Rail maintenance information processing system and method, computer equipment, readable storage medium and program product

Abstract

The invention relates to a steel rail maintenance information processing system and method, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring state detection data, maintenance resource data, line operation data and environment data of a target steel rail; evaluating the health state of each section in the target steel rail according to the state detection data, and obtaining the maintenance priority of each section according to the health state evaluation result; taking minimization of construction cost, maximization of transportation efficiency and minimization of safety risk as optimization targets, and obtaining maintenance plan information of a target steel rail according to maintenance resource data, line operation data, environment data and the maintenance priority of each section; performing real-time risk detection on the target steel rail according to the state detection data and the environment data; and under the condition that the high-risk event is detected, the maintenance plan information of the target steel rail is adjusted, and the adjusted maintenance plan information is obtained. The method can improve the maintenance efficiency of the steel rail.

Description

Technical Field

[0001] This application relates to the field of rail transit technology, and in particular to a rail maintenance information processing system, method, computer equipment, computer-readable storage medium, and computer program product. Background Technology

[0002] To ensure the safe operation of rail transit, it is usually necessary to develop major and minor maintenance plans for the rails and carry out maintenance according to these plans. Related technologies typically rely on manual inspection and static data of the rails for plan development. However, the actual rail maintenance process is usually influenced by a combination of factors, including track condition, construction resource allocation, transportation demand, and real-time conditions. The existing maintenance planning methods often fail to fully consider these influencing factors, hindering the improvement of rail maintenance efficiency. Summary of the Invention

[0003] Therefore, it is necessary to provide a rail maintenance information processing system, method, apparatus, computer equipment, computer-readable storage medium, and computer program product to address the aforementioned technical problems.

[0004] In a first aspect, this application provides a rail maintenance information processing system, comprising: a data acquisition module, a data analysis module, a collaborative optimization module, and a plan adjustment module; the data acquisition module is connected to the data analysis module, the collaborative optimization module, and the plan adjustment module respectively; the collaborative optimization module is connected to the plan adjustment module and the data analysis module.

[0005] The data acquisition module is used to acquire the target rail's condition monitoring data, maintenance resource data, track operation data, and environmental data;

[0006] The data analysis module is used to assess the health status of each section in the target rail based on the status detection data, and to obtain the maintenance priority of each section based on the health status assessment results of each section.

[0007] The collaborative optimization module is used to obtain the maintenance plan information of the target rail based on the maintenance resource data, the line operation data, the environmental data, and the maintenance priority of each section, with the optimization objectives of minimizing construction costs, maximizing transportation efficiency, and minimizing safety risks.

[0008] The plan adjustment module is used to perform real-time risk detection on the target rail based on the status detection data and environmental data; and to adjust the maintenance plan information of the target rail when a high-risk event is detected, so as to obtain the adjusted maintenance plan information.

[0009] In one embodiment, the state detection data includes static attribute data and dynamic state data of the target rail; the data analysis module includes: a static analysis unit, a dynamic analysis unit, and a priority allocation unit; the static analysis unit is used to obtain the basic state assessment results of each section of the target rail based on the static attribute data using a random forest algorithm; the dynamic analysis unit is used to obtain the health risk prediction results of each section of the target rail in future time periods based on the dynamic state data using a temporal convolutional neural network; the priority allocation unit is used to obtain the health state assessment results of each section based on the basic state assessment results and the health risk prediction results of each section of the target rail; and to obtain the maintenance priority of each section based on the health state assessment results of each section.

[0010] In one embodiment, the collaborative optimization module includes a resource constraint modeling unit, a multi-objective optimization unit, and a conflict coordination unit. The resource constraint modeling unit is used to construct the spatiotemporal distribution constraints of maintenance resources for the target rail based on the maintenance resource data. The multi-objective optimization unit is used to utilize the Pareto front search algorithm to minimize construction costs, maximize transportation efficiency, and minimize safety risks as optimization objectives, and to obtain initial maintenance plan information for the target rail based on the line operation data, the environmental data, the maintenance priorities of each section, and the spatiotemporal distribution constraints of maintenance resources. The conflict coordination unit is used to adjust the initial maintenance plan information when the initial maintenance plan information indicates resource occupation conflicts between different sections, thereby obtaining the maintenance plan information for the target rail.

[0011] In one embodiment, the plan adjustment module is used to: increase the maintenance priority of the section corresponding to the high-risk event when a high-risk event is detected; and adjust the maintenance plan information of the target rail using a preemptive scheduling algorithm according to the maintenance priority of each section to obtain the adjusted maintenance plan information.

[0012] In one embodiment, the system further includes a monitoring and feedback module; the monitoring and feedback module includes edge nodes deployed at the maintenance and construction site of the target rail; the monitoring and feedback module is connected to the collaborative optimization module; the monitoring and feedback module is used to collect on-site data of the maintenance and construction site in real time using the edge nodes, and obtain execution deviation data based on the on-site data and the maintenance plan information; the monitoring and feedback module is also used to analyze the execution deviation data from each of the edge nodes to obtain the deviation analysis result of the target rail; the collaborative optimization module is used to adjust the maintenance plan information of the target rail according to the deviation analysis result to obtain the adjusted maintenance plan information.

[0013] In one embodiment, the system further includes a visualization interaction module; the visualization interaction module is connected to the data acquisition module, the collaborative optimization module, and the plan adjustment module; the visualization interaction module is used to visualize the maintenance construction progress information, maintenance resource distribution information, and risk event information of the target rail; the visualization interaction module is also used to visualize the impact of maintenance operations on the train operation of the target rail based on the line operation data and the maintenance plan information.

