Vehicle-ground collaborative operation and maintenance system and method based on rail transit

Abstract

The present invention discloses a vehicle-ground collaborative operation and maintenance system and method based on rail transit, which relates to the field of transportation operation and maintenance technology, and realizes global visual monitoring of rail transit structure. The present invention integrates various local historical operation data to establish a historical driving data chain according to the spatial position relationship between the running track and the rail vehicle at each time node, matches each rail vehicle with each running track in pairs, retrieves the corresponding central associated data cluster and abnormal data according to the matching result, and then establishes a number of running state particles and maintenance plan particles, collects the real-time running data of each rail vehicle and the real-time running data expected to pass through the running track in the real-time state, matches each real-time data in the real-time running data with the running state particles, judges whether there is an abnormality in the rail vehicle or the running track according to the matching result, and then retrieves the corresponding maintenance plan particles to obtain the maintenance plan and execute it.

Description

Technical Field

[0001] The present invention relates to the field of transportation operation and maintenance technology, and in particular to a vehicle-ground collaborative operation and maintenance system and method based on rail transportation. Background Art

[0002] In recent years, the application of intelligent technologies such as the Internet of Things (IoT), big data analysis, and artificial intelligence (AI) in rail transit operation and maintenance has gradually deepened. The vehicle-ground collaborative operation and maintenance method uses these technologies to achieve real-time data collection, intelligent analysis, and prediction of rail transit systems. Through sensors, monitoring equipment, and data analysis platforms, the status of tracks, vehicles, and related equipment can be monitored in real time, thereby achieving a comprehensive understanding and early warning of the system status.

[0003] The following defects exist:

[0004] Information island problem: In the traditional operation and maintenance model, the information of vehicles and ground facilities is usually separated, and their respective monitoring systems, maintenance records and operation data are often not effectively integrated. This leads to an incomplete understanding of the overall status of the system and difficulty in achieving accurate operation and maintenance decisions.

[0005] Long response time: Due to untimely information transmission and feedback, when a rail transit system fails or fails, it may take a long time for the relevant operation and maintenance personnel to discover and respond. This delay not only affects the normal operation of the system, but may also increase maintenance costs and downtime.

[0006] Therefore, how to improve the response rate of the rail transit system while achieving global visual monitoring of the rail transit structure is a defect of the existing technology. For this purpose, a vehicle-ground collaborative operation and maintenance system and method based on rail transit are provided. Summary of the invention

[0007] In order to solve the above technical problems, the purpose of the present invention is to provide a vehicle-ground collaborative operation and maintenance system and method based on rail transit.

[0008] In order to achieve the above object, the present invention provides the following technical solutions:

[0009] The vehicle-ground collaborative operation and maintenance method based on rail transit includes the following steps:

[0010] Step S1: installing a variety of sensors on the urban rail and each train, collecting a number of local historical operation data of the running track and each train through the various sensors, and integrating each local historical operation data to establish a historical driving data chain according to the spatial position relationship between the running track and the train at each time node;

[0011] Step S2: establishing a central correlation data cluster and abnormal data of various data corresponding to any two running tracks and rail vehicles according to the historical running data chain;

[0012] Step S3, matching each rail vehicle with each running track in pairs, retrieving the corresponding central associated data cluster and abnormal data according to the matching results, and then establishing a number of running status particles and maintenance plan particles;

[0013] Step S4: collect the real-time operation data of each rail vehicle and the real-time operation data of the track that is expected to pass through, match each real-time data in the real-time operation data with the corresponding operation status particles, and judge whether there is an abnormality in the rail vehicle or the track according to the matching result, and then call the corresponding maintenance plan particle to obtain the maintenance plan and execute it.

[0014] Furthermore, the local operation data collection process includes:

[0015] According to the distribution of various transfer stations of urban rail, the urban rail is divided into several running tracks, and each running track and rail vehicle is numbered respectively;

[0016] Before each rail motor vehicle travels, a travel event of each rail motor vehicle is obtained, wherein the travel event includes a rail motor vehicle number and a number of a passageway through which the rail motor vehicle will travel;

[0017] The same data collection cycle is set for each rail vehicle and each group of sensors on the corresponding running track. When the rail vehicle is running along the running track, each sensor collects relevant data at its location. At the end of any data collection cycle, the data collected by each group of sensors are integrated to generate local historical operation data of the corresponding area or carriage.

