Locomotive maintenance method, device, equipment, storage medium and program product

Abstract

The invention relates to a locomotive maintenance method, device and equipment, a storage medium and a program product. The method comprises the following steps: in response to a maintenance request for a target locomotive, generating a virtual maintenance scene according to locomotive attribute information of the target locomotive and scene information of a maintenance scene where the target locomotive is located, and storing a target maintenance part corresponding to the maintenance request, pose information of a maintainer in the maintenance scene and the virtual maintenance scene into a server; and sending the target maintenance component to at least two remote auxiliary ends associated with the target locomotive, so that each remote auxiliary end generates a locomotive maintenance scheme according to the target maintenance component, the pose information and the virtual maintenance scene, obtains the locomotive maintenance scheme fed back by each remote auxiliary end, and carries out locomotive maintenance processing on the target locomotive according to each locomotive maintenance scheme. By adopting the method, the reliability of troubleshooting can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of locomotive maintenance, and in particular to a locomotive maintenance method, device, equipment, storage medium and program product. Background Art

[0002] With the rapid development of the locomotive industry, in order to ensure the safety of locomotive operation, locomotive fault repair methods have emerged. Existing fault repair methods, limited by the complex structure of locomotive components and the complex environment of locomotive fault repair, generally use manual methods to repair locomotives.

[0003] However, since the manual maintenance method is related to the maintenance personnel's own fault maintenance ability and fault maintenance experience, relying solely on the manual maintenance method will reduce the reliability of fault maintenance. Summary of the Invention

[0004] Based on this, it is necessary to provide a locomotive maintenance method, device, equipment, storage medium and program product that can improve the reliability of fault repair in response to the above technical problems.

[0005] In a first aspect, the present application provides a locomotive maintenance method, comprising:

[0006] In response to a maintenance request for a target locomotive, generating a virtual maintenance scene based on locomotive attribute information of the target locomotive and scene information of a maintenance scene where the target locomotive is located;

[0007] Sending the target maintenance component corresponding to the maintenance request, the position information of the maintenance personnel in the maintenance scene, and the virtual maintenance scene to at least two remote assistant terminals associated with the target locomotive, so that each remote assistant terminal can generate a locomotive maintenance plan based on the target maintenance component, the position information, and the virtual maintenance scene;

[0008] Obtain the locomotive maintenance plan fed back by each remote auxiliary terminal, and perform locomotive maintenance on the target locomotive according to each locomotive maintenance plan.

[0009] In one embodiment, generating a virtual maintenance scene based on locomotive attribute information of a target locomotive and scene information of a maintenance scene where the target locomotive is located includes:

[0010] Selecting a target virtual locomotive model corresponding to the target locomotive from candidate virtual locomotive models according to locomotive attribute information of the target locomotive; wherein the candidate virtual locomotive model is constructed based on physical scan data of locomotive components;

[0011] According to the scene information of the maintenance scene where the target locomotive is located, a target virtual environment model corresponding to the scene information is selected from each candidate virtual environment model; wherein the candidate virtual environment model is constructed based on the three-dimensional point cloud data of the real maintenance environment;

[0012] The target virtual vehicle model and the target virtual environment model are fused to obtain a virtual maintenance scene.

[0013] In one embodiment, the target maintenance component corresponding to the maintenance request, the posture information of the maintenance personnel in the maintenance scene, and the virtual maintenance scene are sent to at least two remote auxiliary terminals associated with the target locomotive, including:

[0014] According to the target maintenance component corresponding to the maintenance request, the posture information of the maintenance personnel in the maintenance scene is checked for rationality;

[0015] If the rationality check passes, the target maintenance component corresponding to the maintenance request, the posture information of the maintenance personnel in the maintenance scene, and the virtual maintenance scene are sent to at least two remote auxiliary terminals associated with the target locomotive.

[0016] In one embodiment, based on the target maintenance component corresponding to the maintenance request, the posture information of the maintenance personnel in the maintenance scene is checked for rationality, including:

[0017] Generate dynamic maintenance action data of maintenance personnel based on their posture information at each moment in the maintenance scene; the posture information includes spatial positioning information and human joint information;

[0018] According to the difference between the standard maintenance action data and the dynamic maintenance action data corresponding to the target maintenance component, the rationality of the posture information of the maintenance personnel in the maintenance scene is verified.

[0019] In one embodiment, performing locomotive maintenance processing on a target locomotive according to each locomotive maintenance plan includes:

[0020] Conduct consistency checks on component handling opinions for target maintenance components in each locomotive maintenance plan;

[0021] If the consistency test fails, the locomotive maintenance plan with the highest priority feedback from the remote auxiliary terminal is used to perform locomotive maintenance on the target locomotive.

[0022] In one embodiment, in response to a maintenance request for a target locomotive, generating a virtual maintenance scene based on locomotive attribute information of the target locomotive and scene information of a maintenance scene where the target locomotive is located includes:

[0023] According to the abnormal characteristics of the target repair component, the abnormality handling plan corresponding to the abnormal characteristics of the component is obtained from the locomotive fault library; wherein the locomotive fault library is constructed based on the abnormality handling plans corresponding to various conventional locomotive fault conditions;

[0024] Obtaining locomotive operation data of the target locomotive after abnormality processing is performed on the target maintenance component based on the abnormality processing plan;

[0025] When it is determined based on the locomotive operation data that the target maintenance component has not returned to normal, in response to the maintenance request for the target locomotive, a virtual maintenance scene is generated based on the locomotive attribute information of the target locomotive and the scene information of the maintenance scene where the target locomotive is located.

