifying coupling and uncoupling positions according to the first updated coupling and uncoupling operation diagram to perform coupling and uncoupling control of trains.

[0006] In the implementation method, passenger flow prediction is performed for the initial operation routes of the multiple trains in the first preset time zone, and the train coupling and disassembly schemes are fitted for the multiple trains based on the prediction results to generate a first coupling and disassembly operation diagram, including: collecting historical passenger flow data for the initial operation routes of the multiple trains. Based on the historical passenger flow data, multiple passenger flow prediction networks corresponding to the multiple trains are constructed using time series analysis. Passenger flow prediction is performed for the first preset time zone using the multiple passenger flow prediction networks to generate the prediction results, wherein the prediction results include the predicted passenger flow for the initial operation routes of the multiple trains. According to the prediction results, train capacity adaptation fitting is performed to generate the first coupling and disassembly operation diagram. Wherein, the first coupling and disassembly operation diagram includes the time of coupling and disassembly, the location of coupling and disassembly, and the train combination of coupling and disassembly.

[0007] In the implementation, the multiple passenger flow prediction networks are connected to an unstable passenger flow feedback layer, wherein the unstable passenger flow feedback layer is used to optimize the output results of the multiple passenger flow prediction networks according to unstable passenger flow factors. The unstable passenger flow factors are irregular passenger flow influencing factors at time nodes, and the passenger flow influencing samples are collected based on the unstable passenger flow factors to train the unstable passenger flow feedback layer.

[0008] In the implementation, according to the prediction result, train capacity adaptation fitting is performed to generate the first coupling and disassembly operation diagram, including: according to the predicted passenger flow of the initial operation route of the multiple trains, train capacity adaptation analysis is performed to generate train capacity adaptation information of the initial operation route. Based on the train capacity adaptation information, train coupling and disassembly fitting is performed in the first preset time zone to generate the coupling and disassembly time, coupling and disassembly location, and coupling and disassembly train combination, and sequentially connect them to establish the first coupling and disassembly operation diagram.

[0009] In the implementation, the first coupling time is used as a prediction node, and delay prediction is performed on the trains in the first coupled train combination to generate the delay prediction result of the first train combination, including: collecting a historical train delay record data set of the same type of trains in the first coupled train combination, wherein any historical train delay record data includes delayed train operating condition record data and delay time record data. The delayed train operating condition record data and the delay time record data are used as training samples to perform multi-layer decision tree training to generate a multi-layer decision network. The real-time operating conditions of the coupled front train and the coupled rear train in the first coupled train combination are obtained. The real-time train operating conditions are input into the multi-layer decision network to predict the train delay time, and the delay prediction result of the first train combination is generated.

[0010] In the implementation, performing coupling scheduling fitting under the delay state based on the first train combination delay prediction result to generate the first coupling scheduling fitting result includes: extracting the delay time of the coupling front car and the delay time of the coupling rear car in the first train combination delay prediction result. Comparing the delay time of the coupling front car with the delay time of the coupling rear car, determining whether the arrival time deviation between the coupling front car and the coupling rear car is less than or equal to the preset time deviation. If so, adjusting the first coupling time and the corresponding uncoupling time by the delay time to generate the first coupling scheduling fitting result.

[0011] In the implementation, judging whether the arrival time deviation between the front vehicle and the rear vehicle is less than or equal to the preset time deviation further includes: if the arrival time deviation between the front vehicle and the rear vehicle is greater than the preset time deviation, activating the coupling de-marshalling optimization module. Through the coupling de-marshalling optimization module, with the delay time of the front vehicle and the delay time of the rear vehicle being constrained and with the passenger flow of the first coupling position being the goal, the coupling scheme is adjusted for the front vehicle and the rear vehicle, and the first coupling scheduling fitting result is generated.

[0012] In the implementation method, the coupling and uncoupling positions are identified according to the first updated coupling and uncoupling operation diagram to control the coupling and uncoupling of the train, including: according to the first updated coupling and uncoupling operation diagram, the first coupling front car, the first coupling rear car and the corresponding coupling position are extracted, and according to the coupling position, it is judged whether the first coupling front car has reached the front parking area, and whether the first coupling rear car has reached the rear parking area; if so, a coupling instruction is generated, and the first coupling rear car is controlled by the coupling instruction to travel at the first coupling speed toward the first coupling front car until the mechanical coupler completes the collision and the electric coupler is automatically connected.

