Train operation scheduling method and device based on vehicle-ground integrated system and train

Abstract

The disclosure provides a train operation scheduling method based on a train-ground integrated system, which can be applied to the technical field of track vehicle operation and management. The train operation scheduling method comprises: obtaining state monitoring information of each component configured on a plurality of candidate trains, running mileage information of each component, maintenance record information of each component, historical running environment information of the plurality of candidate trains and a plurality of to-be-run line monitoring information; generating health state information of each candidate train based on the state monitoring information of each component, the running mileage information of each component, the maintenance record information of each component and the historical running environment information of each candidate train; generating state information of each to-be-run line based on the to-be-run line monitoring information; and generating an operation scheduling plan for each candidate train based on the health state information of each candidate train and the state information of each to-be-run line, so as to schedule each candidate train to run on each to-be-run line.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of rail vehicle operation and management, and more particularly, to a train operation scheduling method and device based on a train-ground integrated system and a train. BACKGROUND

[0002] Under the traditional mechanical and electrical system integration mode, the information between the rail vehicle system and the ground systems is independent, and the control is decentralized, which makes the efficiency of the collaborative operation and scheduling between the rail vehicle system and the ground systems relatively low. For example, the line scheduling, the section scheduling and the field scheduling each perform their own functions, the vehicle operation failure needs to be communicated and scheduled manually, the daily inspection of the vehicle is performed manually, there is no data interaction between the ground systems and the equipment, there is no data interaction between the vehicle operation and the ground maintenance, the train state information, the maintenance information and the running line state information are not fed back in time, multiple information islands are formed, and the efficiency of the train scheduling operation is affected. SUMMARY

[0003] Therefore, the present disclosure provides a train operation scheduling method and device based on a train-ground integrated system and a train.

[0004] According to an aspect of the present disclosure, a train operation scheduling method based on a train-ground integrated system is provided, including: obtaining state monitoring information of each component configured on a plurality of candidate trains, running mileage information of each component, maintenance record information of each component, historical running environment information of each candidate train and a plurality of to-be-run line monitoring information; generating health state information of each candidate train based on the state monitoring information of each component, the running mileage information of each component, the maintenance record information of each component and the historical running environment information of each candidate train; generating state information of each to-be-run line based on each to-be-run line monitoring information; and generating an operation scheduling plan for each candidate train based on the health state information of each candidate train and the state information of each to-be-run line, to schedule each candidate train to run on each to-be-run line.

[0005] According to an embodiment of the present disclosure, the health state information of each candidate train is generated based on the state monitoring information of each component, the running mileage information of each component, the maintenance record information of each component and the historical running environment information of each candidate train, including: extracting historical running environment information of each component from the historical running environment information of each candidate train; generating residual life information of each component based on the running mileage information of each component, the historical running environment information of each component and the maintenance record information of each component; and generating the health state information of each candidate train based on the residual life information of each component of the same candidate train and the state monitoring information of each component.

[0006] According to an embodiment of the present disclosure, based on the running mileage information of each component, the historical running environment information of each component and the maintenance record information of each component, the residual life information of each component is generated respectively, including: inputting the running mileage information of each component, the historical running environment information of each component and the maintenance record information of each component into the trained first target model, and outputting the residual life information of each component respectively; wherein the first target model is obtained by training the first initial model using the historical running mileage, the historical running environment and the historical maintenance record with the historical residual life of the sample component as the label.

[0007] According to an embodiment of the present disclosure, based on the residual life information of each component of the same candidate train and the state monitoring information of each component, the health state information of each candidate train is generated, including: inputting the residual life information of each component of the same candidate train and the state monitoring information of each component into the trained second target model, and outputting the health state information of each candidate train respectively; wherein the second target model is obtained by training the second initial model using the historical residual life and the historical monitoring state of the components of each sample train with the historical failure rate of each sample train as the label.

[0008] According to an embodiment of the present disclosure, the to-be-operated line monitoring information includes monitoring information of a catenary corresponding to each to-be-operated line, track monitoring information and tunnel monitoring information; based on the to-be-operated line monitoring information, the state information of each to-be-operated line is generated, including: inputting the monitoring information of each catenary corresponding to each to-be-operated line, each track monitoring information and each tunnel monitoring information into the trained third target model to generate the state information of each to-be-operated line; wherein the third target model is obtained by training the third initial model using the historical monitoring information of the catenary corresponding to the sample operating line, the historical monitoring information of the track and the historical monitoring information of the tunnel with the state of the sample operating line as the label.

[0009] According to an embodiment of the present disclosure, based on the health state information of each candidate train and the state information of each to-be-operated line, an operation scheduling plan for each candidate train is generated to schedule each candidate train to operate on each to-be-operated line, including: matching based on the health state information of each candidate train and the state information of each to-be-operated line to obtain an initial matching result; verifying the initial matching result based on the residual life information of each component in each candidate train to obtain a verification result; and in response to the verification result being passed, generating an operation scheduling plan based on the initial matching result.

[0010] Another aspect of the present disclosure provides a train operation scheduling device based on a train-ground integrated system, comprising an acquisition module, a first generation module, a second generation module and a third generation module. The acquisition module is configured to acquire state monitoring information of each component configured on a plurality of candidate trains, operation mileage information of each component, maintenance record information of each component, historical operation environment information of the plurality of candidate trains and a plurality of to-be-operated line monitoring information. The first generation module is configured to generate health state information of each candidate train based on the state monitoring information of each component, the operation mileage information of each component, the maintenance record information of each component and the historical operation environment information of each candidate train. The second generation module is configured to generate state information of each to-be-operated line based on each to-be-operated line monitoring information, and the third generation module is configured to generate an operation scheduling plan for each candidate train based on the health state information of each candidate train and the state information of each to-be-operated line, so as to schedule each candidate train to operate on each to-be-operated line.

[0011] Another aspect of the present disclosure provides a train, comprising: an acquisition module configured to acquire the operation scheduling plan obtained by the above method; and a generation module configured to generate an operation instruction based on the operation scheduling plan, so as to control the train to operate according to the operation scheduling plan.

[0012] Another aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory configured to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method as above.

[0013] Another aspect of the present disclosure provides a computer program product, comprising computer executable instructions configured to implement the method as above when executed.

