A heavy-load train control method, system and storage medium based on virtual coupling

Abstract

The present invention discloses a heavy-load train control method, system and storage medium based on virtual coupling, and relates to the field of heavy-load train intelligent control technology. The first operation data of the heavy-load train is obtained respectively; the communication heavy-load train sequence diagram is obtained according to the first operation data of the heavy-load train, and a virtual coupling heavy-load train communication topology network model is established based on the first control parameters of each control base station during the operation of the heavy-load train and the communication heavy-load train sequence diagram; the first operation data of the heavy-load train is input into the neural network prediction model to predict the second operation data at the next moment; the second operation data is input into the virtual coupling heavy-load train communication topology network model to calculate the second control parameters of each control base station; the second control parameters of each control base station are processed collaboratively to obtain the optimal control parameters. The control efficiency and control accuracy of the heavy-load train are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of heavy-load train intelligent control, and more particularly to a heavy-load train control method, system and storage medium based on virtual coupling. Background Art

[0002] At present, China's heavy-haul railway lines are constantly expanding, and heavy-haul railway transportation has a very important strategic and economic position in rail transportation. With the rapid development of heavy-haul railways, the transportation capacity of heavy-haul railways is constantly improving, and the demand for heavy-haul railway transportation is also constantly increasing. How to improve transportation efficiency and ensure operational safety has always been the focus and challenge of railway research. The development of wireless communication technology, sensor technology, and vehicle-to-vehicle communication technology has brought new opportunities to the railway industry. Concepts such as the Internet of Everything and smart transportation have spawned a variety of technical solutions to improve railway safety, transportation efficiency, resource allocation efficiency, and operation and maintenance efficiency. Heavy-haul trains generally refer to large-scale special freight trains on transportation routes with concentrated freight volumes, and are operated by double or multiple locomotives. Heavy-haul trains have large load-bearing capacity; the number of trains is large. At present, in order to realize the coupling of multiple heavy-haul trains, a train virtual coupling technology has been proposed. The virtual train coupling technology is based on the car-to-car communication technology. It can effectively improve the transportation efficiency and capacity by forwarding the speed and position relationship of the front and rear trains in real time through the car-to-car communication link, and adjust its own speed in time. It can also perform virtual coupling or uncoupling operations when there is a need for specific track operations. In addition, the virtual coupling technology minimizes physical operations, further saving time, human and material resources and costs.

[0003] The so-called virtual coupling means that two trains are controlled and managed as one train without physical coupling. The two trains can accelerate, decelerate and stop synchronously at a small distance. However, how to achieve the coordinated management of multiple heavy-load trains and then realize virtual coupling is urgently needed to be studied by those skilled in the art. Summary of the invention

[0004] In view of this, the present invention provides a heavy-load train control method, system and storage medium based on virtual coupling, which realizes synchronous acceleration, synchronous deceleration and synchronous parking of heavy-load trains, thereby solving the problems existing in the background technology.

[0005] In order to achieve the above object, the present invention adopts the following technical solution:

[0006] A heavy-load train control method based on virtual coupling comprises the following steps:

[0007] respectively acquiring first operation data of the heavy-load train, wherein the first operation data of the heavy-load train includes: operation status of the heavy-load train, performance of the heavy-load train, and road condition information during operation of the heavy-load train;

[0008] A communication heavy-load train sequence diagram is obtained according to the first operation data of the heavy-load train, and a virtual coupled heavy-load train communication topology network model is established based on the first control parameters of each control base station during the operation of the heavy-load train and the communication heavy-load train sequence diagram;

[0009] Inputting the first operation data of the heavy-load train into the neural network prediction model to predict the second operation data at the next moment;

[0010] Inputting the second operation data into the virtual coupled heavy-load train communication topology network model to calculate the second control parameters of each control base station;

[0011] The second control parameters of each control base station are processed collaboratively to obtain the optimal control parameters.

[0012] Optionally, the operating status of the heavy-loaded train includes the speed, acceleration and the front and rear distances of the heavy-loaded train; the performance of the heavy-loaded train includes the communication delay and braking performance differences of the heavy-loaded train; the road condition information includes whether there is a slope, whether there is a tunnel, whether there is a bridge and weather conditions.