[0013] In an implementation, the coupling and uncoupling positions are identified according to the first updated coupling and uncoupling operation diagram to control the coupling and uncoupling of the train, including: extracting the first uncoupling train and the corresponding uncoupling position in the first updated coupling and uncoupling operation diagram according to the first updated coupling and uncoupling operation diagram. When the first uncoupling train arrives at the uncoupling position, an uncoupling instruction is generated; and the first uncoupling train is controlled by the uncoupling instruction to perform a mechanical coupler uncoupling operation at the uncoupling position.

[0014] It is intended to obtain a preset track operation diagram through a method for adaptively adjusting an operation diagram based on automatic coupling and decoupling of trains proposed in this application, wherein the preset track operation diagram includes the initial operation routes of multiple trains.

[0015] A passenger flow forecast is performed for the initial operation routes of the plurality of trains in a first preset time zone, and a train coupling and uncoupling scheme is fitted for the plurality of trains based on the forecast results to generate a first coupling and uncoupling operation diagram. A first coupling train combination and a first coupling time located at a first coupling position are extracted based on the first coupling and uncoupling operation diagram. The first coupling and uncoupling time is used as a forecast node, and a delay forecast is performed for the trains in the first coupling train combination to generate a first train combination delay forecast result. A coupling and uncoupling operation diagram is fitted under a delay state based on the first train combination delay forecast result to generate a first coupling and uncoupling scheduling fitting result. The first coupling and uncoupling operation diagram is adjusted according to the first coupling and uncoupling fitting result to generate a first updated coupling and uncoupling operation diagram. The coupling and uncoupling positions are identified according to the first updated coupling and uncoupling operation diagram to control the coupling and uncoupling of the train. The technical problem that the train dispatching system in the prior art lacks the ability to make real-time adaptive adjustments to the coupling and uncoupling operation diagram when processing coupling and uncoupling operations in a complex environment, resulting in low train dispatching efficiency and poor passenger experience is solved. The technical effect of dynamically adjusting the train coupling and uncoupling operation diagram in a complex environment and improving the adaptability and operating efficiency of the train dispatching system under complex operating conditions is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0017] Figure 1 A schematic flow chart of a method for adaptively adjusting a train diagram based on automatic coupling and uncoupling of trains provided in an embodiment of the present application;

[0018] Figure 2 A schematic flow chart of a method for adaptively adjusting a train operation diagram based on automatic coupling and uncoupling of trains provided in an embodiment of the present application for generating a first coupling and uncoupling operation diagram. DETAILED DESCRIPTION

[0019] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0020] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0021] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0022] The present application embodiment provides a method for adaptively adjusting a train diagram based on automatic coupling and uncoupling of trains, such as Figure 1 As shown, the method includes:

[0023] A preset track operation diagram is obtained, wherein the preset track operation diagram includes initial operation routes of multiple trains. Passenger flow prediction is performed for the initial operation routes of the multiple trains in a first preset time zone, and train coupling and disassembly schemes are fitted for the multiple trains based on the prediction results to generate a first coupling and disassembly operation diagram. A first coupling train combination and a first coupling time at a first coupling position are extracted based on the first coupling and disassembly operation diagram.

[0024] Obtain a preset track operation diagram, which includes the geographical location information of multiple stations, station names, operation schedules, and initial operation routes of multiple trains, and the initial operation routes include multiple stations. After obtaining the preset track operation diagram, perform passenger flow prediction for the initial operation route within a first preset time zone, and the first preset time zone is a preset time interval. Based on the prediction results, fit the coupling and uncoupling schemes of the trains to generate a first coupling and uncoupling operation diagram, wherein the first coupling and uncoupling operation diagram includes the coupling and uncoupling time, the coupling and uncoupling positions, and the coupling and uncoupling train combinations. Further, based on the first coupling and uncoupling operation diagram, extract the first coupling train combination and the first coupling time located at the first coupling position.