[0026] In a second aspect, the present application further provides a locomotive maintenance device, comprising:

[0027] A scene generation module, configured to generate a virtual maintenance scene in response to a maintenance request for a target locomotive based on locomotive attribute information of the target locomotive and scene information of a maintenance scene where the target locomotive is located;

[0028] A data transmission module is used to transmit the target maintenance component corresponding to the maintenance request, the posture information of the maintenance personnel in the maintenance scene, and the virtual maintenance scene to at least two remote auxiliary terminals associated with the target locomotive, so that each remote auxiliary terminal can generate a locomotive maintenance plan based on the target maintenance component, posture information, and virtual maintenance scene;

[0029] The locomotive maintenance module is used to obtain the locomotive maintenance plans fed back by each remote auxiliary terminal, and perform locomotive maintenance processing on the target locomotive according to each locomotive maintenance plan.

[0030] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0031] In response to a maintenance request for a target locomotive, generating a virtual maintenance scene based on locomotive attribute information of the target locomotive and scene information of a maintenance scene where the target locomotive is located;

[0032] Sending the target maintenance component corresponding to the maintenance request, the position information of the maintenance personnel in the maintenance scene, and the virtual maintenance scene to at least two remote assistant terminals associated with the target locomotive, so that each remote assistant terminal can generate a locomotive maintenance plan based on the target maintenance component, the position information, and the virtual maintenance scene;

[0033] Obtain the locomotive maintenance plan fed back by each remote auxiliary terminal, and perform locomotive maintenance on the target locomotive according to each locomotive maintenance plan.

[0034] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0035] In response to a maintenance request for a target locomotive, generating a virtual maintenance scene based on locomotive attribute information of the target locomotive and scene information of a maintenance scene where the target locomotive is located;

[0036] Sending the target maintenance component corresponding to the maintenance request, the position information of the maintenance personnel in the maintenance scene, and the virtual maintenance scene to at least two remote assistant terminals associated with the target locomotive, so that each remote assistant terminal can generate a locomotive maintenance plan based on the target maintenance component, the position information, and the virtual maintenance scene;

[0037] Obtain the locomotive maintenance plan fed back by each remote auxiliary terminal, and perform locomotive maintenance on the target locomotive according to each locomotive maintenance plan.

[0038] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0039] In response to a maintenance request for a target locomotive, generating a virtual maintenance scene based on locomotive attribute information of the target locomotive and scene information of a maintenance scene where the target locomotive is located;

[0040] Sending the target maintenance component corresponding to the maintenance request, the position information of the maintenance personnel in the maintenance scene, and the virtual maintenance scene to at least two remote assistant terminals associated with the target locomotive, so that each remote assistant terminal can generate a locomotive maintenance plan based on the target maintenance component, the position information, and the virtual maintenance scene;

[0041] Obtain the locomotive maintenance plan fed back by each remote auxiliary terminal, and perform locomotive maintenance on the target locomotive according to each locomotive maintenance plan.

[0042] The above-mentioned locomotive maintenance method, device, equipment, storage medium and program product, by responding to the maintenance request for the target locomotive, generates a virtual maintenance scene according to the locomotive attribute information of the target locomotive and the scene information of the maintenance scene where the target locomotive is located, and sends the target maintenance components corresponding to the maintenance request, the posture information of the maintenance personnel in the maintenance scene and the virtual maintenance scene to at least two remote auxiliary terminals associated with the target locomotive, so that each remote auxiliary terminal can generate a locomotive maintenance plan based on the target maintenance components, posture information and virtual maintenance scene; then obtain the locomotive maintenance plan fed back by each remote auxiliary terminal, and perform locomotive maintenance processing on the target locomotive according to each locomotive maintenance plan. Compared with the related art, which only uses manual methods to repair locomotives, the above-mentioned method can effectively ensure the reliability of locomotive maintenance by combining remote auxiliary terminals with manual maintenance, supervising the reliability of manual maintenance, and providing a more comprehensive maintenance strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 1 is a flow chart of a locomotive maintenance method according to an embodiment;

[0045] Figure 2 A schematic diagram of a process for constructing a virtual maintenance scenario in one embodiment;

[0046] Figure 3 A schematic diagram of a rationality check process in one embodiment;

[0047] Figure 4 is a flow chart of a locomotive maintenance method according to another embodiment;

[0048] Figure 5 is a structural block diagram of a locomotive maintenance device in one embodiment;

[0049] Figure 6 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0051] With the rapid development of the locomotive industry, in order to ensure the safety of locomotive operation, locomotive fault repair methods have emerged. Existing fault repair methods, limited by the complex structure of locomotive components and the complex environment of locomotive fault repair, generally use manual methods to repair locomotives.

[0052] However, since the manual maintenance method is related to the maintenance personnel's own fault maintenance ability and fault maintenance experience, relying solely on the manual maintenance method will reduce the reliability of fault maintenance.