[0018] Furthermore, the process of establishing the historical driving data link includes:

[0019] When the rail vehicle running event ends, several historical data nodes are established, and each local running data is input into the historical data node in sequence, and then each historical data node is connected to obtain the vehicle historical data chain and the track historical data chain according to the time sequence of each local running data of the rail vehicle and the running track;

[0020] At the same time, the relative spatial positions of the EMU and the travel track at each time node are matched and connected with the historical data nodes in the EMU historical data chain and the track historical data chain at the same time node and the same spatial position to obtain the historical travel data chain of the corresponding travel event, and mark the corresponding EMU number, travel road number and the start and end time interval of the travel event.

[0021] Furthermore, the process of establishing the center-related data cluster includes:

[0022] Divide each historical data node of the historical driving data chain into several local historical driving data chains according to the driving track, and then classify the local historical driving data chains with the same track train number and driving road number but marked with the start and end time intervals of the driving event;

[0023] Establish several multi-dimensional coordinate systems, put the local historical driving data chain within the same category, corresponding to the same object, spatial position and the same type of data on the same multi-dimensional coordinate system, and obtain the individual spatial distances between different data;

[0024] Set the monomer space distance threshold, take each data as the central data in turn, and then judge the relationship between the monomer space distance between the remaining data and the central data and the monomer space distance threshold;

[0025] According to the judgment results, each central data is taken as the center of the relationship cluster in turn, and then the data associated with the central data is integrated to establish an associated data cluster. The number of data in each associated data cluster is compared, and the associated data cluster with the largest number of data is selected as the central associated data cluster.

[0026] Furthermore, the process of establishing the center-related data cluster also includes:

[0027] Determine whether the monomer space distance between the relationship cluster center of each associated data cluster and the relationship cluster center of the central associated data cluster is greater than or equal to the monomer space distance threshold. If the judgment is true, merge the corresponding associated data cluster with the central associated data cluster to obtain a new central associated data cluster, but the relationship cluster center position of the original central associated data cluster remains unchanged;

[0028] The above operation of merging related data clusters is repeated until there are no related data clusters that meet the conditions and can be merged with the central related data cluster.

[0029] Furthermore, the remaining data not in the central associated data cluster is recorded as abnormal data, and then the corresponding central associated data cluster and abnormal data corresponding to the same object, spatial position and the same type of data in the local historical driving data chain within the same category are obtained.

[0030] Furthermore, the process of establishing the operating status particle and the maintenance plan particle includes:

[0031] Match the numbers of each rail vehicle with each running track in pairs, and retrieve the central associated data cluster and abnormal data of several corresponding data from the urban rail transit three-dimensional image model according to the matching results;

[0032] The data value of the center of the relationship cluster of the central associated data cluster is selected as the optimal operation achievement condition of the corresponding rail vehicle and the running track at the corresponding time node, and several data at the edge position of the central associated data cluster are recorded as the minimum operation achievement condition. At the same time, the corresponding maintenance plan is generated according to the abnormal problems of the rail vehicle and the running track corresponding to various abnormal data;

[0033] According to the number of matching results of each rail vehicle and each running track number, several running status particles and maintenance plan particles are established, and the numbers of the corresponding rail vehicle and the running track are marked on each running status particle, and the relevant optimal running conditions and minimum running conditions are included in the running status particles, and the maintenance plan and related abnormal data are input into the maintenance plan particles.