[0014] Secondly, this application also provides a method for processing rail maintenance information, including:

[0015] Acquire condition monitoring data, maintenance resource data, track operation data, and environmental data for the target rail;

[0016] The health status of each section in the target rail is evaluated based on the status detection data, and the maintenance priority of each section is obtained based on the health status evaluation results of each section.

[0017] With the optimization objectives of minimizing construction costs, maximizing transportation efficiency, and minimizing safety risks, the maintenance plan information for the target rail is obtained based on the maintenance resource data, the line operation data, the environmental data, and the maintenance priority of each section.

[0018] Based on the status detection data and environmental data, real-time risk detection is performed on the target rail; in the event of a high-risk event, the maintenance plan information of the target rail is adjusted to obtain the adjusted maintenance plan information.

[0019] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0020] Acquire condition monitoring data, maintenance resource data, track operation data, and environmental data for the target rail;

[0021] The health status of each section in the target rail is evaluated based on the status detection data, and the maintenance priority of each section is obtained based on the health status evaluation results of each section.

[0022] With the optimization objectives of minimizing construction costs, maximizing transportation efficiency, and minimizing safety risks, the maintenance plan information for the target rail is obtained based on the maintenance resource data, the line operation data, the environmental data, and the maintenance priority of each section.

[0023] Based on the status detection data and environmental data, real-time risk detection is performed on the target rail; in the event of a high-risk event, the maintenance plan information of the target rail is adjusted to obtain the adjusted maintenance plan information.

[0024] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0025] Acquire condition monitoring data, maintenance resource data, track operation data, and environmental data for the target rail;

[0026] The health status of each section in the target rail is evaluated based on the status detection data, and the maintenance priority of each section is obtained based on the health status evaluation results of each section.

[0027] With the optimization objectives of minimizing construction costs, maximizing transportation efficiency, and minimizing safety risks, the maintenance plan information for the target rail is obtained based on the maintenance resource data, the line operation data, the environmental data, and the maintenance priority of each section.

[0028] Based on the status detection data and environmental data, real-time risk detection is performed on the target rail; in the event of a high-risk event, the maintenance plan information of the target rail is adjusted to obtain the adjusted maintenance plan information.

[0029] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0030] Acquire condition monitoring data, maintenance resource data, track operation data, and environmental data for the target rail;

[0031] The health status of each section in the target rail is evaluated based on the status detection data, and the maintenance priority of each section is obtained based on the health status evaluation results of each section.

[0032] With the optimization objectives of minimizing construction costs, maximizing transportation efficiency, and minimizing safety risks, the maintenance plan information for the target rail is obtained based on the maintenance resource data, the line operation data, the environmental data, and the maintenance priority of each section.

[0033] Based on the status detection data and environmental data, real-time risk detection is performed on the target rail; in the event of a high-risk event, the maintenance plan information of the target rail is adjusted to obtain the adjusted maintenance plan information.

[0034] The aforementioned rail maintenance information processing system, method, computer equipment, computer-readable storage medium, and computer program product first acquire the target rail's condition monitoring data, maintenance resource data, line operation data, and environmental data. Based on the condition monitoring data, the health status of each section of the target rail is assessed, and the maintenance priority of each section is determined according to the health status assessment results. Then, with the optimization objectives of minimizing construction costs, maximizing transportation efficiency, and minimizing safety risks, maintenance plan information for the target rail is obtained based on the maintenance resource data, line operation data, environmental data, and the maintenance priorities of each section. Furthermore, real-time risk monitoring of the target rail is performed based on the condition monitoring data and environmental data. If a high-risk event is detected, the maintenance plan information for the target rail is adjusted to obtain the adjusted maintenance plan information. This solution integrates multi-source information such as target rail condition monitoring data, maintenance resource data, line operation data, and environmental data. It utilizes a multi-objective optimization algorithm to formulate maintenance plans, which can fully consider the impact of multiple factors and formulate maintenance plans that are both scientific and efficient. By introducing a dynamic risk assessment and plan adjustment mechanism based on real-time condition and environmental data, the maintenance plan can be adjusted in real time for sudden high-risk events to reduce the risk of maintenance delays, thereby effectively improving the maintenance efficiency of the target rail. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 This is a schematic diagram of the structure of a rail maintenance information processing system in one embodiment;

[0037] Figure 2 This is a schematic diagram of the rail maintenance information processing system in another embodiment;

[0038] Figure 3 This is a flowchart illustrating a rail maintenance information processing method in one embodiment;

[0039] Figure 4 This is a flowchart illustrating the process of obtaining the maintenance priority of each section in one embodiment;

[0040] Figure 5 This is a flowchart illustrating the process of obtaining maintenance plan information for the target rail in one embodiment.

[0041] Figure 6This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0043] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0044] In one embodiment, such as Figure 1 As shown, a rail maintenance information processing system is provided. The system includes: a data acquisition module, a data analysis module, a collaborative optimization module, and a plan adjustment module; the data acquisition module is connected to the data analysis module, the collaborative optimization module, and the plan adjustment module respectively; the collaborative optimization module is connected to the plan adjustment module and the data analysis module.

[0045] The data acquisition module is used to acquire the target rail's condition monitoring data, maintenance resource data, track operation data, and environmental data.

[0046] Specifically, the data acquisition module can be used to acquire real-time condition monitoring data, maintenance resource data, track operation data, and environmental data of the target rail. Condition monitoring data may include, but is not limited to, the track geometry parameters of the target rail, the location of rail damage, and the type of damage at each location; maintenance resource data may include, but is not limited to, the human resources, equipment resources, and material resources available for maintenance of the target rail, and the available closure time windows; track operation data may include, but is not limited to, the train timetable and historical maintenance records of the line corresponding to the target rail.

[0047] The data analysis module is used to assess the health status of each section of the target rail based on the condition detection data, and to obtain the maintenance priority of each section based on the health status assessment results.