[0014] According to the embodiments of the present disclosure, through the train-ground integrated system, the state monitoring information of each component configured on the train, the operation mileage information of each component, the maintenance record information of each component, the historical operation environment information of the plurality of candidate trains and the plurality of to-be-operated line monitoring information can be acquired in time. Based on the above information, the health state information of each candidate train and the state information of each to-be-operated line are generated correspondingly, and through the generated health state information and the state information of the to-be-operated line, a reasonable train operation scheduling plan is finally generated efficiently, so as to schedule each candidate train to operate on each to-be-operated line. The generation process of the above operation scheduling plan utilizes the data interaction of the vehicle and the ground daily inspection system, more reasonably and efficiently evaluates the health state of the train and the state of the operation line of the train, effectively shortens the time for formulating the operation scheduling plan, and improves the efficiency of the train operation scheduling. BRIEF DESCRIPTION OF DRAWINGS

[0015] The above and other objects, features and advantages of the present disclosure will become more apparent from the following description when taken in conjunction with the accompanying drawings, in which:

[0016] Figure 1 An exemplary system architecture to which a train operation scheduling method based on a train-ground integrated system according to embodiments of the present disclosure can be applied is schematically illustrated;

[0017] Figure 2 A working principle schematic diagram of a new daily inspection system according to embodiments of the present disclosure is schematically illustrated;

[0018] Figure 3 A flowchart of a train operation scheduling method based on a train-ground integrated system according to embodiments of the present disclosure is schematically illustrated;

[0019] Figure 4 A health state information generation process schematic diagram according to embodiments of the present disclosure is schematically illustrated;

[0020] Figure 5 A flowchart of a train operation scheduling method based on a train-ground integrated system according to embodiments of the present disclosure is schematically illustrated;

[0021] Figure 6 A structural block diagram of a train operation scheduling device based on a train-ground integrated system according to embodiments of the present disclosure is schematically illustrated;

[0022] Figure 7 A block diagram of an electronic device suitable for implementing a train operation scheduling method of a train-ground integrated system according to embodiments of the present disclosure is schematically illustrated. DETAILED DESCRIPTION

[0023] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It is to be understood, however, that the description is merely exemplary of the present disclosure, and is not intended to limit the scope of the present disclosure. In the following detailed description of the embodiments of the present disclosure, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. However, it will be apparent to one skilled in the art that the present disclosure can be practiced without these specific details. In other instances, well-known structures and functions have not been described in detail in order to avoid obscuring aspects of the present disclosure.

[0024] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the present disclosure. As used herein, the term "includes" and "comprising" and the like are meant to be inclusive in a manner that there are no exclusions of additional unrecited members excluding other non-recited members or additional and / or new members.

[0025] All terms used herein, including technical and scientific terms, have the meanings commonly understood by one of ordinary skill in the art unless otherwise defined. It should be noted that the use of any terms herein should not be interpreted to imply a certain technical detail or method unless otherwise defined. Technical and scientific terms used herein have the same meanings as commonly understood by one of ordinary skill in the art to which this specification belongs.

[0026] In the case of using expressions similar to "at least one of A, B, and C, etc.", it should be generally interpreted to include any of them alone, any combination of two or more of them, etc. (for example, "a system having at least one of A, B, and C" should include a system having A alone, a system having B alone, a system having C alone, a system having A and B together, a system having A and C together, a system having B and C together, and / or a system having A, B, and C together, etc.).

[0027] In embodiments of the present disclosure, the collection, updating, analysis, processing, use, transmission, provision, disclosure, storage, etc. of data (for example, including but not limited to user personal information) involved are in compliance with relevant laws and regulations, are used for legal purposes, and do not violate public order and good customs. In particular, necessary measures are taken to prevent illegal access to user personal information data, and to maintain user personal information security, network security, and national security.

[0028] In embodiments of the present disclosure, the authorization or consent of the user is obtained before the user's personal information is acquired or collected.

[0029] Overhaul refers to a maintenance process in which important parts of a vehicle are disassembled, cleaned, inspected, repaired, and the vehicle is comprehensively detected, debugged, and tested to restore the comprehensive performance of the vehicle to meet the requirements of the regulations and the quality acceptance standards. Daily inspection refers to a technical inspection of a train every day, which is performed on the whole train before it is uncoupled at a station or before it departs. This inspection ensures that the train is in good technical condition, and potential faults are found and handled in a timely manner to ensure the safe operation of the train.

[0030] Under the traditional electromechanical system integration mode, the information between the rail vehicle system and the ground system is independent, and the control is decentralized, so that the efficiency of the collaborative operation and scheduling between the rail vehicle system and the ground system is low. For example, the line dispatching, the section dispatching and the field dispatching each perform its own function, the vehicle operation fault needs the driver to communicate with the section and field dispatching through the telephone facsimile data; the vehicle daily inspection is performed manually; there is no trackside detection equipment, the daily inspection and the heavy maintenance have no data interaction, the vehicle operation data and the maintenance data have no interaction; the train state information, the maintenance information and the running line state information feedback are not timely. Therefore, the process of evaluating the train health state and the train running line state and scheduling the train based on the two evaluation results will consume a large amount of manpower and material resources and take a long time, and the efficiency of the train operation scheduling, fault judgment and maintenance is low.

[0031] Therefore, the embodiments of the present disclosure can obtain the state monitoring information of each component configured on the train, the running mileage information of each component, the maintenance record information of each component, the historical running environment information of a plurality of candidate trains and a plurality of to-be-operated line monitoring information in time through the vehicle-ground integrated system. Based on the above information, the health state information of each candidate train and the state information of each to-be-operated line are generated correspondingly, and through the generated health state information and the state information of the to-be-operated line, a reasonable train operation scheduling plan is finally generated efficiently to schedule each candidate train to run on each to-be-operated line. The generation process of the above operation scheduling plan utilizes the data interaction of the vehicle and the ground daily inspection and other systems, more reasonably and efficiently evaluates the health state of the train and the state of the train running line, effectively shortens the time for formulating the operation scheduling plan and improves the efficiency of the train operation scheduling.

[0032] Embodiments of the present disclosure relate to a vehicle system and a ground maintenance system in a vehicle-ground integrated system, taking vehicle operation and maintenance business as the core, using advanced technologies such as artificial intelligence, industrial internet, internet of things, operations research optimization and three-dimensional visualization, through real-time perception of the vehicle operation and maintenance state, combining with the maintenance process optimization of the key components of the vehicle, reorganizing the vehicle maintenance production mode, and re-planning the layout structure of the section and field, the section and field data and the vehicle data flow and information flow are connected, the vehicle data guides the section and field maintenance and operation, the maintenance and operation data support the vehicle life cycle management, and then a train operation scheduling method with strong operability and reliable strategy is generated, the efficiency of the train operation scheduling is improved, and support is provided for the standard specification of the new digital section and field construction.