[0013] Optionally, the information in the communication heavy-load train sequence diagram includes the relative distance between the preceding heavy-load train and the succeeding heavy-load train, the road condition information of the current virtual coupled heavy-load train, and the heavy-load train performance information; wherein the relative distance between the preceding heavy-load train and the succeeding heavy-load train is calculated as follows:

[0014] Setting a consecutive number for each heavy-load train in the virtual coupled heavy-load train;

[0015] The virtual coupled train identification system based on vehicle-to-vehicle communication and lidar technology combines low-latency vehicle-to-vehicle communication and high-precision lidar ranging to obtain the speed and distance information of adjacent numbered heavy-load trains in real time, and then predict the relative distance between adjacent numbered heavy-load trains at the next moment.

[0016] Optionally, the method further includes training a recursive neural network using optimal control parameters to obtain a virtual coupling control model for a heavy-load train, and controlling the heavy-load train based on the virtual coupling control model for the heavy-load train.

[0017] Optionally, the second control parameters of each control base station are collaboratively processed, specifically including:

[0018] Each base station corresponds to a control parameter node, and the control parameters of multiple control parameter nodes are combined into a control parameter matrix;

[0019] The target control gain coefficient matrix is ​​preset, and the control parameter matrix and the target control gain coefficient matrix are multiplied to obtain the collaborative control result.

[0020] According to the operation conditions of multiple heavy-load trains, the multi-agent formation control principle is applied, and collaborative cruise control is used to ensure that a safe distance is maintained between the unit trains of the heavy-load trains.

[0021] Optionally, it also includes obtaining abnormal collaborative data, pre-processing various data in the collaborative processing process, and normalizing them to obtain the collaborative control parameters and collaborative control status of each heavy-load train unit, where the collaborative control status includes the braking distance of the heavy-load train unit and the speed information of the heavy-load train unit, as well as the overall running speed of the heavy-load train, and the overall running speed of the heavy-load train and the running speed of the heavy-load train unit are traced and evaluated in real time.

[0022] A heavy-load train control system based on virtual coupling, comprising:

[0023] An initial operation data acquisition module is used to acquire first operation data of a heavy-load train, wherein the first operation data of the heavy-load train includes: operation status of the heavy-load train, performance of the heavy-load train, and road condition information during the operation of the heavy-load train;

[0024] A communication topology network model building module is used to obtain a communication heavy-load train sequence diagram according to the first operation data of the heavy-load train, and to establish a virtual coupled heavy-load train communication topology network model based on the first control parameters of each control base station during the operation of the heavy-load train and the communication heavy-load train sequence diagram;

[0025] Operation data prediction module: used to input the first operation data of the heavy-load train into the neural network prediction model to predict the second operation data at the next moment;

[0026] A control parameter calculation module: used for inputting the second operation data into the virtual coupled heavy-load train communication topology network model to calculate the second control parameters of each control base station;

[0027] Cooperative processing module: used for cooperatively processing the second control parameters of each control base station to obtain the optimal control parameters.

[0028] Optionally, it also includes a heavy-load train control model establishment module: used to train the recursive neural network with optimal control parameters to obtain a virtual coupling control model of the heavy-load train, and control the heavy-load train based on the virtual coupling control model of the heavy-load train.

[0029] A computer storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the methods for controlling a heavy-load train based on virtual coupling are implemented.

[0030] It can be seen from the above technical solutions that, compared with the prior art, the present invention provides a heavy-load train control method, system and storage medium based on virtual coupling, which have the following beneficial effects:

[0031] 1. The present invention comprehensively analyzes the operation data of heavy-loaded trains, timely discovers whether there is a problem of too small relative distance at the current moment or the next moment during the operation process, realizes timely response during the operation of heavy-loaded trains, can improve the control efficiency of heavy-loaded trains, and predict the operation status of heavy-loaded trains at the next moment through prediction, and improves the control accuracy of heavy-loaded trains according to the parameters of the heavy-loaded trains themselves, and has good application prospects.