[0048] The data analysis module can connect to the data acquisition module and acquire the condition monitoring data of the target rail collected by the data acquisition module. The target rail can be divided into multiple sections, each corresponding to a maintenance and construction unit. The data analysis module can assess the health status of each section of the target rail based on the condition monitoring data.

[0049] For example, the data analysis module can classify and assess the health status of each section based on the condition monitoring data of the target rail, and then determine the maintenance priority of each section based on the health status assessment results. For example, the health status assessment results can include multiple levels from high to low; the higher the health status assessment level of a section, the healthier that section of the rail is. Sections with lower health status assessment levels have higher maintenance priorities.

[0050] For example, the condition detection data of the target rail may include the segment condition detection data of each section of the target rail. The data analysis module can match the segment condition detection data of each segment with rules in a preset rule base, and obtain a first health status assessment result for each segment based on the matching results. The rules in this rule base may be set based on expert knowledge in the rail transit industry. Simultaneously, the data analysis module can also use a machine learning model to process the segment condition detection data of each segment and output a second health status assessment result for each segment. For example, the data analysis module can use one or more machine learning models to process the segment condition detection data of each segment. The machine learning models may be trained using segment condition detection data of each segment of multiple sample rails from historical time periods and the health status assessment results.

[0051] Specifically, the health status assessment results for each section of the target rail can be obtained by fusing the first and second health status assessment results. For example, the lowest-level result between the first and second health status assessment results can be used as the health status assessment result for that section. Alternatively, a weighted fusion method can be used to obtain the health status assessment results for each section.

[0052] The collaborative optimization module is used to obtain maintenance plan information for the target rail based on maintenance resource data, line operation data, environmental data, and maintenance priorities of each section, with the optimization goals of minimizing construction costs, maximizing transportation efficiency, and minimizing safety risks.

[0053] The collaborative optimization module can connect with the data acquisition module and the data analysis module. It can acquire maintenance resource data, line operation data, and environmental data collected by the data acquisition module, as well as the maintenance priorities of each section analyzed by the data analysis module. Subsequently, the collaborative optimization module can use a multi-objective solution method to obtain the maintenance plan information for the target rail based on this data, with the optimization objectives of minimizing construction costs, maximizing transportation efficiency, and minimizing safety risks.

[0054] For example, the collaborative optimization module can construct spatiotemporal distribution constraints for maintenance resources of the target rail based on maintenance resource data. Then, based on the target rail's line operation data, environmental data, and maintenance priorities for each section, it constructs overall construction cost functions, transportation efficiency functions, and safety risk assessment functions for the target rail. With the optimization objectives of minimizing construction costs, maximizing transportation efficiency, and minimizing safety risks, it searches for the optimal maintenance resource allocation method within the constraint space of the spatiotemporal distribution constraints using a multi-objective solution approach, thereby obtaining the maintenance plan information for the target rail. This maintenance plan information can include the maintenance construction period, allocated human resources, equipment resources, and material resources for each section of the target rail. For example, when resource allocation conflicts exist across sections in the obtained maintenance plan, the collaborative optimization module can also eliminate resource occupancy conflicts between different sections through iterative adjustments, thus obtaining the final maintenance plan information.

[0055] The plan adjustment module is used to perform real-time risk detection on the target rail based on status detection data and environmental data; when a high-risk event is detected, the maintenance plan information of the target rail is adjusted to obtain the adjusted maintenance plan information.

[0056] The planning adjustment module can be connected to the data acquisition module and the collaborative optimization module. It can acquire status detection data and environmental data from the data acquisition module, as well as maintenance plan information for the target rail from the collaborative optimization module.

[0057] When the data acquisition module updates the status detection data and environmental data, the plan adjustment module can perform real-time risk detection on the target rail based on the updated status detection data and environmental data, and adjust the maintenance plan information of the target rail when a high-risk event is detected. For example, a high-risk event may include severe rail damage (such as exceeding the limit for weld depth) or a sudden accident (such as a landslide causing line interruption). When a high-risk event is detected on the target rail, the maintenance plan information of the target rail can be adjusted to ensure that the high-risk section where the high-risk event occurred can be repaired in a timely manner. Thus, the adjusted maintenance plan information can be obtained.

[0058] For example, the target rail can be configured with backup resources (such as emergency maintenance teams, spare rail materials, etc.). The collaborative optimization module can allocate these backup resources to high-risk sections and issue temporary speed limit instructions to affected trains. For example, the collaborative optimization module can also increase the maintenance priority of high-risk sections (e.g., adjust their maintenance priority to the highest level) and adjust the maintenance plan information of the target rail using a preemptive resource scheduling algorithm to ensure that high-risk events can be responded to in a timely manner.

[0059] For example, when the data acquisition module updates the maintenance resource data, the plan adjustment module can also obtain the updated maintenance resource data. If a resource shortage is detected, the system optimization module is triggered to re-optimize the maintenance plan of the target rail based on the updated maintenance resource data, thereby obtaining the adjusted maintenance plan information.

[0060] The aforementioned rail maintenance information processing system integrates multi-source information such as target rail condition monitoring data, maintenance resource data, line operation data, and environmental data. By using a multi-objective optimization algorithm to formulate maintenance plans, it can fully consider the impact of multiple dimensions to formulate maintenance plans that are both scientific and efficient in execution. Furthermore, by introducing a dynamic risk assessment and plan adjustment mechanism based on real-time condition and environmental data, it can adjust the maintenance plan in real time in response to sudden high-risk events to reduce the risk of maintenance delays, thereby effectively improving the maintenance efficiency of the target rail.

[0061] In an exemplary embodiment, the state detection data includes static attribute data and dynamic state data of the target rail; the data analysis module includes: a static analysis unit, a dynamic analysis unit, and a priority allocation unit.