[0033] Figure 1 An exemplary system architecture to which the train operation scheduling method based on the vehicle-ground integrated system can be applied according to an embodiment of the present disclosure is schematically shown. It should be noted that, Figure 1The shown is only an example of a system architecture to which the embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0034] As shown, the system architecture 100 according to the embodiment includes a vehicle system 110, a ground signal system 120, a ground maintenance system 130 and a ground application service platform 140. Figure 1

[0035] The vehicle system 110 includes a vehicle network subsystem 111, a vehicle signal device 112 and other related subsystems. During train operation, the data provided by the train includes but is not limited to the following: train operation mode, such as traction mode, braking mode, coasting mode, traction or braking level information, train running kilometers, train fault diagnosis information, train signal device PHM (Prognostics and Health Management) data and related diagnosis information, wherein the train PHM diagnosis data can be used to guide the daily inspection behavior.

[0036] The above data can be transmitted by the vehicle to the ATS (Automatic Train Supervision) subsystem of the ground signal system 120 through a wireless communication channel, and information superposition is performed on the obtained vehicle data. The data superimposed by the ground signal system 120 includes but is not limited to the following: train number information, train position information, train speed information.

[0037] The signal system is transmitted to the ground maintenance system 130, and the data provided by the ground maintenance system 130 to the ground application service platform includes but is not limited to the following: daily inspection diagnosis information, component replacement information, repair schedule information. It is further transmitted to the ground application service platform 140.

[0038] In addition, the data transmission path can also be changed, and the vehicle data and signal data are transmitted separately, and after being converged in the ground data center, they are sent to the ground maintenance system. Whether the ground data center is set or not does not affect the operation of the whole system.

[0039] The ground maintenance system 130 adds a new type of daily inspection system 131 and an intelligent management and control platform 132. The daily inspection system refers to a system for performing technical inspection on the train every day. The added part can be configured according to different application project scenarios, for example, the added new type of daily inspection system adds trackside vehicle body 360°, wheelset pantograph intelligent inspection robot, etc., which is not limited by the present disclosure.

[0040] According to the embodiments of the present disclosure, the state monitoring, maintenance records and other information of each component can be obtained through the new type of daily inspection system.​Figure 2 A schematic diagram of the working principle of a new daily inspection system according to an embodiment of the present disclosure is shown.

[0041] As shown in Figure 2 When the vehicle enters the throat area, the vehicle 360° appearance image detection can be triggered, the vehicle number recognition, speed measurement, and vehicle roof, side, and bottom image collection are performed, the vehicle appearance daily inspection point faults are identified, and the images and faults are remotely viewed by the daily inspection team personnel; after the vehicle enters the depot, the daily inspection operation is triggered, the daily inspection team personnel issues the automatic inspection instruction, the image collection and identification of the daily inspection points of the vehicle bottom running part are performed, and the images and faults are remotely viewed through the handheld terminal interaction; after the daily inspection team personnel view the fault images, the daily inspection faults and the remaining items are maintained and detected; after the daily inspection operation is completed, the maintenance information is fed back to the ground application service platform, and the train completes the train maintenance state record.

[0042] In the above interaction data, the vehicle operation mode, traction level information, brake level information, vehicle position, and vehicle speed data play an important role. Taking the vehicle state record related to the frame overhaul as an example, when the equipment is overhauled for multiple times, whether it occurs in the same area and / or the same speed level is judged according to the vehicle position and / or the vehicle speed, which is convenient for later equipment improvement and fault analysis. Among them, it can be used for fault coupling analysis, that is, the frame overhaul data and the vehicle operation data, vehicle health data, signal data, and daily inspection data corresponding to the frame overhaul data are transmitted to the frame overhaul equipment supplier for data coupling judgment and analysis at the fault moment.

[0043] Regarding the train operation and maintenance faults, the vehicle system can perform self-checking of the vehicle system according to the fault detection logic of each system, when the fault condition threshold is met, the fault is automatically reported and located to the specific equipment component, and the fault information is fed back to the ground for operation and maintenance. The ground system can monitor the state information of each equipment of the train according to the image recognition, when the fault condition threshold is met, the fault is automatically reported and located to the specific equipment component for operation and maintenance, for example, when the scratch of the high-voltage equipment between the train and the ground is more than 5 mm, the equipment fault is reported. In addition, since the train fault diagnosis data is not necessarily accurate, the train fault diagnosis data is not caused by the train fault, and it may be an indirect train fault caused by the track fault at the location of the train. As long as it does not run on this section of track, the fault will not occur, for example, the train reports “traction converter grounding fault”, which is caused by foreign matter hitting after inspection, at this time, the line can be checked by combining the train position at the time of fault reporting to guide the line to avoid the problem from occurring again without frame overhaul.

[0044] It should be understood that Figure 1 The number of systems, subsystems, and equipment in is only illustrative. The number of systems, subsystems, and equipment can be increased or decreased according to the actual application scene needs.

[0045] Figure 3 A flowchart of a train operation scheduling method based on a train-ground integrated system according to an embodiment of the present disclosure is shown schematically.

[0046] As shown in Figure 3 The method 300 includes operations S310-S340.

[0047] In operation S310, state monitoring information of each component configured on a plurality of candidate trains, operation mileage information of each component, maintenance record information of each component, historical operation environment information of the plurality of candidate trains, and a plurality of to-be-operated line monitoring information are acquired.

[0048] In operation S320, health state information of each candidate train is generated based on the state monitoring information of each component, the operation mileage information of each component, the maintenance record information of each component, and the historical operation environment information of each candidate train.

[0049] In operation S330, state information of each to-be-operated line is generated based on the plurality of to-be-operated line monitoring information.

[0050] In operation S340, an operation scheduling plan for each candidate train is generated based on the health state information of each candidate train and the state information of each to-be-operated line, to schedule each candidate train to operate on each to-be-operated line.