[0053] Based on this, in an exemplary embodiment, a locomotive maintenance method is provided, which is described by taking the application of the method to a locomotive maintenance terminal as an example, wherein the locomotive maintenance terminal can be a server or a terminal with powerful computing capabilities. Figure 1 As shown, the specific steps include:

[0054] S101 , in response to a maintenance request for a target locomotive, generating a virtual maintenance scene according to locomotive attribute information of the target locomotive and scene information of a maintenance scene where the target locomotive is located.

[0055] The target locomotive is a locomotive that requires maintenance; the maintenance request is a request for inspection and maintenance of the target locomotive; and the locomotive attribute information is basic configuration information of the target locomotive, which may include but is not limited to model information of the target locomotive.

[0056] A maintenance scenario is a maintenance scenario for a target locomotive. For example, it can include a maintenance scenario where the locomotive is in operation or in a maintenance depot. Scenario information refers to the environmental information surrounding the maintenance scenario. A virtual maintenance scenario is a virtual scenario generated based on the maintenance requirements of the target locomotive.

[0057] Optionally, when maintenance personnel need to inspect the target locomotive, they can input / select the locomotive attribute information of the target locomotive and the scene information of the maintenance scene where the target locomotive is located in the terminal associated with the locomotive maintenance end, and click the send button to generate a maintenance request containing the locomotive attribute information and the scene information, and send the maintenance request to the locomotive maintenance end.

[0058] Furthermore, after obtaining locomotive attribute information and scene information of the maintenance scene where the target locomotive is located from the maintenance request, the locomotive attribute information and scene information can be used as index information to search in a preset virtual scene library to obtain a virtual maintenance scene.

[0059] Alternatively, the locomotive attribute information and scenario information may be input into a trained virtual simulation model, and the virtual simulation model may generate a virtual maintenance scenario based on the locomotive attribute information and scenario information.

[0060] S102, the target maintenance component corresponding to the maintenance request, the posture information of the maintenance personnel in the maintenance scene and the virtual maintenance scene are sent to at least two remote auxiliary terminals associated with the target locomotive, so that each remote auxiliary terminal can generate a locomotive maintenance plan based on the target maintenance component, posture information and virtual maintenance scene.

[0061] Among them, the so-called target maintenance components are the locomotive components to be maintained; the so-called maintenance personnel are the personnel who maintain the target maintenance components; the so-called posture information is the action information and position information of the maintenance personnel when performing component maintenance; the so-called remote assistance terminal is the equipment terminal that can remotely assist in locomotive maintenance; the so-called locomotive maintenance plan is the specific steps for maintaining the target locomotive.

[0062] Optionally, in order to ensure the reliability of locomotive maintenance, when maintenance personnel are inspecting target maintenance components based on maintenance requirements, the posture information of the maintenance personnel in the maintenance scene can be obtained through the image acquisition equipment deployed in the maintenance scene; then, the target maintenance components, the posture information of the maintenance personnel and the virtual maintenance scene are sent to each remote auxiliary terminal at the same time.

[0063] It is understandable that in order to ensure the synchronization of data transmission, a virtual multi-person screen algorithm can be used to send the target maintenance components, the posture information of the maintenance personnel and the virtual maintenance scene to each remote auxiliary terminal at the same time, so that the expert personnel corresponding to each remote auxiliary terminal can obtain the above data at the same time.

[0064] Specifically, the communication data of all remote assistant terminals to be displayed on the same screen can be compared to filter and obtain the synchronization frame data of each remote assistant terminal. If the synchronization rate of the remote assistant terminal communication data is greater than or equal to the synchronization threshold, the communication data of the remote assistant terminal is determined to be synchronization frame data. After obtaining the network synchronization data based on the synchronization frame data, the network synchronization data can be compressed and differentiated based on the state change between the current frame and the previous frame.

[0065] Priority queues are divided according to the real-time requirements, importance, and compressibility of the data, and compression queues are divided according to the data type; then, the frame rate of the remote auxiliary end is dynamically downgraded based on the size relationship between the remote auxiliary end and the remote auxiliary end.

[0066] The network synchronization data of each remote auxiliary terminal is sent to all remote auxiliary terminals, so that the network synchronization data is processed by cubic Bezier curves and synchronized with polygon paths, and the data size of the network synchronization data is reduced by difference processing; then, the remote auxiliary terminal that receives the network synchronization data obtains the delay data according to the compression time, and then smoothes the data to be displayed according to the data synchronization type and the delay data.

[0067] Optionally, for each remote assistant, after receiving the target maintenance component, position information, and virtual maintenance scenario, the remote assistant can display the above data to the corresponding expert. The expert can analyze the maintenance method for the target maintenance component based on the virtual maintenance scenario and approve the maintenance method for the target maintenance component in the virtual maintenance scenario; and analyze the rationality of the maintenance personnel's maintenance actions based on the maintenance personnel's position information.

[0068] Furthermore, a locomotive maintenance plan can be generated based on the virtual maintenance scenario annotated with maintenance methods and optimization suggestions for maintenance actions. The locomotive maintenance plan is then fed back to the locomotive maintenance end.

[0069] S103, obtaining the locomotive maintenance plans fed back by each remote auxiliary terminal, and performing locomotive maintenance processing on the target locomotive according to each locomotive maintenance plan.

[0070] Optionally, after obtaining the locomotive maintenance plans fed back by each remote auxiliary terminal, each locomotive maintenance plan can be displayed through the display page associated with the locomotive maintenance terminal, so that maintenance personnel can perform locomotive maintenance on the target locomotive based on the maintenance methods annotated in each locomotive maintenance plan and optimization suggestions for the maintenance actions.