[0062] Specifically, the condition monitoring data of the target rail can include static attribute data and dynamic condition data. Static attribute data may include, but is not limited to, data such as the rail material and curve radius of each section of the target rail, while dynamic condition data can be data on the changes of the target rail over time, such as, but not limited to, detection data of cracks in various parts of the target rail.

[0063] The data analysis module can combine temporal convolutional neural networks and random forest algorithms to analyze the health status of each section of the target rail.

[0064] The static analysis unit is used to obtain the basic state assessment results of each section of the target rail based on static attribute data using the random forest algorithm.

[0065] The static attribute data of the rails can include segment static attribute data corresponding to each section. The static analysis unit can construct static attribute features corresponding to each section based on the segment static attribute data, and input these features into a basic state assessment model based on the random forest algorithm, thereby obtaining the basic state assessment results for each section output by the model. For example, the basic state assessment result can be a health score; the higher the health score of a section, the healthier the basic state of that section. The basic state assessment model can be obtained by training a training model based on the random forest algorithm using segment static attribute data and corresponding health scores from multiple sample rails over historical periods.

[0066] The dynamic analysis unit is used to obtain the health risk prediction results of each section of the target rail in the future time period based on the dynamic state data using a temporal convolutional neural network.

[0067] The dynamic status data of the rails can include segment dynamic status data corresponding to each section. For example, the segment dynamic status data for each section can include defect detection data (e.g., crack detection data, etc.) at multiple historical time points. The dynamic analysis unit can construct the corresponding temporal features of defects for each section based on the dynamic status data of each section, and input these features into a risk prediction model based on a temporal convolutional neural network. The model then predicts the defect development trend of each section in the future period (e.g., within the next 6 months or the next 12 months) and obtains the health risk prediction results for each section in the future period. For example, the health risk prediction results can be used to indicate the severity of defects in a section in the future period. The health risk prediction results can include multiple risk levels; the higher the risk level of a section, the more severe the defects in that section in the future period.

[0068] The risk prediction model can be trained using the dynamic status data of each section of multiple sample rails in the first historical period and the risk level in the second historical period, on a model constructed based on a temporal convolutional neural network. The dynamic status data of each section of the sample rails includes defect detection data for that section at multiple first historical time points within the first historical period, and the second historical period can be a future period relative to the first historical period.

[0069] The priority allocation unit is used to obtain the health status assessment results of each section based on the basic condition assessment results and health risk prediction results of each section in the target rail; and to obtain the maintenance priority of each section based on the health status assessment results of each section.

[0070] The priority allocation unit can be connected to the static analysis unit and the dynamic analysis unit. It can acquire the basic condition assessment results and health risk prediction results of each section in the target rail, and then merge them to obtain the health status assessment results of each section. For example, based on the health score in the basic condition assessment results and the risk level in the health risk prediction results, a health status assessment score for each section is calculated. Then, the level of the health status assessment result corresponding to the section is determined based on the range of this score. Specifically, the higher the risk level of the section, the lower the level of the health status assessment result; conversely, the higher the health score of the section, the higher the level of the health status assessment result. Subsequently, the maintenance priority of each section can be obtained based on the health status assessment results of each section, with sections having lower health status assessment result levels corresponding to higher maintenance priorities.

[0071] In this embodiment, by using the random forest algorithm to analyze the static attribute data of the target rail and using the temporal convolutional neural network to capture the long-term temporal evolution of rail damage, it is possible to take into account both the temporal dynamics and the influence of static factors, and achieve accurate assessment of the health status of each section of the target rail. This allows for setting accurate maintenance priorities for each section and provides reliable input for optimizing subsequent maintenance plans.

[0072] In one exemplary embodiment, the collaborative optimization module includes a resource constraint modeling unit, a multi-objective optimization unit, and a conflict coordination unit.

[0073] The resource constraint modeling unit is used to construct the spatiotemporal distribution constraints of maintenance resources for the target rail based on maintenance resource data.

[0074] Specifically, the resource constraint modeling unit can model the spatiotemporal distribution constraints of maintenance resources based on the maintenance resource data of the target rail. For example, the spatiotemporal distribution constraints of maintenance resources may include, but are not limited to: the allocated human resources shall not exceed the total number of human resources, the allocated equipment resources shall not exceed the total number of equipment resources, the materials used shall not exceed the total number of material resources, and the maintenance time of each section must be within the available closure time window, etc.

[0075] The multi-objective optimization unit is used to obtain the initial maintenance plan information of the target rail by using the Pareto front search algorithm to minimize construction costs, maximize transportation efficiency and minimize safety risks. Based on the line operation data, environmental data, maintenance priorities of each section and spatiotemporal distribution constraints of maintenance resources, it obtains the initial maintenance plan information of the target rail.

[0076] Among them, the multi-objective optimization unit can use the Pareto front search algorithm to solve the multi-objective optimization problem of the maintenance plan of the target rail within the constraints of the spatiotemporal distribution of maintenance resources.

[0077] For example, the multi-objective optimization unit can construct the feasible domain of the maintenance plan based on the spatiotemporal distribution constraints of maintenance resources, and construct construction cost functions, transportation efficiency functions, and safety risk assessment functions corresponding to the optimization objectives based on the track operation data, environmental data, and maintenance priorities of each section of the target rail. For example, the construction cost function may include labor costs, equipment depreciation costs, etc.; the transportation efficiency function may include a transportation efficiency loss rate calculated based on the number of minutes of train delays; and the safety risk assessment function may include a construction safety risk index obtained from environmental data and a track condition deterioration risk index obtained from the maintenance priorities of each section.