[0051] According to an embodiment of the present disclosure, the state monitoring information of each component configured on a train includes state monitoring information of components of each subsystem in a vehicle system, which can be state monitoring information of components such as a traction system, a power supply system, and a train-ground communication device, to realize state diagnosis of the components configured on the train. Specifically, the state monitoring information can be state monitoring information of components such as a train bogie, a car body, a door, a brake, a traction, an air conditioner, a broadcast, a smoke, an auxiliary system, a passenger information system, a train-ground wireless communication device, a train control and management system (TCMS) network itself, and a vehicle TCMS and other system network communication device. For example, the state monitoring information is “X train bogie has a crack”, “X train charger is faulty”, “X train traction device is normal”, and the like. The state monitoring information of each component can be acquired through vehicle self-checking, or can be acquired through ground system diagnosis, and information interaction can be performed between the two through train-ground communication.

[0052] The operation mileage information of each component can be obtained from the operation mileage information of the train, representing the operation mileage of each component, for example, the operation mileage of a P traction motor is 75200 kilometers. The operation mileage information of each component includes the operation mileage when the train is carrying passengers and the operation mileage when the train is empty.

[0053] The maintenance record information of each component includes the maintenance record information of each component and the maintenance information of each component, and the maintenance record and the maintenance record can be used as the basis for judging the remaining service life of the component. For example, the maintenance record information is "X train bogie is replaced due to cracks on October 25, 2018, and the replacement bogie is expected to have a service life of 10 years".

[0054] The running environment information of the train includes the road condition of the train running, the train running mode, the train traction, the brake level information and the like. For example, the historical running environment information of the train is "the train runs through 10 curves and 5 steep slopes", and the traction wheel and the bogie may be severely worn.

[0055] According to the embodiments of the present disclosure, the state monitoring information, the running mileage information, the maintenance record information and the historical running environment information of each candidate train are obtained by using the above-mentioned multi-parameter fusion calculation, and the health status evaluation of the train is realized.

[0056] The health status information of each candidate train can be obtained by using the analytic hierarchy process and the expert experience method to give the corresponding weight coefficients to the state monitoring data, the running mileage data, the maintenance record data and the running environment data of different components, and finally the data is added to obtain the health status score of each component. The health status score of the component with the smallest score is taken as the total score of the health status of the train, so as to quantitatively generate the health status information of each candidate train.

[0057] For example: according to the expert experience, the weights of the state monitoring, the running mileage, the maintenance record and the running environment of the traction motor are 0.8, 0.5, 0.6 and 0.4 respectively, and the values obtained after processing the state monitoring, the running mileage, the maintenance record and the running environment data of the traction motor are 90, 70, 60 and 85 respectively. Therefore, the health status score of each component can be obtained by adding the above-mentioned weight coefficients. The health status score of the bogie is 248. At this time, the lower 177 is selected as the total score of the health status of the train.

[0058] The health status information of each candidate train can also be obtained by grading the state monitoring data, the running mileage data, the maintenance record data and the running environment data of different components, and the minimum grade is taken as the health status grade of the train to evaluate the health status of the train.

[0059] For example, after the state monitoring data, the running mileage data, the maintenance record data, and the running environment data of the traction motor and the bogie are evaluated, the grades of the traction motor and the bogie are obtained as first grade and second grade, the first grade indicates that the component state is poor, and the second grade indicates that the component state is medium, and then a smaller grade of the first grade is selected as the health state evaluation of the train.

[0060] The above evaluation results can also be presented to the operation and maintenance personnel through visual charts such as column charts, line charts, statistical tables, and the like.

[0061] The to-be-operated line monitoring information can be obtained after the ground line state is evaluated by the on-board track maintenance detection system, and based on the to-be-operated line monitoring information, the state information of each to-be-operated line is generated, which can be used to represent whether the train to-be-operated line can normally operate, wherein the to-be-operated line monitoring information includes road condition information of the to-be-operated line, power usage information of the to-be-operated line, and the like.

[0062] According to the embodiments of the present disclosure, by one-to-one matching the obtained health state information of each candidate train and the state information of the to-be-operated line, the operation scheduling plan for each candidate train is generated. The matching of the health state information of the train and the state information of the to-be-operated line can be performed according to the generated matching list of the health state of the corresponding train and the state of the operating line, or can be performed through the mapping relationship table between the two, or can be performed through the matching rules formulated by expert experience.

[0063] For example, in the matching list, when the train health state is a grade a, it can be matched with the operating line state of grades a, b, and c. The health state information of the X train is "train health state is good, grade a", and the state information of the Y operating line is "train line state is grade b", then the health state information of the X train can be matched with the state information of the Y operating line, and the X train is scheduled to operate according to the Y operating line.

[0064] According to the embodiments of the present disclosure, through the vehicle-ground integrated system, the state monitoring information of each component configured on the train, the running mileage information of each component, the maintenance record information of each component, the historical running environment information of a plurality of candidate trains, and a plurality of to-be-operated line monitoring information can be obtained in time. Based on the above information, the health state information of each candidate train and the state information of each to-be-operated line are generated accordingly, and through the generated health state information and the state information of the to-be-operated line, a reasonable train operation scheduling plan is finally generated efficiently to schedule each candidate train to operate on each to-be-operated line. The generation process of the above operation scheduling plan utilizes the data interaction of the vehicle and the ground daily inspection system, and more reasonably and efficiently evaluates the health state of the train and the state of the operating line of the train, effectively shortens the time for formulating the operation scheduling plan, and improves the efficiency of the train operation scheduling.

[0065] According to an embodiment of the present disclosure, based on the state monitoring information of each component, the running mileage information of each component, the maintenance record information of each component, and the historical running environment information of each candidate train, the health state information of each candidate train is generated, including: extracting the historical running environment information of each component from the historical running environment information of each candidate train; based on the running mileage information of each component, the historical running environment information of each component, and the maintenance record information of each component, the residual life information of each component is generated respectively; and based on the residual life information of each component of the same candidate train and the state monitoring information of each component, the health state information of each candidate train is generated.

[0066] Figure 4 A schematic diagram of a health state information generation process according to an embodiment of the present disclosure is shown.

[0067] As shown in Figure 4 According to the historical running environment information 421 of the train, the historical running environment information 422 of the component can be extracted, which includes the frequency and duration of the component traction braking, the degree of strong impact or wear of the component, and the moisture condition of the component. The historical running environment information of the component and the running mileage information of the component can reflect the service life of the component to a certain extent. The number of times of maintenance and the maintenance condition of the component also affect the evaluation of the residual service life of the component. Therefore, the residual life information 425 of the component can be determined according to the historical running environment information 422 of the component, the running mileage information 423 of the component, and the maintenance record information 424 of the component.