[0071] In the above locomotive maintenance method, by responding to the maintenance request for the target locomotive, a virtual maintenance scene is generated according to the locomotive attribute information of the target locomotive and the scene information of the maintenance scene where the target locomotive is located, and the target maintenance components corresponding to the maintenance request, the posture information of the maintenance personnel in the maintenance scene and the virtual maintenance scene are sent to at least two remote auxiliary terminals associated with the target locomotive, so that each remote auxiliary terminal can generate a locomotive maintenance plan based on the target maintenance components, posture information and virtual maintenance scene; then the locomotive maintenance plan fed back by each remote auxiliary terminal is obtained, and the target locomotive is subjected to locomotive maintenance processing according to each locomotive maintenance plan. Compared with the related art, which only uses manual methods to perform locomotive maintenance, the above method can effectively ensure the reliability of locomotive maintenance by combining remote auxiliary terminals with manual maintenance, supervising the reliability of manual maintenance, and providing a more comprehensive maintenance strategy.

[0072] In order to ensure the reliability of the construction of the virtual maintenance scene, based on the above embodiment, in the embodiment of the present application, an optional method for constructing the virtual maintenance scene is provided, such as Figure 2 As shown, the specific steps include:

[0073] S201 , selecting a target virtual locomotive model corresponding to the target locomotive from candidate virtual locomotive models according to locomotive attribute information of the target locomotive.

[0074] The candidate virtual locomotive model is constructed based on physical scan data of locomotive components. Furthermore, the physical scan data is data obtained by scanning the appearance of a real locomotive. The target virtual locomotive model is the virtual locomotive model corresponding to the target locomotive.

[0075] Optionally, candidate virtual locomotive models can be pre-built based on physical scan data of various locomotive types. These candidate virtual locomotive models and their corresponding locomotive attribute information can be associated and stored in a locomotive model library. Accordingly, upon receiving a maintenance request for a target locomotive, the locomotive model library can be queried based on the target locomotive's attribute information to retrieve the target virtual locomotive model corresponding to the target locomotive.

[0076] For example, a solid geometric model of a locomotive component may be generated based on the physical scanning data of the locomotive. Then, the solid geometric model of the locomotive component may be triangulated and segmented to extract the outer contour line of the locomotive component model.

[0077] Based on the outer contours of the locomotive component models, the locomotive component solid geometry models are traversed and feature extracted and classified and stored. The extracted features are then calculated using a quadratic error measurement algorithm to obtain an error measurement matrix and a triangle folding factor. Finally, based on the error measurement matrix and triangle folding factor, the locomotive component models are locally refined using a triangle neighborhood local analysis algorithm and a surface flatness analysis algorithm. This results in local angular and surface features of the locomotive component models, thereby generating the final virtual locomotive model.

[0078] S202 , selecting a target virtual environment model corresponding to the scene information from each candidate virtual environment model according to the scene information of the maintenance scene where the target locomotive is located.

[0079] The candidate virtual environment model is constructed based on the 3D point cloud data of the real maintenance environment, and the target virtual environment model is the virtual environment model corresponding to the maintenance scene where the target locomotive is located.

[0080] Optionally, candidate virtual environment models can be pre-constructed based on the 3D point cloud data of each maintenance environment. These candidate virtual environment models and their corresponding scene information can then be associated and stored in a scene model library. Accordingly, upon receiving a maintenance request for a target locomotive, the scene model library can be queried based on the scene information of the target locomotive's maintenance scene to retrieve the target virtual environment model corresponding to that scene information.

[0081] For example, a patch-based multi-view stereo matching growth algorithm (PMVS) can be used to obtain the overall skeleton point cloud and sub-region three-dimensional point cloud of the maintenance scene based on the overall image and local area images in multiple dimensions of the maintenance scene.

[0082] Based on the Particle Swarm Optimization-Iterative Closest Point (PSO-ICP) algorithm, the overall skeleton point cloud and the sub-region 3D point cloud are fused to obtain the scene point cloud data of the maintenance scene.

[0083] An adaptive hierarchical slicing processing algorithm is used to simplify the scene point cloud data to obtain simplified scene point cloud data. A point cloud normal estimation algorithm based on principal component analysis (PCA) and spatial lattice is used to process the simplified scene point cloud data to obtain a virtual environment model.

[0084] S203: Fusing the target virtual vehicle model and the target virtual environment model to obtain a virtual maintenance scene.

[0085] Optionally, after determining the target virtual vehicle model and the target virtual environment model, a fusion algorithm may be used to perform overall fusion processing on the target virtual vehicle model and the target virtual environment model, thereby obtaining a virtual maintenance scene.

[0086] For example, a multi-level asymptotic algorithm can be used to perform texture grading on the virtual vehicle model and virtual environment model, gradually generating texture layers of varying precision. Detailed textures are then generated and lightweighted based on these texture layers. Finally, using light probes, lighting information from multiple areas of the maintenance scene is collected and interpolated to dynamically assign lighting information to the virtual vehicle model and virtual environment model, generating a virtual maintenance scene that is more similar to the real scene.