[0034] Furthermore, the process of determining whether there is an abnormality in the rail vehicle or the running track includes:

[0035] Acquire the real-time travel events of each rail vehicle, traverse the travel tracks that the rail vehicle will pass through in the three-dimensional image model of urban rail transit according to the real-time travel events, and then collect the real-time operation data of each rail vehicle and the travel tracks that it will pass through in real-time state;

[0036] Before the rail vehicle travels, firstly, according to the track number that the rail vehicle is going to pass, the real-time operation data of the track that the rail vehicle is going to pass is input into the corresponding operation status particle, and then it is judged whether each real-time data in each real-time operation data is within any data interval with the best operation achievement condition and the minimum operation achievement condition as the extreme value in the corresponding operation status particle;

[0037] If yes, no operation is performed; if no, the corresponding real-time data is abnormal data, and then the corresponding maintenance plan particle is matched according to the abnormal data, and the maintenance plan in the maintenance plan particle is obtained to repair the corresponding driving track;

[0038] When the rail vehicle is running, the real-time operation data of the rail vehicle and the track on which it is currently traveling is obtained, and a similar process to obtaining the maintenance plan for the track to be passed is adopted to obtain the maintenance plan of the rail vehicle and the track on which it is currently traveling at each time node in real time and execute it until the real-time driving event of the corresponding rail vehicle ends.

[0039] A vehicle-ground collaborative operation and maintenance system based on rail transit, comprising a rail transit data acquisition module, a historical data analysis module and a historical data analysis module;

[0040] The rail transit data acquisition module is used to collect several local historical operation data and real-time operation data of the running track and each rail vehicle through various sensors, and integrate various local historical operation data to establish a historical driving data chain according to the spatial position relationship between the running track and the rail vehicle at each time node;

[0041] The historical data analysis module is used to establish the central correlation data cluster and abnormal data of the data corresponding to any two running tracks and rail vehicles according to the historical running data chain, and then match each rail vehicle with each running track in pairs, and retrieve the corresponding central correlation data cluster and abnormal data according to the matching result, and then establish a number of running state particles and maintenance plan particles;

[0042] The historical data analysis module is used to match each real-time data in the real-time operation data with the corresponding operation status particles, and judge whether there is an abnormality in the rail vehicle or the running track according to the matching result, and then call the corresponding maintenance plan particle to obtain the maintenance plan and execute it.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] According to the spatial position relationship between the running track and the rail vehicle at each time node, the present invention integrates each local historical operation data to establish a historical running data chain, matches each rail vehicle with each running track in pairs, retrieves the corresponding central associated data cluster and abnormal data according to the matching result, and then establishes a plurality of running state particles and maintenance plan particles, collects the real-time running data of each rail vehicle and the real-time running data expected to pass through the running track in real time, matches each real-time data in the real-time running data with the running state particles, judges whether the rail vehicle or the running track is abnormal according to the matching result, and then retrieves the corresponding maintenance plan particles to obtain and execute the maintenance plan, thereby realizing global visual monitoring of the rail transit structure while improving the response rate of the rail transit system. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention.

[0046] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0047] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention. Embodiment 1

[0048] like Figure 1 As shown, the vehicle-ground collaborative operation and maintenance method based on rail transit includes the following steps:

[0049] Step S1: installing a variety of sensors on the urban rail and each train, collecting a number of local historical operation data of the running track and each train through the various sensors, and integrating each local historical operation data to establish a historical driving data chain according to the spatial position relationship between the running track and the train at each time node;

[0050] Step S2: establishing a central correlation data cluster and abnormal data of various data corresponding to any two running tracks and rail vehicles according to the historical running data chain;

[0051] Step S3, matching each rail vehicle with each running track in pairs, retrieving the corresponding central associated data cluster and abnormal data according to the matching results, and then establishing a number of running status particles and maintenance plan particles;

[0052] Step S4: collect the real-time operation data of each rail vehicle and the real-time operation data of the track that is expected to pass through, match each real-time data in the real-time operation data with the corresponding operation status particles, and judge whether there is an abnormality in the rail vehicle or the track according to the matching result, and then call the corresponding maintenance plan particle to obtain the maintenance plan and execute it. Embodiment 2

[0053] This embodiment is a further limitation of Embodiment 1, and Step S1 is implemented by the following process:

[0054] According to the distribution of various transfer stations of urban rail, the urban rail is divided into several running tracks, and each running track and rail vehicle is numbered a1, a2, a3, ..., a n , and b1, b2, b3, ..., b m , where n and m are natural numbers greater than 0;