[0068] For example, the corresponding life conversion coefficient can be determined according to the historical running environment information of the component, the running mileage information of the component, and the maintenance record information of the component, and then the wear life value is generated. The initial value of the factory predicted service life is subtracted from the wear life value to finally obtain the residual life value of the component.

[0069] The state monitoring information 426 of the component can be converted into a numerical value through data standardization processing, quantifying the state monitoring information of the component, and obtaining the state monitoring value of the component.

[0070] According to the residual life information 425 of the component and the state monitoring information 426 of the component, the health state information 427 of the train can be obtained. Specifically, the health state value of each component can be calculated according to the product of the residual life value of the component and the state monitoring value of the component, and the minimum value of the health state of each component of the train is taken as the health state value of the train.

[0071] According to an embodiment of the present disclosure, historical running environment information of components is extracted from historical running environment information of a train, and residual life information of each component is obtained according to running mileage information, historical running environment information and maintenance record information of the component, and health state information of the train is generated based on the residual life information and state monitoring information. The health state of the train is evaluated by the residual life of the component, which realizes more comprehensive and accurate evaluation and diagnosis of the train through the use of the component, prevents unexpected failure of the component, generates a corresponding train operation scheduling strategy, and improves the safety of vehicle operation scheduling.

[0072] According to an embodiment of the present disclosure, residual life information of each component is generated based on running mileage information of each component, historical running environment information of each component and maintenance record information of each component, including: inputting the running mileage information of each component, the historical running environment information of each component and the maintenance record information of each component into the trained first target model, and respectively outputting the residual life information of each component. Wherein, the first target model is obtained by training the first initial model with historical running mileage, historical running environment and historical maintenance record with the historical residual life of the sample component as the label.

[0073] The historical residual life of the sample component is the historical residual life of each historical scrapped component at different historical time points, and the size of the historical residual life is associated with the historical running mileage, the historical running environment and the historical maintenance record.

[0074] The first target model can be trained by machine learning algorithms such as neural network, random forest, support vector machine and the like, and the algorithms used can be adjusted according to specific circumstances, which is not limited in the present disclosure.

[0075] For example, a neural network algorithm is used, the historical running mileage, the historical running environment and the historical maintenance record of each sample component are input, the historical residual life of the sample component is taken as the output label, the first initial model is trained, when the error between the output residual life value and the true value is greater than a predetermined threshold, the parameters of the model are adjusted, so that the model can as accurately as possible fit the relationship between the input data and the output value, until the error between the predicted residual life value output by the model and the true label value meets the predetermined threshold, and the model parameter adjustment is terminated. After training and verification of a large amount of historical data of sample components, the first target model is obtained.

[0076] In addition, before using data to train and calculate the model, in order to improve the accuracy of the model calculation, the original data can be subjected to data cleaning, data standardization and the like, for example, abnormal data and repeated data can be deleted, the data can be normalized, the data can be converted to values between 0 and 1, and the like.

[0077] According to the embodiment of the present disclosure, by inputting the operation mileage information, the historical operation environment information and the maintenance record information of each component into the trained first target model, the residual life information of each component can be accurately and quickly calculated, the error caused by manual parameter setting is reduced, the accuracy of residual life calculation is improved, the health status of the train is effectively evaluated, and then the corresponding train operation scheduling strategy is generated, thereby improving the efficiency of train operation scheduling.

[0078] According to the embodiment of the present disclosure, based on the residual life information of each component of the same candidate train and the state monitoring information of each component, the health status information of each candidate train is generated, including: inputting the residual life information of each component of the same candidate train and the state monitoring information of each component into the trained second target model, and outputting the health status information of each candidate train respectively; wherein the second target model is obtained by training the second initial model using the historical residual life and the historical monitoring state of the components of each sample train with the historical failure rate of each sample train as a label.

[0079] According to the embodiment of the present disclosure, the historical failure rate of the sample train is the proportion of the failure times of each historical scrapped component at different historical time to the total number of uses, for example, the failure rate of the traction motor from t time to the time t n when scrapped is 1%.

[0080] Similar to the first target model, the second target model can also be trained by a machine learning algorithm such as neural network, random forest, support vector machine, etc., and the algorithm used can be adjusted according to the specific situation, which is not limited by the present disclosure. The specific training process and the data preprocessing process are similar to the first target model, which can be adjusted according to the actual situation, and will not be repeated here.

[0081] According to the embodiment of the present disclosure, by constructing the target model of the train health status information and inputting the residual life information of each component and the state monitoring information of each component of the same candidate train into the trained second target model, the health status information of each candidate train is quickly and accurately determined, the error of health status evaluation caused by experience error is reduced, the accuracy of train health status evaluation is improved, and then the corresponding train operation scheduling strategy is generated, thereby improving the efficiency of train operation scheduling.

[0082] According to embodiments of this disclosure, the monitoring information of the line to be operated includes the monitoring information of the overhead contact system, track monitoring information, and tunnel monitoring information corresponding to the line to be operated; based on the monitoring information of each line to be operated, the state information of each line to be operated is generated, including: inputting the monitoring information of each overhead contact system, each track monitoring information, and each tunnel monitoring information corresponding to each line to be operated into a trained third target model to generate the state information of each line to be operated; wherein, the third target model is obtained by training a third initial model using the state of the sample operating line as a label and utilizing the historical monitoring information of the overhead contact system, the historical monitoring information of the track, and the historical monitoring information of the tunnel corresponding to the sample operating line.

[0083] According to embodiments of this disclosure, the monitoring information for each overhead contact line includes the contact line voltage and current information. Track monitoring information includes the degree of track wear, track geometry, track spacing, and other information. Tunnel monitoring information includes tunnel environmental information, tunnel length, wind speed within the tunnel, and airflow pressure, and other information.

[0084] The status of the sample operating lines includes the status information of historical operating lines under the same operating route and speed. By inputting the monitoring information of each overhead contact line, each track monitoring information, and each tunnel monitoring information corresponding to each line to be operated into the trained third target model, the status information of each line to be operated can be generated.

[0085] Similar to the first and second objective models, the third objective model can also be trained using machine learning algorithms such as neural networks, random forests, and support vector machines. The algorithm used can be adjusted according to specific circumstances, and this disclosure does not impose any limitations on it. The specific training process and data preprocessing process are similar to the objective models mentioned above and can be adjusted according to actual conditions, so they will not be elaborated here.