[0087] In an embodiment of the present application, a virtual maintenance scene is constructed by selecting a target virtual locomotive model from each candidate virtual locomotive model based on locomotive attribute information, and selecting a target virtual environment model from each candidate virtual environment model based on scene information, thereby ensuring the reliability of the construction of the virtual maintenance scene.

[0088] In order to ensure the reliability of data transmission, based on the above embodiments, an optional method of data transmission is provided in an embodiment of the present application, specifically, according to the target maintenance component corresponding to the maintenance request, the rationality of the posture information of the maintenance personnel in the maintenance scene is checked; if the rationality check passes, the target maintenance component corresponding to the maintenance request, the posture information of the maintenance personnel in the maintenance scene and the virtual maintenance scene are sent to at least two remote auxiliary terminals associated with the target locomotive.

[0089] It is understandable that in order to avoid wasting resources of the remote assistance end, before transmitting data to the remote assistance end, the posture information of the maintenance personnel can be checked for rationality in combination with the target maintenance component corresponding to the maintenance request.

[0090] Optionally, a motion verification model for the target maintenance component can be determined based on the target maintenance component corresponding to the maintenance request; then, the posture information of the maintenance personnel in the maintenance scene is input into the trained motion verification model, and the motion verification model performs rationality verification based on the posture information and outputs the rationality verification result.

[0091] Furthermore, if the rationality check fails, the standard maintenance actions can be displayed on a display page associated with the locomotive maintenance terminal for reference by the maintenance personnel. If the rationality check passes, the target maintenance component corresponding to the maintenance request, the maintenance personnel's posture information in the maintenance scene, and the virtual maintenance scene can be subsequently sent to at least two remote auxiliary terminals associated with the target locomotive to obtain the locomotive maintenance plan fed back by the remote auxiliary terminals.

[0092] In an embodiment of the present application, by performing a rationality check on the posture information of the maintenance personnel in the maintenance scene before sending data to the remote assistance terminal, waste of resources of the remote assistance terminal can be effectively avoided.

[0093] In order to ensure the reliability of the rationality check, based on the above embodiment, an optional method of rationality check is provided in the embodiment of the present application, such as Figure 3 As shown, the specific steps include:

[0094] S301: Generate dynamic maintenance motion data of the maintenance personnel according to the posture information of the maintenance personnel at each moment in the maintenance scene.

[0095] The posture information includes spatial positioning information and human joint information. The so-called dynamic maintenance motion data refers to the motion data of the maintenance personnel in the dynamic maintenance state.

[0096] Optionally, for each moment, the maintenance personnel's maintenance action data at that moment can be determined based on the maintenance personnel's spatial positioning information and human joint information at that moment; then, dynamic maintenance action data can be generated based on the maintenance action data corresponding to each moment in the time sequence.

[0097] For example, after obtaining the maintenance worker's spatial positioning information and body joint information, a basic human body model of the maintenance worker can be constructed. After obtaining multiple maintenance worker action sequences, the basic frame action model of each action sequence is screened to obtain the maintenance worker's dynamic posture template.

[0098] The dynamic posture classification network corresponding to the dynamic posture template is used to perform action recognition on the posture information of the maintenance personnel, and the shape difference operator of the action sequence contained in the posture information is calculated. Then, a two-dimensional convolutional layer is used to extract the spatial dimension features of the shape difference operator, and the dynamic modeling of the action sequence is performed based on the spatial dimension features to obtain the dynamic maintenance action data of the maintenance personnel.

[0099] S302: Based on the difference between the standard maintenance action data and the dynamic maintenance action data corresponding to the target maintenance component, the posture information of the maintenance personnel in the maintenance scene is checked for rationality.

[0100] The so-called standard maintenance action data refers to the standard action data when maintenance personnel perform maintenance on maintenance components.

[0101] Optionally, standard maintenance action data for each maintenance component may be predetermined. After obtaining the standard maintenance action data corresponding to the target maintenance component from the predetermined standard maintenance action data, the dynamic maintenance action data may be compared with the standard maintenance action data for consistency, thereby obtaining the difference in action data.

[0102] Furthermore, the rationality check result of the posture information can be obtained based on the difference in the motion data. For example, if the difference in the motion data is large, it is determined that the rationality check of the posture information has failed; if the difference in the motion data is small, it is determined that the rationality check of the posture information has passed.

[0103] In an embodiment of the present application, the reliability of the posture data verification can be ensured by performing a rationality check on the posture information based on the difference between the standard maintenance action data and the dynamic maintenance action data corresponding to the target maintenance component at each sampling moment.

[0104] It is understandable that due to the existence of multiple remote auxiliary terminals, there may be inconsistent maintenance opinions among the remote auxiliary terminals. In this case, in order to ensure the reliability of the locomotive maintenance plan, based on the above embodiment, in the embodiment of the present application, an optional method for selecting a locomotive maintenance plan is provided, specifically, a consistency test is performed on the component processing opinions for the target maintenance components in each locomotive maintenance plan; if the consistency test fails, the locomotive maintenance plan fed back by the remote auxiliary terminal with the highest priority is used to perform locomotive maintenance processing on the target locomotive.

[0105] Optionally, component processing opinions for target maintenance components can be obtained from the locomotive maintenance plans fed back by each remote auxiliary terminal, and the component processing opinions of each remote auxiliary terminal can be analyzed using a large language model to determine whether the processing opinions between the remote auxiliary terminals are consistent.