[0032] 2. The virtual coupled heavy-load train identification system based on vehicle-to-vehicle communication and lidar technology of the present invention combines low-latency vehicle-to-vehicle communication, high-precision lidar ranging and other technologies to ensure that the train control system of the rear heavy-load train can accurately and real-time obtain the position and speed information of the heavy-load train in front. Through the control model of the heavy-load train, the train braking mode is adjusted in real time, and the braking curve is drawn. In the scenario of intensive tracking of marshaled trains, the high reliability and high safety of the train control system are guaranteed, which further shortens the train running distance, improves railway transportation efficiency and track occupancy rate, and has broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0034] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0035] Figure 2 It is a schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] The embodiment of the present invention discloses a heavy-load train control method based on virtual coupling, such as Figure 1 As shown, the following steps are included:

[0038] S1: respectively obtaining first operating data of a heavy-load train, wherein the first operating data of the heavy-load train includes: operating status of the heavy-load train, performance of the heavy-load train, and road condition information during the operation of the heavy-load train;

[0039] S2: obtaining a communication heavy-load train sequence diagram according to the first operation data of the heavy-load train, and establishing a virtual coupled heavy-load train communication topology network model based on the first control parameters of each control base station during the operation of the heavy-load train and the communication heavy-load train sequence diagram;

[0040] S3: inputting the first operation data of the heavy-load train into the neural network prediction model to predict the second operation data at the next moment;

[0041] S4: inputting the second operation data into the virtual coupled heavy-load train communication topology network model, and calculating the second control parameters of each control base station;

[0042] S5: Coordinately process the second control parameters of each control base station to obtain an optimal control parameter.

[0043] Furthermore, in S1, the running status of the heavy-loaded train includes the speed, acceleration and the front and rear distances of the heavy-loaded train; the performance of the heavy-loaded train includes the communication delay and braking performance difference of the heavy-loaded train; the road condition information includes whether there is a slope, whether there is a tunnel, whether there is a bridge and weather conditions.

[0044] Further, in S2, the information in the communication heavy-load train sequence diagram includes the relative distance between the previous heavy-load train and the next heavy-load train, the road condition information of the current virtual coupled heavy-load train, and the heavy-load train performance information; wherein, the relative distance between the previous heavy-load train and the next heavy-load train is calculated as follows:

[0045] S21: setting a consecutive number for each heavy-load train in the virtual coupled heavy-load train;

[0046] S22: The virtual coupled train identification system based on vehicle-to-vehicle communication and lidar technology combines low-latency vehicle-to-vehicle communication and high-precision lidar ranging to obtain the speed and distance information of adjacent numbered heavy-load trains in real time, and then predict the relative distance between adjacent numbered heavy-load trains at the next moment.

[0047] Among them, the relative distance includes that in order to realize the safe operation of the small spacing between unit trains in the virtual marshaling train (i.e., far less than the absolute braking distance), the safety protection control between unit trains must break through the traditional train protection method based on absolute braking distance and change to a method based on relative braking distance. Through the above technical solution of the present invention, the rear train can make full use of the operating status information such as the position, speed, acceleration, etc. of the front train, and incorporate the line resources that will be dynamically released by the front train in the future into the protection speed calculation process in advance, thereby shortening the train tracking distance while ensuring safety.

[0048] In the virtual coupling scenario, the train control system needs to reduce the train running interval as much as possible while ensuring the safe, reliable and efficient operation of the train. Therefore, the train identification system is required to have low response and measurement delays; the communication system updates the mobile authorization message frequency high, that is, the vehicle-to-vehicle communication mode is adopted. In addition, the high safety of the train control system depends on the high reliability of the train identification system. According to the fail-safe principle, once a fault occurs and the rear vehicle cannot receive the running and speed information of the front vehicle, a braking stop strategy should be adopted.

[0049] Further, in S5, the second control parameters of each control base station are collaboratively processed, specifically including:

[0050] S51: Each base station corresponds to a control parameter node, and control parameters of multiple control parameter nodes are combined into a control parameter matrix;

[0051] S52: Preset a target control gain coefficient matrix, multiply the control parameter matrix and the target control gain coefficient matrix to obtain a coordinated control result.