[0086] According to embodiments of this disclosure, a third target model is trained using historical monitoring information of the overhead contact system, track, and tunnel corresponding to the sample running line. The third target model is then used to calculate and analyze the status information of the running line, which can reduce errors caused by manual assessment and judgment, improve the accuracy of train running line status assessment, and generate corresponding train operation scheduling strategies to improve the efficiency of train operation scheduling.

[0087] Figure 5 A flowchart illustrating a train operation scheduling method based on a vehicle-ground integrated system according to an embodiment of the present disclosure is shown.

[0088] like Figure 5 As shown, the method 500 includes operations S541 to S545.

[0089] In operation S541, the health state information of each candidate train and the state information of each to-be-operated line are matched to obtain an initial matching result.

[0090] In operation S542, the initial matching result is checked based on the residual life information of each component in each candidate train to obtain a checking result.

[0091] In operation S543, it is judged whether the checking result passes. If the judgment result is yes, operation S544 is performed; if the judgment result is no, operation S545 is performed.

[0092] In operation S544, an operation scheduling plan is generated based on the initial matching result.

[0093] In operation S545, an operation scheduling plan is generated by adjusting the initial matching result.

[0094] After the health state information of each candidate train and the state information of each to-be-operated line are sorted, the matching is performed. Specifically, the matching can be performed through a corresponding mapping relationship between the health state information and the state information of the operating line, for example: the mapping relationship is that the health state information is greater than 80 points, and the operating line state is good, and the health state information is less than 75 points, and no train is dispatched. If the generated health state information a is 85 points and the operating line state information b is good, a and b can be matched.

[0095] Since there may be the following problem in the initial matching result: the health state determined by the state of each component exactly meets the threshold value, but the matching operating line state is medium or below. At this time, the component cannot meet the requirements of the current operating line state. For example, the x component is seriously worn due to long service life, but the health state score is high because the historical operating environment of the x component is good, the maintenance frequency is low, and the maintenance frequency is high. However, the residual life of the component is not enough to meet the operating line with more curves and braking. Therefore, the initial matching result needs to be checked by the residual life information of the component to reduce the risk of the operation scheduling plan and improve the safety of the train operation scheduling.

[0096] When checking, the checking can be performed according to the checking rule. For example, when the operating line state is medium, the residual service life of the component is not less than 1 year. When the checking result passes, the operation scheduling plan can be generated based on the initial matching result. When the checking result does not pass, the matching result needs to be adjusted to meet the checking rule. After passing the checking, the corresponding operation scheduling plan is generated based on the adjusted matching result.

[0097] According to an embodiment of the present disclosure, the matching is performed according to the health state information of the train and the state information of the to-be-operated line, and a matching result can be quickly obtained. In addition, the initial matching result is verified by the residual life information of the components, and the possible safety hazards in the initial matching are comprehensively considered, and then a more reasonable and safe operation scheduling plan is generated.

[0098] Based on the train operation scheduling method based on the train-ground integrated system, the present disclosure further provides a train operation scheduling device based on the train-ground integrated system. The following will be described in detail Figure 6 with reference to the train operation scheduling device based on the train-ground integrated system according to an embodiment of the present disclosure.

[0099] Figure 6 An embodiment of the train operation scheduling device based on the train-ground integrated system according to the present disclosure is schematically shown in a structure block diagram.

[0100] As shown in Figure 6 the train operation scheduling device 600 based on the train-ground integrated system of the embodiment includes an acquisition module 610, a first generation module 620, a second generation module 630, and a third generation module 640.

[0101] The acquisition module 610 is configured to acquire state monitoring information of each component configured on a plurality of candidate trains, operation mileage information of each component, maintenance record information of each component, historical operation environment information of the plurality of candidate trains, and a plurality of to-be-operated line monitoring information. In an embodiment, the acquisition module 610 can be configured to perform the operation S310 described above, and details are not repeated here.

[0102] The first generation module 620 is configured to generate health state information of each candidate train based on the state monitoring information of each component, the operation mileage information of each component, the maintenance record information of each component, and the historical operation environment information of each candidate train. In an embodiment, the first generation module 620 can be configured to perform the operation S320 described above, and details are not repeated here.

[0103] The second generation module 630 is configured to generate state information of each to-be-operated line based on each to-be-operated line monitoring information. In an embodiment, the second generation module 630 can be configured to perform the operation S330 described above, and details are not repeated here.

[0104] The third generation module 640 is configured to generate an operation scheduling plan for each candidate train based on the health state information of each candidate train and the state information of each to-be-operated line, so as to schedule each candidate train to operate on each to-be-operated line. In an embodiment, the third generation module 640 can be configured to perform the operation S340 described above, and details are not repeated here.

[0105] According to an embodiment of the present disclosure, the first generation module comprises an extraction submodule, a residual life information generation submodule and a health state information generation submodule. The extraction submodule is configured to extract historical running environment information of each component from historical running environment information of each candidate train. The residual life information generation submodule is configured to generate residual life information of each component based on running mileage information of each component, historical running environment information of each component and maintenance record information of each component. The health state information generation submodule is configured to generate health state information of each candidate train based on residual life information of each component of the same candidate train and state monitoring information of each component.

[0106] According to an embodiment of the present disclosure, the residual life information generation submodule comprises a first target model application unit configured to input running mileage information of each component, historical running environment information of each component and maintenance record information of each component into a trained first target model to output residual life information of each component respectively; wherein the first target model is obtained by training a first initial model with historical residual life of a sample component as a label, historical mileage, historical running environment and historical maintenance record.

[0107] According to an embodiment of the present disclosure, the health state information generation submodule comprises a second target model application unit configured to input residual life information of each component of the same candidate train and state monitoring information of each component into a trained second target model to output health state information of each candidate train respectively; wherein the second target model is obtained by training a second initial model with historical failure rate of each sample train as a label, historical residual life of components of each sample train and historical monitoring state.

[0108] According to an embodiment of the present disclosure, the to-be-operated line monitoring information comprises monitoring information of a catenary corresponding to each to-be-operated line, track monitoring information and tunnel monitoring information. The second generation module comprises a third target model application submodule configured to input monitoring information of each catenary corresponding to each to-be-operated line, each track monitoring information and each tunnel monitoring information into a trained third target model to generate state information of each to-be-operated line; wherein the third target model is obtained by training a third initial model with state of a sample operating line as a label, historical monitoring information of a catenary corresponding to the sample operating line, historical monitoring information of a track and historical monitoring information of a tunnel.