[0078] Subsequently, the multi-objective optimization unit can search for candidate solutions in the feasible region. Each candidate solution can correspond to a candidate maintenance plan for the target rail, which may include the maintenance construction period, allocated human resources, equipment resources, and material resources for each section of the target rail. The construction cost, transportation efficiency, and safety risk assessment value corresponding to each candidate solution can be calculated separately. Based on the Pareto optimality criterion, the candidate solutions are judged for non-dominance relationships, and the candidate solutions are updated based on the judgment results. This process gradually brings the candidate solutions closer to the Pareto optimal frontier that minimizes construction cost, maximizes transportation efficiency, and minimizes safety risk, ultimately yielding a set of Pareto optimal solutions.

[0079] After obtaining a set of Pareto optimal solutions, one solution can be selected as the initial maintenance plan information for the target rail according to preset rules. For example, the solution that is closest to the three optimization objectives overall can be selected as the initial maintenance plan information for the target rail based on the objective function values ​​of each Pareto optimal solution.

[0080] The conflict coordination unit is used to adjust the initial maintenance plan information when resource occupation conflicts exist between different sections, as indicated by the initial maintenance plan information, to obtain the maintenance plan information for the target rail.

[0081] The conflict coordination unit can verify whether there are cross-segment resource occupation conflicts in the initial maintenance plan information, such as checking for resource allocation conflicts between different sections being maintained simultaneously. When the initial maintenance plan information indicates that there are resource occupation conflicts between different sections of the target rail, the conflict coordination unit can adjust the initial maintenance plan information to eliminate resource occupation conflicts between different construction sections, thereby obtaining the maintenance plan information for the target rail. For example, adjusting the initial maintenance plan information can involve selecting another solution from the Pareto optimal solution as the initial maintenance plan information for the target rail, and then verifying it until a solution without cross-segment resource occupation conflicts is selected.

[0082] In this embodiment, the spatiotemporal constraint modeling of maintenance resources is combined with multi-objective optimization. Under the premise of ensuring transportation efficiency, the Pareto front search algorithm is used to balance cost and safety objectives, and the conflict coordination unit is used to dynamically solve the problem of cross-segment resource contention. This enables the quantitative trade-off of multi-dimensional objectives in the optimization solution of the maintenance plan, resulting in a maintenance plan with higher efficiency and feasibility.

[0083] In an exemplary embodiment, the plan adjustment module is used to: increase the maintenance priority of the section corresponding to the high-risk event when a high-risk event is detected; and adjust the maintenance plan information of the target rail using a preemptive scheduling algorithm according to the maintenance priority of each section to obtain the adjusted maintenance plan information.

[0084] The planning adjustment module can perform real-time risk detection on the target rail based on real-time updated status detection data and environmental data, and adjust the maintenance plan information of the target rail when a high-risk event is detected. For example, high-risk events may include serious rail damage (such as exceeding the limit of the damage depth) or sudden accidents (such as a landslide causing line interruption).

[0085] In the event of a high-risk event, the high-risk section affected by the event can be identified within the target rail based on its location. Subsequently, the maintenance priority of this high-risk section can be increased, and the maintenance plan information of the target rail can be adjusted using a preemptive scheduling algorithm based on the maintenance priorities of each section, resulting in an adjusted maintenance plan. For example, the plan adjustment module can set the maintenance priority of the high-risk section to the highest priority and check for available backup resources. If backup resources are available, the maintenance plan information of the target rail can be modified to prioritize the maintenance time of the high-risk section while satisfying the spatiotemporal distribution constraints of maintenance resources, and the backup resources can be allocated to the high-risk section. Simultaneously, a temporary speed limit instruction can be issued to affected trains. If no backup resources are available, the maintenance plan information of the target rail can be modified to prioritize the maintenance time of the high-risk section while satisfying the spatiotemporal distribution constraints of maintenance resources, and the maintenance resources of sections with lower maintenance priority and interruptible maintenance processes can be allocated to the high-risk section.

[0086] In this embodiment, by introducing a real-time data-driven maintenance plan adjustment mechanism, emergency plans can be quickly generated when sudden failures or resource changes are detected, which helps to improve the flexibility of the maintenance plan for the target rail and shorten the response time to high-risk events.

[0087] In one exemplary embodiment, the system further includes a monitoring feedback module; the monitoring feedback module includes edge nodes deployed at the maintenance and construction site of the target rail; the monitoring feedback module is connected to the collaborative optimization module.

[0088] The monitoring and feedback module is used to collect real-time field data from the maintenance and construction site using edge nodes, and to obtain execution deviation data based on the field data and maintenance plan information.

[0089] Specifically, the monitoring feedback module can be equipped with edge nodes, which can be used to perform data preprocessing and abnormal status identification locally on the construction site, and transmit execution deviation data back via 5G network.

[0090] For example, edge nodes can be deployed at the maintenance and construction site of the target rail. They can communicate with multiple sensors at the construction site to acquire real-time data collected by the sensors. For example, sensors can include, but are not limited to, embedded sensors (such as GNSS positioning and vibration detection sensors) mounted on construction machinery, and image acquisition equipment set up at the construction site. The edge nodes can acquire real-time data from the maintenance and construction site and process it to calculate key indicators of the maintenance and construction process (such as rail weld quality and tamping compaction). Simultaneously, the edge nodes can obtain the maintenance plan for the section where the maintenance and construction site is located based on maintenance plan information and determine the current maintenance plan progress to be achieved. Then, by comparing the real-time key indicators of the maintenance and construction site with the maintenance plan progress, execution deviation data between the construction plan and actual execution can be obtained. When the execution deviation data meets preset conditions (e.g., a progress delay > 5%), the edge node can transmit the execution deviation data back via a 5G network.

[0091] The monitoring and feedback module is also used to analyze the execution deviation data from each edge node to obtain the deviation analysis results of the target rail.