[0055] A cloud management platform is set up, and various sensors are set up on the running track and rail vehicles, such as high-speed cameras, laser sensors, temperature sensors, etc., and each sensor is connected to the cloud data management platform for communication. It should be noted that each group of sensors on the running track is evenly distributed on the running track at a fixed spatial distance, and each carriage of the rail vehicle is equipped with a group of sensors;

[0056] The cloud management platform first obtains the optical image data of each sensor group at its location, and builds a corresponding 3D image model based on the optical image data. According to the actual urban rail and rail vehicle locations corresponding to each 3D image, each 3D image model is stitched together in sequence to obtain a 3D image model of urban rail transit.

[0057] Then, according to the distribution of each transfer station of the urban rail transit, the corresponding transfer station locations are marked on the three-dimensional image model of the urban rail transit;

[0058] Furthermore, before each rail vehicle travels, the staff uploads the corresponding travel event to the cloud management platform, and then the cloud management platform marks the starting position and the end position of each rail vehicle on the three-dimensional image model of the urban rail transit. The travel event includes the rail vehicle number and the number of the aisle it will pass through;

[0059] For rail vehicles that are about to travel or are in travel, the cloud management platform obtains the tracks that each rail vehicle is expected to pass through, and then sets the same data collection cycle for each rail vehicle and each group of sensors on the corresponding track;

[0060] Furthermore, when the rail vehicle is traveling along the track, each sensor collects relevant data of its location, and at the end of any data collection cycle, the cloud management platform integrates the data collected by each group of sensors to generate local historical operation data of the corresponding area or carriage;

[0061] It should be noted that the local historical operation data includes temperature change curves, optical video data, etc.;

[0062] Through the above process of generating local historical operation data, the cloud management platform generates all local operation data of each rail vehicle in each travel event in each data collection cycle;

[0063] When the rail vehicle running event ends, firstly, several historical data nodes are established, and then each local running data is sequentially input into the historical data node, and then each historical data node is connected according to the time sequence of each local running data of the rail vehicle and the running track, so as to obtain the vehicle historical data chain and the track historical data chain;

[0064] At the same time, the relative spatial positions of the rail vehicle and the travel track at each time node are matched and connected with the historical data nodes in the historical data chain of the vehicle and the historical data chain of the track at the same time node and the same spatial position, so as to obtain the historical travel data chain of the corresponding travel event, and mark the corresponding rail vehicle number, travel road number and the starting and ending time interval of the travel event. Embodiment 3

[0065] This embodiment is a further limitation of Embodiment 1, and Step S2 is implemented by the following process:

[0066] For each rail vehicle in different driving events, the historical driving data chain includes the optical video data of the rail vehicle and each driving track at different time nodes, and generates a dynamic rail vehicle model and a dynamic driving track model.

[0067] According to the historical data node matching relationship between the motor vehicle historical data chain and the track historical data chain in the historical driving data chain, the dynamic track motor vehicle model and the dynamic driving track model are mapped to the urban rail transit three-dimensional image model. It should be noted that the dynamic rail motor vehicle model and the dynamic driving track model change dynamically over time on the urban rail transit three-dimensional image model;

[0068] Then, various data in the historical driving data chain corresponding to the dynamic rail vehicle model and the dynamic driving track model are marked on the dynamic rail vehicle model and the dynamic driving track model;

[0069] Since the rail vehicle mainly experiences three processes of acceleration, constant speed and deceleration during its travel, the speed change curve of the rail vehicle in the corresponding historical travel data chain shows characteristic changes, that is, there are obvious curves of upslope, gentle, downslope and gentle periodic changes;

[0070] Therefore, each historical data node of the historical driving data chain is divided into several local historical driving data chains according to the driving track, and then the local historical driving data chains with the same track train number and driving road number but the start and end time intervals of the driving event are classified;

[0071] Establish several multi-dimensional coordinate systems, put the local historical driving data chain within the same category, corresponding to the same object, spatial position and the same type of data on the same multi-dimensional coordinate system, and obtain the individual spatial distances between different data;