[0106] If the consistency test passes, the locomotive maintenance plans provided by each remote assistant terminal can be displayed for reference by maintenance personnel based on the time the locomotive maintenance plans were obtained. If the consistency test fails, the locomotive maintenance plan provided by the remote assistant terminal with the highest priority can be used to perform maintenance on the target locomotive. The priority of the remote assistant terminal can be determined based on information such as the working hours and job level of the expert personnel corresponding to the remote assistant terminal.

[0107] In an embodiment of the present application, when the locomotive maintenance plans fed back by the remote auxiliary terminals are inconsistent, the locomotive maintenance plan fed back by the remote auxiliary terminal with the highest priority is used to perform locomotive maintenance on the target locomotive, thereby ensuring the reliability of the locomotive maintenance plan.

[0108] It can be understood that since there is a certain delay in the feedback from the remote auxiliary end, in order to improve the efficiency of locomotive maintenance, on the basis of the above embodiment, in the embodiment of the present application, an optional method of exception handling is provided, specifically, according to the component abnormality characteristics of the target maintenance component, the exception handling scheme corresponding to the component abnormality characteristics is obtained from the locomotive fault library; the locomotive operation data of the target locomotive after the target maintenance component is handled based on the exception handling scheme is obtained; when it is determined according to the locomotive operation data that the target maintenance component has not returned to normal, in response to the maintenance request for the target locomotive, a virtual maintenance scene is generated according to the locomotive attribute information of the target locomotive and the scene information of the maintenance scene where the target locomotive is located.

[0109] The locomotive fault database is constructed based on the corresponding exception handling solutions for various common locomotive fault conditions. Component anomaly characteristics are the anomaly characteristics of the target repair component, and the anomaly handling solution is the solution for addressing the component anomaly. Locomotive operating data is the operating data of the target locomotive after the anomaly handling process has been completed.

[0110] It is understood that a locomotive fault database can be pre-built based on common locomotive component failures and corresponding exception handling solutions. For example, locomotive component anomaly characteristics and corresponding locomotive fault cause data can be obtained from each locomotive fault case. Subsequently, a Monte Carlo algorithm can be used to perform quantitative and qualitative data analysis on the locomotive fault cause data to build a locomotive fault database based on a B+ tree index.

[0111] Alternatively, the component anomaly characteristics of the target repair component can be used to search the locomotive fault database to obtain an anomaly handling solution corresponding to the component anomaly characteristics. For example, based on a B+ tree indexing algorithm, the component anomaly characteristics of the target repair component can be used to match key information with common locomotive faults in the locomotive fault database, and the anomaly handling solution with the highest matching degree can be fed back.

[0112] Optionally, after the maintenance personnel adopt the abnormality handling solution to handle the abnormality of the target maintenance component, in order to determine whether the target maintenance component has returned to normal, the locomotive operation data of the target locomotive after the abnormality handling can be obtained.

[0113] Furthermore, the locomotive operation data can be compared with the standard operation data of the target locomotive in normal operation. If the comparison result is consistent, it is confirmed that the operation of the target maintenance component has returned to normal. At this time, there is no need to perform subsequent related processing on the remote auxiliary end.

[0114] If the comparison result is inconsistent, it is necessary to perform subsequent relevant processing of the remote auxiliary terminal, that is, in response to the maintenance request for the target locomotive, generate a virtual maintenance scene according to the locomotive attribute information of the target locomotive and the scene information of the maintenance scene where the target locomotive is located, and send the target maintenance components corresponding to the maintenance request, the posture information of the maintenance personnel in the maintenance scene and the virtual maintenance scene to at least two remote auxiliary terminals associated with the target locomotive, so that each remote auxiliary terminal can generate a locomotive maintenance plan based on the target maintenance components, posture information and virtual maintenance scene.

[0115] In the embodiment of the present application, by directly querying the handling method of conventional faults in the locomotive fault database, the efficiency of locomotive maintenance can be effectively improved.

[0116] Figure 4 FIG1 is a flow chart of a locomotive maintenance method in another embodiment. Based on the above embodiment, this embodiment provides an optional example of a locomotive maintenance method. Figure 4 The specific implementation process is as follows:

[0117] S401, according to the component abnormality characteristics of the target maintenance component, obtain the abnormality processing solution corresponding to the component abnormality characteristics from the locomotive fault database.

[0118] Among them, the locomotive fault database is constructed based on the abnormal handling solutions corresponding to various conventional locomotive fault conditions.

[0119] S402, obtaining locomotive operation data of the target locomotive after abnormality processing is performed on the target maintenance component based on the abnormality processing solution.

[0120] S403, when it is determined based on the locomotive operation data that the target maintenance component has not returned to normal, in response to the maintenance request for the target locomotive, a target virtual locomotive model corresponding to the target locomotive is selected from each candidate virtual locomotive model based on the locomotive attribute information of the target locomotive.

[0121] The candidate virtual locomotive models are constructed based on the physical scanning data of locomotive components.

[0122] S404 , selecting a target virtual environment model corresponding to the scene information from each candidate virtual environment model according to the scene information of the maintenance scene where the target locomotive is located.

[0123] Among them, the candidate virtual environment model is constructed based on the three-dimensional point cloud data of the real maintenance environment.

[0124] S405: Fusing the target virtual vehicle model and the target virtual environment model to obtain a virtual maintenance scene.