[0092] The monitoring and feedback module, after receiving execution deviation data from one or more edge nodes, can analyze it to obtain the deviation analysis results for the target rail, and then provide these results to the collaborative optimization module. For example, the deviation analysis results for the target rail may include the sections of the target rail where execution deviations currently exist, as well as the respective progress lag deviations of these sections.

[0093] The collaborative optimization module is used to adjust the maintenance plan information of the target rail based on the deviation analysis results, and obtain the adjusted maintenance plan information.

[0094] The collaborative optimization module, after receiving the deviation analysis results from the monitoring feedback module, can adjust the maintenance plan information of the target rail. For example, it can reallocate resources so that more maintenance resources can be allocated to the sections that are behind schedule, thereby obtaining the adjusted maintenance plan information.

[0095] In this embodiment, IoT technology is used to digitally track the construction process. Edge nodes perform data preprocessing and execution deviation identification locally on the construction site. By analyzing the overall execution deviation of the target rail, the deviation analysis results are fed back to the collaborative optimization module. This enables a closed-loop control of "planning-execution-correction" through the linkage between the monitoring feedback module and the collaborative optimization module. Moreover, in this embodiment, edge nodes only transmit data back when the execution deviation data meets preset conditions, which reduces data transmission volume, enables rapid alarm for abnormal progress, and avoids monitoring failure due to network latency.

[0096] In one exemplary embodiment, the system further includes a visualization interaction module; the visualization interaction module is connected to the data acquisition module, the collaborative optimization module, and the plan adjustment module.

[0097] Specifically, the rail maintenance information processing system may include a visual interaction module, which can be connected to the data acquisition module, collaborative optimization module, and planning adjustment module, and display the information provided by these modules through a visual interface.

[0098] The visualization and interaction module is used to visually display the maintenance and construction progress information, maintenance resource distribution information, and risk event information of the target rail.

[0099] The visualization and interaction module can obtain the current maintenance progress and resource distribution information of the target rail based on the maintenance plan information provided by the collaborative optimization module. It can also obtain the current risk event information of the target rail based on the high-risk event information provided by the plan adjustment module. Subsequently, the visualization and interaction module can display the target rail's construction progress Gantt chart, resource heat map, and risk warning information in a 3D geographic information display interface based on the maintenance progress, resource distribution, and risk event information.

[0100] For example, a Gantt chart of the construction progress of the target rail can be displayed by adding markers for the maintenance and construction periods of each section of the target rail in the 3D geographic information display interface; a resource heat map can be displayed by visually marking the spatial distribution of construction personnel and equipment at different times in the interface; and risk warning information can be displayed by marking the location and detection time of high-risk events in the interface.

[0101] The visualization and interaction module is also used to visualize the impact of maintenance operations on train operation on the target rail, based on line operation data and maintenance plan information.

[0102] The visualization and interaction module can also visualize the impact of maintenance operations on train operation on the target rail, based on line operation data provided by the data acquisition module and the latest maintenance plan information provided by the collaborative optimization module or the plan adjustment module. For example, the visualization and interaction module can support virtual reality immersive display functions, which can construct a virtual operating environment for the target rail and simulate the impact of maintenance operations on the passing speed and signal interlocking of adjacent lines during specific construction periods (such as nighttime track maintenance windows).

[0103] For example, the visualization interaction module can also obtain information on multiple candidate maintenance plans (e.g., different Pareto optimal solutions) provided by the collaborative optimization module, and simulate the impact of different maintenance plans on train operation respectively, so as to help managers intuitively evaluate the operational impact of different plans and reduce decision-making bias.

[0104] In this embodiment, by visually displaying the maintenance construction progress information, maintenance resource distribution information, and risk event information of the target rail, and simulating the impact of maintenance operations on the train operation of the target rail, managers can intuitively understand the spatial relationship between construction personnel and equipment, as well as the impact of maintenance plans on the operation of the target rail. This allows for the development of efficient and feasible maintenance plans without the need for multiple on-site surveys.

[0105] In one exemplary embodiment, such as Figure 2 As shown, a rail maintenance information processing system is provided.

[0106] Specifically, such as Figure 2 As shown, the rail maintenance information processing system in this embodiment may include a data acquisition module, a data analysis module, a collaborative optimization module, a plan adjustment module, a monitoring feedback module, a visualization interaction module, and a data security gateway module. The modules in the system can be connected through a system bus.

[0107] The data acquisition module can acquire real-time status monitoring data, maintenance resource data, line operation data, and environmental data of the target rail, as well as historical maintenance records of the target rail. It can aggregate multi-source heterogeneous data of the target rail (such as rail damage location, construction resource scheduling constraints, and train timetables) to solve the problem of data fragmentation in the traditional manual experience-based approach.

[0108] The data analysis module can assess the health status of each section of the target rail based on a preset rule base and a machine learning model, and determine the maintenance priority of each section based on the health status assessment results. For example, the data analysis module can match the section status detection data of each section with rules in the preset rule base, and obtain a first health status assessment result for each section based on the matching results. Simultaneously, the data analysis module can also process the section status detection data of each section using a machine learning model and output a second health status assessment result for each section. Specifically, the data analysis module can use a basic status assessment model based on a random forest algorithm to obtain the basic status assessment results for each section based on its static attribute data, and a risk prediction model based on a temporal convolutional neural network to obtain the health risk prediction results for each section in the future based on its dynamic status data. Combining the basic status assessment results and the health risk prediction results, the second health status assessment results for each section are obtained. Subsequently, the health status assessment results of each section of the target rail can be fused together with the first and second health status assessment results to obtain the health status assessment results of each section, and the maintenance priority of each section can be obtained based on the health status assessment results. Thus, by adopting a rule-based and machine learning fusion mechanism, industry expert knowledge can be preserved, and the basic health status of each section can be analyzed based on static parameters (such as rail material and curve radius). Furthermore, the long-term temporal evolution of rail damage (such as the seasonal variation of crack propagation rate) can be captured through temporal feature analysis. This allows for a balance between temporal dynamics and the influence of static factors, improving the prediction accuracy of rail defects (especially defects in complex sections such as turnouts and small-radius curves), enabling proactive early warning of maintenance needs for each section, and providing reliable input for optimizing subsequent maintenance plans.