[0072] Set the monomer space distance threshold, take each data as the central data in turn, and then judge the relationship between the monomer space distance between the remaining data and the central data and the monomer space distance threshold;

[0073] If the monomer space distance is greater than or equal to the monomer space distance threshold, it is judged that the corresponding data is associated with the central data;

[0074] If the monomer space distance is less than the monomer space distance threshold, it is judged that there is no correlation between the corresponding data and the central data;

[0075] Each central data is taken as the center of the relationship cluster in turn, and then the data associated with the central data is integrated to establish an associated data cluster. The number of data in each associated data cluster is compared, and the associated data cluster with the largest number of data is selected as the central associated data cluster;

[0076] Determine whether the monomer space distance between the relationship cluster center of each associated data cluster and the relationship cluster center of the central associated data cluster is greater than or equal to the monomer space distance threshold. If the judgment is true, merge the corresponding associated data cluster with the central associated data cluster to obtain a new central associated data cluster, but the relationship cluster center position of the original central associated data cluster remains unchanged;

[0077] Repeat the above operation of merging related data clusters until there are no related data clusters that meet the conditions and can be merged with the central related data cluster;

[0078] The remaining data not in the central associated data cluster is recorded as abnormal data, and then the corresponding central associated data cluster and abnormal data corresponding to the same object, spatial position and the same type of data in the local historical driving data chain within the same category are obtained, and the central associated data cluster and abnormal data are bound to the dynamic rail vehicle model and the dynamic driving track model at the corresponding time node. Embodiment 4

[0079] This embodiment is a further limitation of Embodiment 1, and step S3 is implemented by the following process:

[0080] Match the numbers of each rail vehicle with each running track in pairs, and retrieve the central associated data cluster and abnormal data of several corresponding data from the urban rail transit three-dimensional image model according to the matching results;

[0081] The data value of the center of the relationship cluster of the central associated data cluster is selected as the optimal operation achievement condition of the corresponding rail vehicle and the running track at the corresponding time node, and several data at the edge position of the central associated data cluster are recorded as the minimum operation achievement condition. At the same time, the corresponding maintenance plan is generated according to the abnormal problems of the rail vehicle and the running track corresponding to various abnormal data;

[0082] According to the number of matching results of each rail vehicle and each running track number, several running status particles and maintenance plan particles are established, and the numbers of the corresponding rail vehicle and the running track are marked on each running status particle, and the relevant optimal running conditions and minimum running conditions are included in the running status particles, and the maintenance plan and related abnormal data are input into the maintenance plan particles. Embodiment 5

[0083] This embodiment is a further limitation of Embodiment 1, and step S4 is implemented by the following process:

[0084] Acquire the real-time travel events of each rail vehicle, traverse the travel tracks that the rail vehicle will pass through in the three-dimensional image model of urban rail transit according to the real-time travel events, and then collect the real-time operation data of each rail vehicle and the travel tracks that it will pass through in real-time state;

[0085] Before the rail vehicle travels, firstly, according to the track number that the rail vehicle is going to pass, the real-time operation data of the track that the rail vehicle is going to pass is input into the corresponding operation status particle, and then it is judged whether each real-time data in each real-time operation data is within any data interval with the best operation achievement condition and the minimum operation achievement condition as the extreme value in the corresponding operation status particle;

[0086] If yes, no operation is performed; if no, the corresponding real-time data is abnormal data, and then the corresponding maintenance plan particle is matched according to the abnormal data, and the maintenance plan in the maintenance plan particle is obtained to repair the corresponding driving track;

[0087] When the rail vehicle is running, the real-time operation data of the rail vehicle and the track on which it is currently traveling is obtained, and a similar process to obtaining the maintenance plan for the track to be passed is adopted to obtain the maintenance plan of the rail vehicle and the track on which it is currently traveling at each time node in real time and execute it until the real-time driving event of the corresponding rail vehicle ends.