[0025] like Figure 2 As shown, the method provided in the embodiment of the present application also includes: collecting historical passenger flow data for the initial operating routes of the multiple trains. Based on the historical passenger flow data, multiple passenger flow prediction networks corresponding to the multiple trains are constructed using time series analysis. Passenger flow prediction is performed for the first preset time zone using the multiple passenger flow prediction networks to generate the prediction results, wherein the prediction results include the predicted passenger flow for the initial operating routes of the multiple trains. According to the prediction results, train capacity adaptation fitting is performed to generate the first coupling and disassembly operation diagram. Wherein, the first coupling and disassembly operation diagram includes the time of coupling and disassembly, the location of coupling and disassembly, and the train combination of coupling and disassembly.

[0026] The passenger flow is predicted for the initial operation routes of the plurality of trains in the first preset time zone, and the train coupling and disassembly schemes are fitted for the plurality of trains based on the prediction results to generate the first coupling and disassembly operation diagram, including: collecting historical passenger flow data of the stations for the initial operation routes of the plurality of trains, and the collection time is derived from data records such as historical passenger flow records. After collecting the historical passenger flow data of each station on the initial operation routes of the plurality of trains, a passenger flow prediction network for each initial operation route is constructed through time series analysis. The time series analysis method can identify trends, cycles and random fluctuations from historical data to predict future passenger flow. When constructing the passenger flow prediction network, the historical passenger flow data is preprocessed, and the specific passenger flow data is marked with corresponding date, time, working day or holiday label information. For example, the historical passenger flow data of station A in a certain initial operation route includes hourly passenger flow records for the past year. After data preprocessing, these records are sorted in chronological order to obtain a data set. Further, 80% of the data in the data set is used as a training set, and the remaining 20% ​​is used as a test set to train the long short-term memory network, and the model is tested through the test set to obtain a trained passenger flow prediction network. The multiple passenger flow prediction networks are used to predict the passenger flow of the initial operation routes of multiple trains based on the time, working days or holidays and other information of the first preset time zone, and generate prediction results corresponding to the stations in the initial operation routes, wherein the prediction results include the predicted passenger flow of each station in the initial operation routes of the multiple trains. Further, according to the prediction results, train capacity adaptation fitting is performed to generate the first coupling and uncoupling operation diagram. The first coupling and uncoupling operation diagram includes the time of coupling and uncoupling, the location of coupling and uncoupling, and the train combination of coupling and uncoupling, and the location of coupling and uncoupling is the actual location of the station where coupling and uncoupling are performed.

[0027] The passenger flow prediction network mainly relies on historical passenger flow data and time series analysis. However, in actual operation, unstable passenger flow factors may appear, which cannot be accurately predicted by historical data. To this end, the system introduces an unstable passenger flow feedback layer to capture and process these irregular passenger flow changes and optimize the output of the prediction network. The multiple passenger flow prediction networks are connected to the unstable passenger flow feedback layer, wherein the unstable passenger flow feedback layer is used to optimize the output results of the multiple passenger flow prediction networks according to the unstable passenger flow factors. The unstable passenger flow factors are irregular passenger flow influencing factors at time nodes, that is, the unstable passenger flow factors refer to those passenger flow influencing factors that are random or sudden and cannot be predicted by conventional time series analysis, such as sudden weather changes, temporary large-scale activities, accidents, etc. The unstable passenger flow factors are used to collect passenger flow influencing samples, obtain passenger flow influencing samples corresponding to various types of unstable passenger flow factors, and obtain unstable passenger flow influencing samples. After collecting a predetermined amount of unstable passenger flow influencing samples, a neural network model is used to train the unstable passenger flow feedback layer. The unstable passenger flow impact samples include various unstable passenger flow factors and corresponding passenger flow impact samples. The unstable passenger flow impact samples are used as training data to train the neural network model and obtain the trained unstable passenger flow feedback layer. The unstable passenger flow feedback layer can dynamically adjust the prediction results to ensure the stability and efficiency of train operation in any emergency situation.

[0028] The method provided in the embodiment of the present application further includes: performing train capacity adaptation analysis according to the predicted passenger flow of the initial operation route of the multiple trains, and generating train capacity adaptation information of the initial operation route. Based on the train capacity adaptation information, train coupling and uncoupling fitting is performed in the first preset time zone, and the coupling and uncoupling time, coupling and uncoupling position, and coupling and uncoupling train combination are generated, and sequential connection is performed to establish the first coupling and uncoupling operation diagram.