[0109] According to an embodiment of the present disclosure, the third generation module comprises a matching sub-module, a checking sub-module and a responding sub-module. The matching sub-module is configured to match the health state information of each candidate train and the state information of each to-be-operated line to obtain an initial matching result. The checking sub-module is configured to check the initial matching result based on the residual life information of each component in each candidate train to obtain a checking result. The responding sub-module is configured to generate the operation scheduling plan based on the initial matching result in response to the checking result being passed.

[0110] Any one or more of the modules, sub-modules, units, sub-units according to the embodiments of the present disclosure, or at least part of functions of any one or more of the modules, sub-modules, units, sub-units can be implemented in one module. Any one or more of the modules, sub-modules, units, sub-units according to the embodiments of the present disclosure can be split into multiple modules for implementation. Any one or more of the modules, sub-modules, units, sub-units according to the embodiments of the present disclosure can be at least partially implemented as a hardware circuit, for example, a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on substrate, a system on package, an application specific integrated circuit (ASIC), or any other reasonable manner of hardware or firmware through integration or packaging of circuits, or in any one of software, hardware and firmware implementation manners or in a proper combination of any one or more of the implementation manners. Alternatively, one or more of the modules, sub-modules, units, sub-units according to the embodiments of the present disclosure can be at least partially implemented as computer program modules which can perform corresponding functions when the computer program modules are run.

[0111] For example, any multiple of the acquisition module 610, the first generation module 620, the second generation module 630 and the third generation module 640 can be combined in one module / unit / sub-unit for implementation, or any one of the modules / units / sub-units can be split into multiple modules / units / sub-units. Alternatively, at least part of the functions of one or more of the modules / units / sub-units can be combined with at least part of the functions of other modules / units / sub-units, and implemented in one module / unit / sub-unit. According to an embodiment of the present disclosure, at least one of the acquisition module 610, the first generation module 620, the second generation module 630 and the third generation module 640 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on substrate, a system on package, an application specific integrated circuit (ASIC), or any other reasonable manner that can be integrated or packaged by a circuit, etc. hardware or firmware, or in any one of software, hardware and firmware three implementation ways or in any appropriate combination of any several of them. Alternatively, at least one of the acquisition module 610, the first generation module 620, the second generation module 630 and the third generation module 640 can be at least partially implemented as a computer program module that can perform corresponding functions when the computer program module is run.

[0112] Embodiments of the present disclosure also include a train comprising an acquisition module and a generation module. The acquisition module is configured to acquire the operation scheduling plan obtained by the above method. The generation module is configured to generate an operation instruction based on the operation scheduling plan to control the train to operate according to the operation scheduling plan.

[0113] Figure 7 A block diagram of an electronic device suitable for implementing the train operation scheduling method of the train-ground integrated system according to an embodiment of the present disclosure is schematically shown. Figure 7 The electronic device shown is merely an example and should not bring any limitation to the functions and use range of the embodiments of the present disclosure.

[0114] As Figure 7As shown, the electronic device 700 according to embodiments of the present disclosure includes a processor 701 that can perform various appropriate actions and processes according to programs stored in a read only memory (ROM) 702 or loaded into a random access memory (RAM) 703 from a storage section 708. The processor 701 can include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor, and / or a related chipset, and / or a special purpose microprocessor (e.g., an application specific integrated circuit (ASIC)), and so on. The processor 701 can also include an on-board memory for cache use. The processor 701 can include a single processing unit or multiple processing units for executing different actions of the method processes according to embodiments of the present disclosure.

[0115] In the RAM 703, various programs and data required for the operation of the electronic device 700 are stored. The processor 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. The processor 701 performs various operations of the method processes according to embodiments of the present disclosure by executing the programs in the ROM 702 and / or the RAM 703. Note that the programs can also be stored in one or more memories other than the ROM 702 and the RAM 703. The processor 701 can also perform various operations of the method processes according to embodiments of the present disclosure by executing the programs stored in the one or more memories.

[0116] According to embodiments of the present disclosure, the electronic device 700 can also include an input / output (I / O) interface 705, which is also connected to the bus 704. The system 700 can further include one or more of the following components connected to the input / output (I / O) interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the input / output (I / O) interface 705 as necessary. A removable medium 711 such as a magnetic disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 710 as necessary, so that a computer program read out therefrom is installed into the storage section 708 as necessary.

[0117] According to an embodiment of the present disclosure, the method flow according to the embodiments of the present disclosure can be implemented as a computer software program. For example, the embodiments of the present disclosure include a computer program product comprising a computer program carrying computer program code for executing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network through the communication part 709, and / or installed from the detachable medium 711. When the computer program is executed by the processor 701, the above-mentioned functions defined in the system / apparatus according to the embodiments of the present disclosure are performed. According to an embodiment of the present disclosure, the system, apparatus, module, unit, etc. described above can be implemented by computer program modules.

[0118] The present disclosure also provides a computer readable storage medium, which can be included in the device / apparatus / system described in the above embodiments, or exist separately without being assembled into the device / apparatus / system. The above computer readable storage medium carries one or more programs, which when executed, implement the methods according to the embodiments of the present disclosure.

[0119] According to an embodiment of the present disclosure, the computer readable storage medium can be a non-volatile computer readable storage medium. For example, it can include but not limited to portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disc read-only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing. In the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus or device.

[0120] For example, according to an embodiment of the present disclosure, the computer readable storage medium can include the ROM 702 and / or the RAM 703 described above and / or one or more memories other than the ROM 702 and the RAM 703.

[0121] The embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for executing the methods provided by the embodiments of the present disclosure, which program code is used to make the electronic device implement the methods provided by the embodiments of the present disclosure when the computer program product is run on the electronic device.

[0122] When the computer program is executed by the processor 701, the above-mentioned functions defined in the system / apparatus according to the embodiments of the present disclosure are performed. According to an embodiment of the present disclosure, the system, apparatus, module, unit, etc. described above can be implemented by computer program modules.