[0052] Furthermore, combined with the operating characteristics of multiple heavy-load unit trains, the multi-agent formation control principle can also be applied to achieve safe spacing between unit trains of heavy-load trains through coordinated cruise control. The specific approach is to use the safe spacing between unit trains as the extreme point of the potential energy function, and by improving the potential energy function, both the stable operation of the virtual formation and the safe spacing between unit trains can be ensured to meet the safety protection requirements of unit trains.

[0053] Further optimization of this embodiment also includes training the recursive neural network with optimal control parameters to obtain a heavy-load train virtual coupling control model, and controlling the heavy-load train based on the heavy-load train virtual coupling control model. The present invention uses a recursive neural network to fit and predict expert experience data, trains a safe, stable, and efficient heavy-load train virtual controller, and applies the heavy-load train virtual controller to the actual operation of the heavy-load train, so as to have safe, stable, and efficient properties.

[0054] Among them, the control base station refers to the train control room, which can be located on a heavy-load train or along the heavy-load train line, and can even be unmanned and remotely controlled.

[0055] As a preferred embodiment, the present invention also includes obtaining abnormal collaborative data, preprocessing and normalizing various data in the collaborative processing process, obtaining the collaborative control parameters and collaborative control status of each heavy-load train unit, wherein the collaborative control status includes the braking distance of the heavy-load train unit and the speed information of the heavy-load train unit, as well as the overall running speed of the heavy-load train. The overall running speed of the heavy-load train and the running speed of the heavy-load train unit are traced and evaluated in real time, so as to comprehensively obtain the specific degree of impact of abnormal collaborative processing, and provide reliable local data support for the overall management and control of subsequent collaborative departments and collaborative personnel, thereby improving the accuracy and availability of collaborative processing data monitoring and analysis; the present invention is used to solve the technical problem that the existing scheme cannot implement different dimensions of monitoring and analysis of the collaborative processing status of the heavy-load train as a whole and the heavy-load train units, and implement dynamic control and alarm prompts according to the analysis results to improve the subsequent collaborative processing effect.

[0056] and Figure 1 Corresponding to the method shown, the present invention also discloses a heavy-load train control system based on virtual coupling for Figure 1 The implementation of the method, the specific structure is as follows Figure 2 As shown, including:

[0057] An initial operation data acquisition module is used to acquire first operation data of a heavy-load train, wherein the first operation data of the heavy-load train includes: operation status of the heavy-load train, performance of the heavy-load train, and road condition information during the operation of the heavy-load train;

[0058] A communication topology network model building module is used to obtain a communication heavy-load train sequence diagram according to the first operation data of the heavy-load train, and to establish a virtual coupled heavy-load train communication topology network model based on the first control parameters of each control base station during the operation of the heavy-load train and the communication heavy-load train sequence diagram;

[0059] Operation data prediction module: used to input the first operation data of the heavy-load train into the neural network prediction model to predict the second operation data at the next moment;

[0060] A control parameter calculation module: used for inputting the second operation data into the virtual coupled heavy-load train communication topology network model to calculate the second control parameters of each control base station;

[0061] Cooperative processing module: used for cooperatively processing the second control parameters of each control base station to obtain the optimal control parameters.

[0062] Further optimization of this embodiment also includes a heavy-load train control model establishment module: used to train the recursive neural network with optimal control parameters to obtain a heavy-load train virtual coupling control model, and control the heavy-load train based on the heavy-load train virtual coupling control model.

[0063] Finally, this embodiment discloses a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, any one of the steps of a heavy-load train control method based on virtual coupling is implemented.