[0029] According to the prediction results, train capacity adaptation fitting is performed to generate the first coupling and disassembly operation diagram, including: according to the predicted passenger flow of the initial operation routes of multiple trains, train capacity adaptation analysis is performed, and the passenger capacity corresponding to the train model needs to be determined when performing the train capacity adaptation analysis, and the demand quantity and demand time corresponding to the train model that can be coupled and disassembled are obtained in combination with the predicted passenger flow of the initial operation routes of multiple trains, so as to generate the train capacity adaptation information of the multiple stations, and the train capacity adaptation information includes the train model that can be coupled and disassembled and the corresponding demand quantity and demand time, and the demand time corresponds to the train schedule. Based on the train capacity adaptation information, train coupling and disassembly fitting is performed in the first preset time zone, that is, coupling or disassembly of the train in the first preset time zone is performed according to the train capacity adaptation information, and the coupling and disassembly time, that is, the demand time, the coupling and disassembly position, and the coupling and disassembly train combination are generated, and sequentially connected, and the first coupling and disassembly operation diagram is established through a drawing tool.

[0030] Taking the first coupling time as a prediction node, a delay prediction is performed on the trains in the first coupling train combination to generate a first train combination delay prediction result. Based on the first train combination delay prediction result, a coupling scheduling fitting is performed under a delay state to generate a first coupling scheduling fitting result. According to the first coupling scheduling fitting result, the first coupling and uncoupling operation diagram is adjusted to generate a first updated coupling and uncoupling operation diagram; coupling and uncoupling positions are identified according to the first updated coupling and uncoupling operation diagram to perform coupling and uncoupling control of trains.

[0031] Based on the first coupling time as the prediction node, the weather factors at the corresponding positions of each time node in the operation zone starting from the prediction node are obtained to obtain the weather prediction time series information, and the delay prediction of the trains in the first coupling train combination is performed according to the weather prediction time series information to generate the delay prediction result of the first train combination. Further, the coupling scheduling fitting under the delay state is performed based on the delay prediction result of the first train combination, and the first coupling scheduling fitting result is generated to readjust the coupling and uncoupling plan to generate the first coupling scheduling fitting result. Finally, the first coupling and uncoupling operation diagram is adjusted according to the first coupling and uncoupling operation diagram, and the corresponding coupling and uncoupling trains in the first coupling and uncoupling operation diagram are replaced and the coupling and uncoupling train time is updated to generate the first updated coupling and uncoupling operation diagram. According to the first updated coupling and uncoupling operation diagram, the coupling and uncoupling positions are identified to control the coupling and uncoupling of the train. The technical problem that the train dispatching system in the prior art lacks the ability to make real-time adaptive adjustments to the coupling and uncoupling operation diagram when processing coupling and uncoupling operations in complex environments, resulting in low train dispatching efficiency and poor passenger experience is solved. The technical effect of dynamically adjusting the train coupling and uncoupling operation diagram in a complex environment and improving the adaptability and operating efficiency of the train dispatching system under complex operating conditions is achieved.

[0032] The method provided in the embodiment of the present application also includes: collecting a historical train delay record data set of the same type of trains in the first coupled train combination, wherein any historical train delay record data includes delayed train operating condition record data and delay time record data. Using the delayed train operating condition record data and the delay time record data as training samples, multi-layer decision tree training is performed to generate a multi-layer decision network. The real-time operating conditions of the coupled front train and the coupled rear train in the first coupled train combination are obtained. The real-time train operating conditions are input into the multi-layer decision network to predict the train delay time, and the delay prediction result of the first train combination is generated.

[0033] Taking the first coupling time as the prediction node, performing delay prediction on the trains in the first coupled train combination, and generating the delay prediction result of the first train combination, including: collecting the historical train delay record data set of the same type of trains in the first coupled train combination based on the historical train operation records, wherein any historical train delay record data includes delayed train operation condition record data and delay time record data, the delay time is the fixed time in the timetable in the record data plus the delay time, and the delayed train operation condition is the delayed weather factor including all weather factors such as rainfall, wind speed, temperature, etc. during train operation. Subsequently, taking the delayed train operation condition and the delay time record data as training samples, multi-layer decision tree training is performed according to the training samples, and then a multi-layer decision network is generated. The real-time operation condition of the coupled front train and the coupled rear train in the first coupled train combination is obtained, and the real-time operation condition of the train includes the running section and the running zone.