[0123] In one embodiment, the computer program can be embodied on a tangible memory device, such as a compact disc, a Blu-ray disc, a flash drive, a floppy disc, a register, a hard drive, a DVD, a digital tape, a memory stick, or other machine readable medium. In another embodiment, the computer program can be transmitted in a signal over a network, including but not limited to the Internet, a local area network, a wide area network, a wired network, a wireless network, a magnetic field wave, an optical field wave, or other network via a network interface. The computer program can be downloaded or uploaded to and / or installed on the computing device 701 via the network interface 709. The computer program can also be embodied in a computer program product that can be distributed to a potential consumer of the computer program, such as a semiconductor manufacturer, a manufacturer of electronic devices, a distributor, or a retailer, to name a few. The computer program product can be in any of a variety of forms. For example, the computer program product can be a compact disc, a Blu-ray disc, a flash drive, a floppy disc, a register, a hard drive, a DVD, a digital tape, a memory stick, or other machine readable medium. The computer program product can be embodied in a computer program, which can be downloaded or uploaded to and / or installed on the computing device 701 via the network interface 709. The computer program product can also be distributed to a potential consumer of the computer program, such as a semiconductor manufacturer, a manufacturer of electronic devices, a distributor, or a retailer, to name a few. The computer program product can be in any of a variety of forms. For example, the computer program product can be a compact disc, a Blu-ray disc, a flash drive, a floppy disc, a register, a hard drive, a DVD, a digital tape, a memory stick, or other machine readable medium. The computer program product can be embodied in a computer program, which can be downloaded or uploaded to and / or installed on the computing device 701 via the network interface 709.

[0124] According to an embodiment of the present disclosure, the program code for execution by the computer program can be written in any combination of one or more programming languages, including a high-level procedural or object-oriented programming language, and / or an assembly or machine language. The programming language includes, but is not limited to, Java, C++, Python, “C” language, or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In the case involving a remote computing device, the remote computing device can be connected to the user computing device by any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, connected to the Internet by an Internet service provider).

[0125] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions. Those skilled in the art will understand that the features recited in the various embodiments and / or claims of this disclosure can be combined and / or combined in various ways, even if such combinations or combinations are not expressly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure may be combined and / or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0126] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this disclosure is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A train operation scheduling method based on a train-ground integrated system, comprising: obtaining state monitoring information of each component configured on a plurality of candidate trains, operation mileage information of each component, maintenance record information of each component, historical operation environment information of the plurality of candidate trains, and a plurality of to-be-operated line monitoring information; generating health state information of each of the candidate trains based on the state monitoring information of each component, the operation mileage information of each component, the maintenance record information of each component, and the historical operation environment information of each of the candidate trains; generating state information of each of the to-be-operated lines based on the to-be-operated line monitoring information; and obtaining an initial matching result based on the health state information of each of the candidate trains and the state information of each of the to-be-operated lines; verifying the initial matching result based on residual life information of each component in each of the candidate trains to obtain a verification result; and in response to the verification result being passed, generating an operation scheduling plan for each candidate train based on the initial matching result to schedule each candidate train to operate on each to-be-operated line. The generating of the health state information of each of the candidate trains based on the state monitoring information of each component, the operation mileage information of each component, the maintenance record information of each component, and the historical operation environment information of each of the candidate trains comprises: extracting historical operation environment information of each component from the historical operation environment information of each candidate train; 2. The method of claim 1, wherein, generating residual life information of each component based on the operation mileage information of each component, the historical operation environment information of each component, and the maintenance record information of each component; and generating the health state information of each of the candidate trains based on the residual life information of each component and the state monitoring information of each component of the same candidate train. The generating of the residual life information of each component based on the operation mileage information of each component, the historical operation environment information of each component, and the maintenance record information of each component comprises: inputting the operation mileage information of each component, the historical operation environment information of each component, and the maintenance record information of each component into a trained first target model to respectively output the residual life information of each component; 3. The method of claim 2, wherein, wherein the first target model is obtained by training a first initial model using historical operation mileage, historical operation environment, and historical maintenance record with historical residual life of a sample component as a label. The generating of the health state information of each of the candidate trains based on the residual life information of each component and the state monitoring information of each component of the same candidate train comprises: inputting the residual life information of each component and the state monitoring information of each component of the same candidate train into a trained second target model to respectively output the health state information of each candidate train; 4. The method of claim 2, wherein, wherein the second target model is obtained by training a second initial model using historical residual life and historical monitoring state of components of each sample train with historical failure rate of each sample train as a label. ​ ​ 5. The method of claim 1, wherein, The to-be-operated line monitoring information includes monitoring information of a catenary corresponding to the to-be-operated line, track monitoring information, and tunnel monitoring information; The state information of each to-be-operated line is generated based on the to-be-operated line monitoring information, including: The monitoring information of each catenary corresponding to each to-be-operated line, each track monitoring information, and each tunnel monitoring information are input into the third target model trained, to generate the state information of each to-be-operated line. The third target model is obtained by training a third initial model using historical monitoring information of a catenary corresponding to a sample operating line, historical monitoring information of a track, and historical monitoring information of a tunnel, with the state of the sample operating line as a label.

6. A train operation scheduling device based on a train-ground integrated system, comprising: an acquisition module configured to acquire state monitoring information of each component configured on a plurality of candidate trains, operating mileage information of each component, maintenance record information of each component, historical operating environment information of the plurality of candidate trains, and to-be-operated line monitoring information of a plurality of to-be-operated lines; a first generation module configured to generate health state information of each candidate train based on the state monitoring information of each component, the operating mileage information of each component, the maintenance record information of each component, and the historical operating environment information of each candidate train; a second generation module configured to generate state information of each to-be-operated line based on the to-be-operated line monitoring information; and a third generation module configured to obtain an initial matching result based on the health state information of each candidate train and the state information of each to-be-operated line; verify the initial matching result based on residual life information of each component in each candidate train to obtain a verification result; and in response to the verification result being passed, generate an operation scheduling plan for each candidate train based on the initial matching result to schedule each candidate train to operate on each to-be-operated line.

7. A train, comprising: an acquisition module configured to acquire the operation scheduling plan of any one of claims 1-5; a generation module configured to generate an operation instruction based on the operation scheduling plan to control the train to operate according to the operation scheduling plan.

8. An electronic device, comprising: one or more processors; a memory configured to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method of any one of claims 1-5.

9. A computer program product, wherein, The computer program product includes computer executable instructions for implementing the method of any one of claims 1-5 when executed. The computer program product includes computer executable instructions for implementing the method of any one of claims 1-5 when executed.

Images