[0109] The collaborative optimization module constructs spatiotemporal distribution constraints of maintenance resources for the target rail based on maintenance resource data. Then, using the Pareto front search algorithm, it optimizes to minimize construction costs, maximize transportation efficiency, and minimize safety risks. Based on line operation data, environmental data, maintenance priorities for each section, and spatiotemporal distribution constraints of maintenance resources, it obtains initial maintenance plan information for the target rail (e.g., a preliminary major and minor repair plan). If the initial maintenance plan indicates resource conflicts between different sections, it adjusts the initial maintenance plan information to obtain the final maintenance plan for the target rail. This module combines spatiotemporal constraint modeling of maintenance resources with multi-objective optimization. While ensuring transportation efficiency, it balances cost and safety objectives using the Pareto front search algorithm and dynamically resolves cross-section resource contention issues. This allows for a quantitative trade-off of multi-dimensional objectives in the optimization of the maintenance plan, resulting in a more efficient and feasible maintenance plan.

[0110] The planning adjustment module receives real-time updated status and environmental data to perform real-time risk detection on the target rail. Upon detecting a high-risk event, it adjusts the maintenance plan information for the target rail, resulting in a revised maintenance plan. Specifically, when a high-risk event is detected, the planning adjustment module automatically increases the maintenance priority of the corresponding section and forcibly allocates maintenance resources (e.g., by allocating reserve resources or through a preemptive resource scheduling algorithm), while simultaneously issuing temporary speed limit instructions to affected trains. This module, by introducing a real-time data-driven re-optimization mechanism, can quickly generate contingency plans when sudden faults or resource changes are detected, improving the flexibility of the target rail maintenance plan and effectively shortening the response time to high-risk events.

[0111] The monitoring and feedback module can collect real-time on-site data from the maintenance and construction site via IoT devices. Using edge nodes, it obtains execution deviation data based on the on-site data and maintenance plan information. Then, based on the execution deviation data returned by each edge node, it obtains the deviation analysis results for the target rail and feeds them back to the collaborative optimization module, enabling the module to adjust the maintenance plan information for the target rail. Thus, the monitoring and feedback module can achieve digital tracking of the construction process through IoT, using edge nodes to complete data preprocessing and anomaly identification locally at the construction site, and forming a closed-loop control of "plan-execution-correction" through linkage with the collaborative optimization module. Furthermore, edge nodes can only transmit key indicators (such as progress deviation >5%) via 5G, thereby reducing data transmission volume, enabling rapid alarms for abnormal progress conditions, and avoiding monitoring failures due to network latency.

[0112] The visualization and interactive module provides a 3D geographic information display interface, integrating a Gantt chart of construction progress, a resource heat map, and risk warning prompts to visualize the maintenance progress, resource distribution, and risk event information of the target rail. Simultaneously, the module supports immersive virtual reality displays, simulating the impact of maintenance operations on train operation on the target rail under different construction schemes based on line operation data and maintenance plans. Therefore, this module, through 3D geographic information and construction simulation, assists managers in intuitively assessing the operational impact of different schemes to reduce decision-making biases. Furthermore, by visually displaying the spatial relationships between construction personnel and equipment, it helps optimize construction organization schemes, thereby reducing the number of on-site surveys.

[0113] The data security gateway module allows for tiered access permissions to different user roles and uses blockchain technology to ensure the immutable storage of critical operation logs. This module, through blockchain storage and tiered access control, safeguards the security and reliability of core data in cross-departmental collaboration.

[0114] In this embodiment, the system can also establish a data interface with the rail transit signal control system, automatically reserve a time window for signal equipment commissioning in the construction plan, and generate interlocking test schemes. Therefore, when using this system for rail information processing, the disconnect between signal commissioning and track construction in the traditional model can be avoided, shortening the signal system access and commissioning cycle and reducing planned rework rates.

[0115] In this embodiment, a fully intelligent information processing solution is provided for the formulation, optimization, and execution of major and medium-scale maintenance plans for rails. By integrating multi-source data acquisition, intelligent analysis, dynamic optimization, and execution monitoring functions, the system achieves full lifecycle management of major and medium-scale maintenance plans, effectively solving problems such as poor coordination and delayed response in traditional methods. Furthermore, by utilizing multi-objective optimization algorithms to optimize maintenance plans, the system can balance cost, efficiency, and safety objectives in the formulation of maintenance plans. Simultaneously, the system supports rapid response to emergencies and resource reallocation, effectively improving the intelligent level of rail transit operation and maintenance management, thereby achieving efficient rail maintenance.

[0116] Based on the same inventive concept, this application also provides a rail maintenance information processing method. The solution provided by this method is similar to the solution described in the above system embodiments. Therefore, the specific limitations of one or more rail maintenance information processing method embodiments provided below can be found in the limitations of the rail maintenance information processing system above, and will not be repeated here.

[0117] The rail maintenance information processing method provided in this application embodiment can be applied to, for example, Figure 1 The diagram shows a rail maintenance information processing system. This system can be deployed on a server or implemented through interaction between a terminal and the server. The server can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server providing cloud computing services.

[0118] In one exemplary embodiment, such as Figure 3 As shown, a method for processing rail maintenance information is provided, which includes the following steps:

[0119] Step S301: Obtain the target rail condition monitoring data, maintenance resource data, track operation data, and environmental data.