[0034] Based on the running section and the running time zone in the real-time running condition of the train, the weather forecast time series information of the running section in the corresponding running time zone is obtained. The weather forecast time series information is the weather forecast information of the corresponding position of each running time node in the running time interval. The weather forecast time series information is obtained according to the time series order of the running time node. The running time node is a time node in the running time zone obtained at a fixed time interval based on the prediction node. The weather forecast time series information is input into the multi-layer decision network to perform delay prediction of the arrival of the connected front car and the connected rear car, and the delay time prediction results of the longest delay time in the delay prediction of the connected front car and the connected rear car are obtained respectively, and the first train combination delay prediction result is generated. The delay time prediction results of the connected front car and the connected rear car are included in the first train combination delay prediction result.

[0035] The method provided in the embodiment of the present application further includes: extracting the delay time of the front car and the delay time of the rear car in the first train combination delay prediction result. Comparing the delay time of the front car and the delay time of the rear car, it is determined whether the arrival time deviation between the front car and the rear car is less than or equal to the preset time deviation. If so, the first connection time and the corresponding unbundling time are adjusted by the delay time to generate the first connection scheduling fitting result.

[0036] Based on the delay prediction result of the first train combination, the coupling scheduling fitting under the delay state is performed to generate the first coupling scheduling fitting result, including: extracting the delay time of the coupling front car and the delay time of the coupling rear car in the delay prediction result of the first train combination, and the delay time is the original arrival timetable plus the delay time to obtain the final predicted arrival time. Subsequently, the delay time of the coupling front car and the delay time of the coupling rear car are compared to determine whether the arrival time deviation of the coupling front car and the coupling rear car is less than or equal to the preset time deviation. The preset time deviation is a preset maximum time deviation threshold. If the time deviation is less than or equal to the preset time deviation, it is possible to wait. If the time deviation is greater than the preset time deviation, the coupling and uncoupling planning needs to be readjusted. If so, the time deviation of the coupling front car and the delay time of the coupling rear car is obtained, and the first coupling time and the corresponding uncoupling time are adjusted according to the time deviation, that is, the delay caused by the time deviation is compensated on the basis of the original first coupling time and the corresponding uncoupling time, and the first coupling scheduling fitting result is generated.

[0037] The method provided by the embodiment of the present application further includes: if the arrival time deviation between the front vehicle and the rear vehicle of the coupling is greater than the preset time deviation, the coupling unbundling optimization module is activated. Through the coupling unbundling optimization module, the coupling scheme is adjusted for the front vehicle and the rear vehicle of the coupling, with the delay time of the front vehicle and the delay time of the rear vehicle of the coupling as constraints and the passenger flow of the first coupling position as the goal, to generate the first coupling scheduling fitting result.

[0038] Determining whether the arrival time deviation between the front car and the rear car is less than or equal to the preset time deviation also includes: if the arrival time deviation between the front car and the rear car is greater than the preset time deviation, activating the coupling and uncoupling optimization module. Through the coupling and uncoupling optimization module, taking the delay time of the front car and the delay time of the rear car as constraints, and aiming to meet the passenger flow of the first coupling position, i.e., the coupling station position, obtaining the idle rear car and front car that need to be coupled under the delay time of the front car and the delay time of the rear car, and selecting the coupled trains and the front car with the goal of meeting the passenger flow of the first coupling position, i.e., the coupling station position, and obtaining the idle rear car and front car with the shortest delay as the adjustment train. The coupling scheme is adjusted for the coupled front car and the coupled rear car according to the adjustment train, the coupled front car is coupled to the coupled rear car in the adjustment train, and the coupled rear car is coupled to the coupled front car in the adjustment train, so as to generate the first coupling scheduling fitting result.

[0039] The method provided by the embodiment of the present application also includes: according to the first updated coupling and uncoupling operation diagram, identifying the coupling and uncoupling positions to control the coupling and uncoupling of the train, including: according to the first updated coupling and uncoupling operation diagram, extracting the first coupling front car, the first coupling rear car and the corresponding coupling position, and judging whether the first coupling front car has reached the front parking area and the first coupling rear car has reached the rear parking area according to the coupling position. If so, generating a coupling instruction, and controlling the first coupling rear car to travel toward the first coupling front car at the first coupling speed with the coupling instruction until the mechanical coupler completes the collision and the electric coupler is automatically connected.