[0125] S406: Generate dynamic maintenance motion data of the maintenance personnel according to the posture information of the maintenance personnel at each moment in the maintenance scene.

[0126] Among them, posture information includes spatial positioning information and human joint information.

[0127] S407: Based on the difference between the standard maintenance action data and the dynamic maintenance action data corresponding to the target maintenance component, the posture information of the maintenance personnel in the maintenance scene is checked for rationality.

[0128] S408. If the rationality check passes, the target maintenance components corresponding to the maintenance request, the posture information of the maintenance personnel in the maintenance scene, and the virtual maintenance scene are sent to at least two remote auxiliary terminals associated with the target locomotive, so that each remote auxiliary terminal can generate a locomotive maintenance plan based on the target maintenance components, posture information, and virtual maintenance scene.

[0129] S409: Obtain the locomotive maintenance plans fed back by each remote auxiliary terminal, and perform consistency detection on the component processing opinions for the target maintenance components in each locomotive maintenance plan.

[0130] S410: If the consistency test fails, the locomotive maintenance plan fed back by the remote auxiliary terminal with the highest priority is adopted to perform locomotive maintenance on the target locomotive.

[0131] The specific process of the above S401-S410 can be found in the description of the above method embodiment. The implementation principle and technical effects are similar and will not be repeated here.

[0132] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0133] Based on the same inventive concept, embodiments of the present application also provide a locomotive maintenance device for implementing the locomotive maintenance method described above. The solution provided by this device is similar to the solution described in the method described above. Therefore, the specific limitations of one or more locomotive maintenance device embodiments provided below can be found in the above-described limitations of the locomotive maintenance method and will not be further elaborated here.

[0134] In an exemplary embodiment, Figure 5 As shown, a locomotive maintenance device 1 is provided, comprising: a scene generation module 10, a data sending module 20 and a locomotive maintenance module 30, wherein:

[0135] A scene generation module 10 is configured to generate a virtual maintenance scene in response to a maintenance request for a target locomotive based on locomotive attribute information of the target locomotive and scene information of a maintenance scene where the target locomotive is located;

[0136] The data transmission module 20 is used to transmit the target maintenance component corresponding to the maintenance request, the posture information of the maintenance personnel in the maintenance scene, and the virtual maintenance scene to at least two remote assistant terminals associated with the target locomotive, so that each remote assistant terminal can generate a locomotive maintenance plan based on the target maintenance component, the posture information, and the virtual maintenance scene;

[0137] The locomotive maintenance module 30 is used to obtain the locomotive maintenance plans fed back by each remote auxiliary terminal, and perform locomotive maintenance processing on the target locomotive according to each locomotive maintenance plan.

[0138] In an exemplary embodiment, the scene generation module 10 is specifically configured to:

[0139] According to the locomotive attribute information of the target locomotive, a target virtual locomotive model corresponding to the target locomotive is selected from each candidate virtual locomotive model; wherein the candidate virtual locomotive model is constructed based on the physical scanning data of the locomotive components; according to the scene information of the maintenance scene where the target locomotive is located, a target virtual environment model corresponding to the scene information is selected from each candidate virtual environment model; wherein the candidate virtual environment model is constructed based on the three-dimensional point cloud data of the real maintenance environment; the target virtual locomotive model and the target virtual environment model are fused to obtain a virtual maintenance scene.

[0140] In an exemplary embodiment, the data sending module 20 includes:

[0141] A verification unit is used to verify the rationality of the posture information of the maintenance personnel in the maintenance scene according to the target maintenance component corresponding to the maintenance request;

[0142] The data sending unit is used to send the target maintenance component corresponding to the maintenance request, the posture information of the maintenance personnel in the maintenance scene and the virtual maintenance scene to at least two remote auxiliary terminals associated with the target locomotive when the rationality check passes.

[0143] In an exemplary embodiment, the verification unit is specifically configured to:

[0144] Based on the posture information of the maintenance personnel at each moment in the maintenance scene, the dynamic maintenance motion data of the maintenance personnel is generated; wherein the posture information includes spatial positioning information and human joint information; according to the difference between the standard maintenance motion data and the dynamic maintenance motion data corresponding to the target maintenance component, the rationality of the posture information of the maintenance personnel in the maintenance scene is verified.

[0145] In an exemplary embodiment, the locomotive maintenance module 30 is specifically configured to:

[0146] The component handling opinions for the target maintenance components in each locomotive maintenance plan are checked for consistency; if the consistency test fails, the locomotive maintenance plan with the highest priority feedback from the remote auxiliary terminal is used to perform locomotive maintenance on the target locomotive.

[0147] In an exemplary embodiment, the locomotive maintenance device 1 further includes a solution acquisition module, wherein the solution acquisition module is specifically configured to:

[0148] According to the abnormal characteristics of the target maintenance component, an abnormality handling plan corresponding to the abnormal characteristics of the component is obtained from the locomotive fault library; wherein the locomotive fault library is constructed based on the abnormality handling plans corresponding to various conventional locomotive fault conditions; after the abnormality handling of the target maintenance component based on the abnormality handling plan is obtained, the locomotive operation data of the target locomotive is obtained; when it is determined according to the locomotive operation data that the target maintenance component has not returned to normal, in response to the maintenance request for the target locomotive, a virtual maintenance scene is generated according to the locomotive attribute information of the target locomotive and the scene information of the maintenance scene where the target locomotive is located.