[0088] The present invention also discloses a vehicle-ground collaborative operation and maintenance system based on rail transit, comprising a rail transit data acquisition module, a historical data analysis module and a historical data analysis module;

[0089] The rail transit data acquisition module is used to collect several local historical operation data and real-time operation data of the running track and each rail vehicle through various sensors, and integrate various local historical operation data to establish a historical driving data chain according to the spatial position relationship between the running track and the rail vehicle at each time node;

[0090] The historical data analysis module is used to establish the central correlation data cluster and abnormal data of the data corresponding to any two running tracks and rail vehicles according to the historical running data chain, and then match each rail vehicle with each running track in pairs, and retrieve the corresponding central correlation data cluster and abnormal data according to the matching result, and then establish a number of running state particles and maintenance plan particles;

[0091] The historical data analysis module is used to match each real-time data in the real-time operation data with the corresponding operation status particles, and judge whether there is an abnormality in the rail vehicle or the running track according to the matching result, and then call the corresponding maintenance plan particle to obtain the maintenance plan and execute it.

[0092] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A vehicle-ground collaborative operation and maintenance method based on rail transit, characterized in that: The following steps are involved: Step S1: installing a variety of sensors on the urban rail and each train, collecting a number of local historical operation data of the running track and each train through the various sensors, and integrating each local historical operation data to establish a historical driving data chain according to the spatial position relationship between the running track and the train at each time node; Step S2: establishing a central correlation data cluster and abnormal data of various data corresponding to any two running tracks and rail vehicles according to the historical running data chain; The process of establishing the center-related data cluster includes: Each historical data node of the historical driving data chain is divided into several local historical driving data chains according to the driving track, and then the local historical driving data chains with the same track train number and driving track number are classified according to the start and end time interval of the driving event; Establish several multi-dimensional coordinate systems, put the local historical driving data chain within the same category, corresponding to the same object, spatial position and the same type of data on the same multi-dimensional coordinate system, and obtain the individual spatial distances between different data; Set the monomer space distance threshold, take each data as the central data in turn, and then judge the relationship between the monomer space distance between the remaining data and the central data and the monomer space distance threshold; According to the judgment results, each central data is taken as the center of the relationship cluster in turn, and then the data associated with the central data is integrated to establish a related data cluster, and the number of data in each related data cluster is compared, and the related data cluster with the largest number of data is selected as the central related data cluster; Determine whether the monomer space distance between the relationship cluster center of each associated data cluster and the relationship cluster center of the central associated data cluster is greater than or equal to the monomer space distance threshold. If the judgment is true, merge the corresponding associated data cluster with the central associated data cluster to obtain a new central associated data cluster, but the relationship cluster center position of the original central associated data cluster remains unchanged; Repeat the above operation of merging related data clusters until there are no related data clusters that meet the conditions and can be merged with the central related data cluster; Step S3, matching each rail vehicle with each running track in pairs, retrieving the corresponding central associated data cluster and abnormal data according to the matching results, and then establishing a number of running status particles and maintenance plan particles; The process of establishing the operating status particle and the maintenance plan particle includes: The data value of the center of the relationship cluster of the central associated data cluster is selected as the optimal operation achievement condition of the corresponding rail vehicle and the running track at the corresponding time node, and several data at the edge position of the central associated data cluster are recorded as the minimum operation achievement condition. At the same time, the corresponding maintenance plan is generated according to the abnormal problems of the rail vehicle and the running track corresponding to various abnormal data; According to the number of matching results of each rail vehicle and each running track number, several running state particles and maintenance plan particles are established, and the numbers of the corresponding rail vehicle and the running track are marked on each running state particle, and the relevant optimal running conditions and minimum running conditions are included in the running state particles, and the maintenance plan and related abnormal data are input into the maintenance plan particles; Step S4: collect the real-time operation data of each rail vehicle and the real-time operation data of the track that is expected to pass through, match each real-time data in the real-time operation data with the corresponding operation status particles, and judge whether there is an abnormality in the rail vehicle or the track according to the matching result, and then call the corresponding maintenance plan particle to obtain the maintenance plan and execute it.