[0040] According to the first updated coupling and uncoupling operation diagram, coupling and uncoupling positions are identified to control coupling and uncoupling of the train, including: according to the first updated coupling and uncoupling operation diagram, a first uncoupling train and a corresponding uncoupling position are extracted. When the first uncoupling train arrives at the uncoupling position, an uncoupling instruction is generated. The first uncoupling train is controlled by the uncoupling instruction to perform a mechanical coupler uncoupling operation at the uncoupling position.

[0041] The technical solution provided by the embodiment of the present invention obtains a preset track operation diagram, wherein the preset track operation diagram includes initial operation routes of multiple trains. Passenger flow prediction is performed for the initial operation routes of the multiple trains in a first preset time zone, and train coupling and uncoupling schemes are fitted for the multiple trains based on the prediction results to generate a first coupling and uncoupling operation diagram. The first coupling train combination and the first coupling time located at the first coupling position are extracted based on the first coupling and uncoupling operation diagram. The first coupling and uncoupling time is used as a prediction node, and delay prediction is performed for the trains in the first coupling train combination to generate a first train combination delay prediction result. Based on the first train combination delay prediction result, coupling scheduling fitting is performed under a delay state to generate a first coupling scheduling fitting result. The first coupling and uncoupling operation diagram is adjusted according to the first coupling and uncoupling fitting result to generate a first updated coupling and uncoupling operation diagram; and coupling and uncoupling positions are identified according to the first updated coupling and uncoupling operation diagram to perform coupling and uncoupling control of trains. The invention solves the technical problem that the train dispatching system in the prior art lacks the ability to make real-time adaptive adjustments to the coupling and uncoupling operation diagram when processing coupling and uncoupling operations in complex environments, resulting in low train dispatching efficiency and poor passenger experience. The invention realizes the technical effect of dynamically adjusting the train coupling and uncoupling operation diagram in complex environments and improving the adaptability and operating efficiency of the train dispatching system under complex operating conditions.

[0042] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for adaptively adjusting a train diagram based on automatic train coupling and uncoupling, characterized in that: include: Obtaining a preset track operation diagram, wherein the preset track operation diagram includes initial operation routes of multiple trains; Performing passenger flow prediction for the initial operation routes of the plurality of trains in a first preset time zone, fitting train coupling and uncoupling schemes for the plurality of trains based on the prediction results, and generating a first coupling and uncoupling operation diagram; Extracting the first coupling train combination and the first coupling time at the first coupling position based on the first coupling disassembly running diagram; Taking the first coupling time as a prediction node, performing delay prediction on the trains in the first coupled train combination, and generating a delay prediction result for the first train combination; Perform coupling scheduling fitting under the delay state based on the first train combination delay prediction result to generate a first coupling scheduling fitting result; Adjusting the first coupling unmarshaling operation diagram according to the first coupling scheduling fitting result to generate a first updated coupling unmarshaling operation diagram; According to the first updated coupling and uncoupling operation diagram, coupling and uncoupling positions are identified to perform coupling and uncoupling control of the train; The method includes: predicting passenger flow for the initial operation routes of the plurality of trains in a first preset time zone, fitting train coupling and uncoupling schemes for the plurality of trains based on the prediction results, and generating a first coupling and uncoupling operation diagram, including: Collecting historical passenger flow data for the initial operation routes of the plurality of trains; Based on the historical passenger flow data, a plurality of passenger flow prediction networks corresponding to the plurality of trains are constructed by using time series analysis; Performing passenger flow prediction for the first preset time zone using the multiple passenger flow prediction networks to generate the prediction results, wherein the prediction results include predicted passenger flows for the initial operation routes of the multiple trains; According to the prediction result, train capacity adaptation fitting is performed to generate the first coupling and uncoupling operation diagram; The first coupling and uncoupling operation diagram includes coupling and uncoupling time, coupling and uncoupling positions, and coupling and uncoupling train combinations; The multiple passenger flow prediction networks are connected to an unstable passenger flow feedback layer, wherein the unstable passenger flow feedback layer is used to optimize the output results of the multiple passenger flow prediction networks according to the unstable passenger flow factor; The unstable passenger flow factor is a passenger flow influencing factor with irregular time nodes, and the passenger flow influencing samples are collected by using the unstable passenger flow factor to train the unstable passenger flow feedback layer; According to the prediction result, train capacity adaptation fitting is performed to generate the first coupling and uncoupling operation diagram, including: Performing train capacity adaptation analysis according to the predicted passenger flow of the initial operation routes of the plurality of trains, and generating train capacity adaptation information of the initial operation routes; Based on the train capacity adaptation information, train coupling and uncoupling fitting is performed in the first preset time zone to generate the coupling and uncoupling time, coupling and uncoupling positions, and coupling and uncoupling train combinations, which are connected in sequence to establish the first coupling and uncoupling operation diagram.