[0149] Each module in the locomotive maintenance device described above may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0150] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless means, and the wireless means can be implemented via Wi-Fi, a mobile cellular network, near-field communication (NFC), or other technologies. When executed by the processor, the computer program implements a locomotive maintenance method. The display unit of the computer device is used to form a visually visible image, and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0151] Those skilled in the art will understand that Figure 6The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0152] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0153] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0154] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0155] It should be noted that the data involved in this application (including but not limited to locomotive operation data, etc.) are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0156] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), quantum computing-based data processing logic devices, artificial intelligence (AI) processors, and the like.

[0157] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0158] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A locomotive maintenance method, characterized in that: The method comprises: In response to a maintenance request for a target locomotive, generating a virtual maintenance scene based on locomotive attribute information of the target locomotive and scene information of a maintenance scene where the target locomotive is located; Sending the target maintenance component corresponding to the maintenance request, the posture information of the maintenance personnel in the maintenance scene, and the virtual maintenance scene to at least two remote assistant terminals associated with the target locomotive, so that each remote assistant terminal generates a locomotive maintenance plan based on the target maintenance component, the posture information, and the virtual maintenance scene; Obtain locomotive maintenance plans fed back by each remote auxiliary terminal, and perform locomotive maintenance processing on the target locomotive according to each locomotive maintenance plan.

2. The method according to claim 1, characterized in that The generating of a virtual maintenance scene according to the locomotive attribute information of the target locomotive and the scene information of the maintenance scene where the target locomotive is located includes: selecting a target virtual locomotive model corresponding to the target locomotive from candidate virtual locomotive models according to locomotive attribute information of the target locomotive; wherein the candidate virtual locomotive model is constructed based on physical scan data of locomotive components; According to the scene information of the maintenance scene where the target locomotive is located, a target virtual environment model corresponding to the scene information is selected from each candidate virtual environment model; wherein the candidate virtual environment model is constructed based on three-dimensional point cloud data of a real maintenance environment; The target virtual vehicle model and the target virtual environment model are fused to obtain a virtual maintenance scene.

3. The method according to claim 1, characterized in that The sending of the target maintenance component corresponding to the maintenance request, the posture information of the maintenance personnel in the maintenance scene, and the virtual maintenance scene to at least two remote auxiliary terminals associated with the target locomotive includes: Performing a rationality check on the posture information of the maintenance personnel in the maintenance scene according to the target maintenance component corresponding to the maintenance request; If the rationality check passes, the target maintenance component corresponding to the maintenance request, the posture information of the maintenance personnel in the maintenance scene, and the virtual maintenance scene are sent to at least two remote auxiliary terminals associated with the target locomotive.

4. The method according to claim 3, characterized in that The rationality check of the posture information of the maintenance personnel in the maintenance scene according to the target maintenance component corresponding to the maintenance request includes: Generate dynamic maintenance motion data of the maintenance personnel according to the posture information of the maintenance personnel at each moment in the maintenance scene; wherein the posture information includes spatial positioning information and human body joint information; According to the difference between the standard maintenance action data corresponding to the target maintenance component and the dynamic maintenance action data, the rationality of the posture information of the maintenance personnel in the maintenance scene is checked.

5. The method according to claim 1, wherein The performing locomotive maintenance processing on the target locomotive according to each locomotive maintenance plan includes: Conduct consistency testing on the component handling opinions for the target maintenance components in each locomotive maintenance plan; In the case that the consistency test fails, the locomotive maintenance plan fed back by the remote auxiliary terminal with the highest priority is adopted to perform locomotive maintenance processing on the target locomotive.

6. The method according to claim 1, characterized in that The step of generating a virtual maintenance scene in response to a maintenance request for a target locomotive according to locomotive attribute information of the target locomotive and scene information of a maintenance scene where the target locomotive is located includes: According to the component abnormality characteristics of the target maintenance component, an abnormality handling solution corresponding to the component abnormality characteristics is obtained from a locomotive fault library; wherein the locomotive fault library is constructed based on the abnormality handling solutions corresponding to various conventional locomotive fault conditions; Acquiring locomotive operation data of the target locomotive after performing abnormal processing on the target maintenance component based on the abnormal processing solution; When it is determined according to the locomotive operation data that the target maintenance component has not returned to normal, in response to a maintenance request for the target locomotive, a virtual maintenance scene is generated according to locomotive attribute information of the target locomotive and scene information of the maintenance scene where the target locomotive is located.

7. A locomotive maintenance device, characterized in that: The device comprises: A scene generation module, configured to generate a virtual maintenance scene in response to a maintenance request for a target locomotive based on locomotive attribute information of the target locomotive and scene information of a maintenance scene where the target locomotive is located; a data sending module, configured to send the target maintenance component corresponding to the maintenance request, the posture information of the maintenance personnel in the maintenance scene, and the virtual maintenance scene to at least two remote assistant terminals associated with the target locomotive, so that each remote assistant terminal can generate a locomotive maintenance plan based on the target maintenance component, the posture information, and the virtual maintenance scene; The locomotive maintenance module is used to obtain the locomotive maintenance plans fed back by each remote auxiliary terminal, and perform locomotive maintenance processing on the target locomotive according to each locomotive maintenance plan.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images