[0064] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0065] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A heavy-load train control method based on virtual coupling, characterized in that: The following steps are involved: The first operation data of the heavy-load train is respectively obtained, and the first operation data of the heavy-load train includes: the operation state of the heavy-load train, the performance of the heavy-load train and the road condition information during the operation of the heavy-load train; the operation state of the heavy-load train includes the speed and acceleration of the heavy-load train and the front and rear distances of the front and rear vehicles; the performance of the heavy-load train includes the communication delay of the heavy-load train and the difference in braking performance; the road condition information includes whether there is a slope, whether there is a tunnel, whether there is a bridge and weather conditions; A communication heavy-load train sequence diagram is obtained according to the first operation data of the heavy-load train, and a virtual coupled heavy-load train communication topology network model is established based on the first control parameters of each control base station during the operation of the heavy-load train and the communication heavy-load train sequence diagram; Inputting the first operation data of the heavy-load train into the neural network prediction model to predict the second operation data at the next moment; Inputting the second operation data into the virtual coupled heavy-load train communication topology network model to calculate the second control parameters of each control base station; Coordinately process the second control parameters of each control base station to obtain an optimal control parameter; The recursive neural network is trained using the optimal control parameters to obtain a virtual coupling control model for a heavy-haul train, and the heavy-haul train is controlled based on the virtual coupling control model for the heavy-haul train; It also includes obtaining abnormal collaborative data, pre-processing and normalizing various data in the collaborative processing process, and obtaining the collaborative control parameters and collaborative control status of each heavy-load train unit, where the collaborative control status includes the braking distance of the heavy-load train unit and the speed information of the heavy-load train unit, as well as the overall running speed of the heavy-load train, and real-time traceability and evaluation of the overall running speed of the heavy-load train and the running speed of the heavy-load train unit.

2. A method for controlling a heavy-load train based on virtual coupling according to claim 1, characterized in that: The information in the communication heavy-load train sequence diagram includes the relative distance between the preceding heavy-load train and the succeeding heavy-load train, the road condition information of the current virtual coupled heavy-load train, and the performance information of the heavy-load train; wherein the relative distance between the preceding heavy-load train and the succeeding heavy-load train is calculated as follows: Setting a consecutive number for each heavy-load train in the virtual coupled heavy-load train; The virtual coupled train identification system based on vehicle-to-vehicle communication and lidar technology combines low-latency vehicle-to-vehicle communication and high-precision lidar ranging to obtain the speed and distance information of adjacent numbered heavy-load trains in real time, and then predict the relative distance between adjacent numbered heavy-load trains at the next moment.

3. A method for controlling a heavy-load train based on virtual coupling according to claim 1, characterized in that: The second control parameters of each control base station are collaboratively processed, specifically including: Each base station corresponds to a control parameter node, and the control parameters of multiple control parameter nodes are combined into a control parameter matrix; The target control gain coefficient matrix is ​​preset, and the control parameter matrix and the target control gain coefficient matrix are multiplied to obtain the collaborative control result.

4. A method for controlling a heavy-load train based on virtual coupling according to claim 3, characterized in that: According to the operation conditions of multiple heavy-load trains, the multi-agent formation control principle is applied, and collaborative cruise control is used to ensure that a safe distance is maintained between the unit trains of the heavy-load trains.

5. A heavy-load train control system based on virtual coupling, using a heavy-load train control method based on virtual coupling as claimed in any one of claims 1 to 3, characterized in that: include: An initial operation data acquisition module is used to acquire first operation data of a heavy-load train, wherein the first operation data of the heavy-load train includes: operation status of the heavy-load train, performance of the heavy-load train, and road condition information during the operation of the heavy-load train; A communication topology network model building module is used to obtain a communication heavy-load train sequence diagram according to the first operation data of the heavy-load train, and to establish a virtual coupled heavy-load train communication topology network model based on the first control parameters of each control base station during the operation of the heavy-load train and the communication heavy-load train sequence diagram; Operation data prediction module: used to input the first operation data of the heavy-load train into the neural network prediction model to predict the second operation data at the next moment; A control parameter calculation module: used for inputting the second operation data into the virtual coupled heavy-load train communication topology network model to calculate the second control parameters of each control base station; Cooperative processing module: used for cooperatively processing the second control parameters of each control base station to obtain the optimal control parameters.

6. A heavy-load train control system based on virtual coupling according to claim 5, characterized in that: It also includes a heavy-load train control model establishment module: it is used to train the recursive neural network with optimal control parameters to obtain a heavy-load train virtual coupling control model, and control the heavy-load train based on the heavy-load train virtual coupling control model.

7. A computer storage medium, characterized in that: The computer storage medium stores a computer program, and when the computer program is executed by the processor, the steps of a heavy-load train control method based on virtual coupling as described in any one of claims 1 to 4 are implemented.

Images