2. The method for adaptively adjusting the train diagram based on automatic train coupling and uncoupling as claimed in claim 1, characterized in that: Taking the first coupling time as a prediction node, performing delay prediction on the trains in the first coupled train combination, and generating a delay prediction result for the first train combination, including: Collecting a historical train delay record data set of the same type of trains of the first coupled train combination, wherein any piece of historical train delay record data includes delayed train operation condition record data and delay time record data; Using the delayed train operating condition record data and the delay time record data as training samples, multi-layer decision tree training is performed to generate a multi-layer decision network; Acquiring the real-time operating conditions of the front train and the rear train in the first coupled train combination; The real-time operating conditions of the train are input into the multi-layer decision network to predict the train delay time, and the first train combination delay prediction result is generated.

3. The method for adaptively adjusting the train diagram based on automatic train coupling and uncoupling as claimed in claim 2, characterized in that: Performing coupling scheduling fitting under the delay state based on the first train combination delay prediction result to generate a first coupling scheduling fitting result includes: Extracting the delay time of the preceding train and the delay time of the succeeding train from the delay prediction result of the first train combination; Comparing the delay time of the preceding vehicle and the delay time of the succeeding vehicle, determining whether the arrival time deviation between the preceding vehicle and the succeeding vehicle is less than or equal to a preset time deviation; If so, the first coupling time and the corresponding uncoupling time are adjusted according to the delay time to generate the first coupling scheduling fitting result.

4. The method for adaptively adjusting the train diagram based on automatic train coupling and uncoupling as claimed in claim 3, characterized in that: Determining whether the arrival time deviation between the front vehicle and the rear vehicle is less than or equal to a preset time deviation further includes: If the arrival time difference between the front vehicle and the rear vehicle is greater than the preset time difference, the coupling unpacking optimization module is activated; Through the coupling unmarshalling optimization module, with the delay time of the front vehicle and the delay time of the rear vehicle being constrained and with the passenger flow of the first coupling position being met as the goal, the coupling scheme is adjusted for the front vehicle and the rear vehicle, and the first coupling scheduling fitting result is generated.

5. The method for adaptively adjusting the train diagram based on automatic train coupling and uncoupling as claimed in claim 1, characterized in that: According to the first updated coupling and uncoupling operation diagram, coupling and uncoupling positions are identified to control the coupling and uncoupling of the train, including: Extracting the first coupling front vehicle, the first coupling rear vehicle and corresponding coupling positions according to the first updated coupling disassembly operation diagram, and judging whether the first coupling front vehicle has reached the front parking area and whether the first coupling rear vehicle has reached the rear parking area according to the coupling positions; If so, a coupling instruction is generated, and the coupling instruction is used to control the first coupled rear vehicle to travel toward the first coupled front vehicle at a first coupling speed until the mechanical coupler completes the collision and the electrical coupler is automatically connected.

6. The method for adaptively adjusting the train diagram based on automatic train coupling and uncoupling as claimed in claim 5, characterized in that: According to the first updated coupling and uncoupling operation diagram, coupling and uncoupling positions are identified to control the coupling and uncoupling of the train, including: Extracting a first disassembly train and a corresponding disassembly position according to the first updated coupling and disassembly operation diagram; When the first disassembling train arrives at the disassembling position, generating a disassembling instruction; The first de-marshalling train is controlled by the de-marshalling instruction to perform a de-marshalling operation of a mechanical coupler at the de-marshalling position.

Images