2. The vehicle-ground collaborative operation and maintenance method based on rail transit according to claim 1 is characterized in that: The process of collecting local historical operation data includes: According to the distribution of various transfer stations of urban rail, the urban rail is divided into several running tracks, and each running track and rail vehicle is numbered respectively; Before each rail motor vehicle travels, a travel event of each rail motor vehicle is obtained, wherein the travel event includes the rail motor vehicle number and the number of the track through which the rail motor vehicle will travel; The same data collection cycle is set for each rail vehicle and each group of sensors on the corresponding running track. When the rail vehicle is running along the running track, each sensor collects relevant data at its location. At the end of any data collection cycle, the data collected by each group of sensors are integrated to generate local historical operation data of the corresponding area or carriage.

3. The vehicle-ground collaborative operation and maintenance method based on rail transit according to claim 2 is characterized in that: The process of establishing the historical driving data link includes: When the rail vehicle running event ends, several historical data nodes are established, and each local running data is input into the historical data node in sequence, and then each historical data node is connected to obtain the vehicle historical data chain and the track historical data chain according to the time sequence of each local running data of the rail vehicle and the running track; The historical data nodes at the same time node and the same spatial position in the EMU historical data chain and the track historical data chain are matched and connected to obtain the historical travel data chain of the corresponding travel event, and the corresponding rail EMU number, travel track number and the start and end time interval of the travel event are marked.

4. The vehicle-ground collaborative operation and maintenance method based on rail transit according to claim 1, characterized in that: The remaining data that is not in the central associated data cluster is recorded as abnormal data, and then the corresponding central associated data cluster and abnormal data corresponding to the same object, spatial position and type in the local historical driving data chain within the same category are obtained.

5. The vehicle-ground collaborative operation and maintenance method based on rail transit according to claim 1 is characterized in that: The process of determining whether there is an abnormality in the rail vehicle or the running track includes: Acquire the real-time travel events of each rail vehicle, traverse the travel tracks that the rail vehicle will pass through in the three-dimensional image model of urban rail transit according to the real-time travel events, and then collect the real-time operation data of each rail vehicle and the travel tracks that it will pass through in real-time state; Before the rail vehicle travels, according to the track number that the rail vehicle is going to pass, the real-time operation data of the track that the rail vehicle is going to pass is input into the corresponding operation status particle, and then it is determined whether each real-time data in each real-time operation data is within any data interval with the best operation achievement condition and the minimum operation achievement condition as extreme values ​​in the corresponding operation status particle; If yes, no operation is performed; if no, the corresponding real-time data is abnormal data, and then the corresponding maintenance plan particle is matched according to the abnormal data, and the maintenance plan in the maintenance plan particle is obtained to repair the corresponding driving track; When the rail vehicle is running, the real-time operation data of the rail vehicle and the track on which it is currently traveling is obtained, and the maintenance plan of the track to be passed is obtained in real time at each time node and the maintenance plan of the rail vehicle and the track on which it is currently traveling is executed until the real-time driving event of the corresponding rail vehicle ends.

6. A vehicle-ground collaborative operation and maintenance system based on rail transit, used to implement the vehicle-ground collaborative operation and maintenance method based on rail transit according to any one of claims 1 to 5, characterized in that: It includes rail transit data acquisition module, historical data analysis module and historical data analysis module; The rail transit data acquisition module is used to collect several local historical operation data and real-time operation data of the running track and each rail vehicle through various sensors, and integrate various local historical operation data to establish a historical driving data chain according to the spatial position relationship between the running track and the rail vehicle at each time node; The historical data analysis module is used to establish the central correlation data cluster and abnormal data of the data corresponding to any two running tracks and rail vehicles according to the historical running data chain, and then match each rail vehicle with each running track in pairs, and retrieve the corresponding central correlation data cluster and abnormal data according to the matching result, and then establish a number of running state particles and maintenance plan particles; The historical data analysis module is used to match each real-time data in the real-time operation data with the corresponding operation status particles, and judge whether there is an abnormality in the rail vehicle or the running track according to the matching result, and then call the corresponding maintenance plan particle to obtain the maintenance plan and execute it.

Images