[0120] Step S302: Assess the health status of each section of the target rail based on the condition detection data, and obtain the maintenance priority of each section based on the health status assessment results.

[0121] Step S303: With the optimization objectives of minimizing construction costs, maximizing transportation efficiency, and minimizing safety risks, maintenance plan information for the target rail is obtained based on maintenance resource data, line operation data, environmental data, and maintenance priorities for each section.

[0122] Step S304: Based on the condition detection data and environmental data, perform real-time risk detection on the target rail; if a high-risk event is detected, adjust the maintenance plan information of the target rail to obtain the adjusted maintenance plan information.

[0123] In one exemplary embodiment, the state detection data includes static attribute data and dynamic state data of the target rail; such as Figure 4 As shown, the health status of each section of the target rail is assessed based on condition monitoring data. The maintenance priority for each section is then determined based on the assessment results, and may include:

[0124] Step S401: Using the random forest algorithm, the basic state assessment results of each section in the target rail are obtained based on the static attribute data.

[0125] Step S402: Using a temporal convolutional neural network, the health risk prediction results of each section of the target rail in the future time period are obtained based on the dynamic state data.

[0126] Step S403: Based on the basic condition assessment results and health risk prediction results of each section in the target rail, obtain the health status assessment results of each section; and obtain the maintenance priority of each section based on the health status assessment results of each section.

[0127] In one exemplary embodiment, such as Figure 5 As shown, with the optimization objectives of minimizing construction costs, maximizing transportation efficiency, and minimizing safety risks, the maintenance plan information for the target rail is obtained based on maintenance resource data, line operation data, environmental data, and maintenance priorities for each section. This plan may include:

[0128] Step S501: Construct the spatiotemporal distribution constraints of maintenance resources for the target rail based on maintenance resource data.

[0129] Step S502: Using the Pareto front search algorithm, with the optimization objectives of minimizing construction costs, maximizing transportation efficiency, and minimizing safety risks, the initial maintenance plan information of the target rail is obtained based on line operation data, environmental data, maintenance priorities of each section, and spatiotemporal distribution constraints of maintenance resources.

[0130] Step S503: If the initial maintenance plan information indicates that there is a resource occupation conflict between different sections, the initial maintenance plan information is adjusted to obtain the maintenance plan information of the target rail.

[0131] In an exemplary embodiment, when a high-risk event is detected, the maintenance plan information of the target rail is adjusted to obtain adjusted maintenance plan information, including: increasing the maintenance priority of the section corresponding to the high-risk event when a high-risk event is detected; and adjusting the maintenance plan information of the target rail using a preemptive scheduling algorithm according to the maintenance priority of each section to obtain adjusted maintenance plan information.

[0132] In an exemplary embodiment, the method further includes: using edge nodes deployed at the maintenance construction site of the target rail to collect on-site data of the maintenance construction site in real time; obtaining execution deviation data based on the on-site data and maintenance plan information; analyzing the execution deviation data from each edge node to obtain the deviation analysis result of the target rail; and adjusting the maintenance plan information of the target rail based on the deviation analysis result to obtain the adjusted maintenance plan information.

[0133] In an exemplary embodiment, the method further includes visualizing the maintenance construction progress information, maintenance resource distribution information, and risk event information of the target rail; and visualizing the impact of maintenance operations on train operation of the target rail based on line operation data and maintenance plan information.

[0134] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0135] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data such as target rail condition monitoring data, maintenance resource data, track operation data, and environmental data. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a rail maintenance information processing method.

[0136] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0137] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0138] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0139] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0140] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0141] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, 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 many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0142] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0143] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A rail maintenance information processing system, characterized in that, The system includes: a data acquisition module, a data analysis module, a collaborative optimization module, and a plan adjustment module; the data acquisition module is connected to the data analysis module, the collaborative optimization module, and the plan adjustment module respectively; the collaborative optimization module is connected to the plan adjustment module and the data analysis module. The data acquisition module is used to acquire the target rail's condition monitoring data, maintenance resource data, track operation data, and environmental data; The data analysis module is used to assess the health status of each section in the target rail based on the status detection data, and to obtain the maintenance priority of each section based on the health status assessment results of each section. The collaborative optimization module is used to obtain the maintenance plan information of the target rail based on the maintenance resource data, the line operation data, the environmental data, and the maintenance priority of each section, with the optimization objectives of minimizing construction costs, maximizing transportation efficiency, and minimizing safety risks. The plan adjustment module is used to perform real-time risk detection on the target rail based on the status detection data and environmental data; and to adjust the maintenance plan information of the target rail when a high-risk event is detected, so as to obtain the adjusted maintenance plan information.

2. The system according to claim 1, characterized in that, The status detection data includes the static attribute data and dynamic status data of the target rail; the data analysis module includes: a static analysis unit, a dynamic analysis unit, and a priority allocation unit; The static analysis unit is used to obtain the basic state assessment results of each section in the target rail based on the static attribute data using the random forest algorithm. The dynamic analysis unit is used to obtain the health risk prediction results of each section of the target rail in the future time period based on the dynamic state data using a temporal convolutional neural network. The priority allocation unit is used to obtain the health status assessment result of each section based on the basic status assessment result and the health risk prediction result of each section in the target rail; and to obtain the maintenance priority of each section based on the health status assessment result of each section.

3. The system according to claim 1, characterized in that, The collaborative optimization module includes a resource constraint modeling unit, a multi-objective optimization unit, and a conflict coordination unit. The resource constraint modeling unit is used to construct the spatiotemporal distribution constraints of the maintenance resources of the target rail based on the maintenance resource data. The multi-objective optimization unit is used to obtain the initial maintenance plan information of the target rail by using the Pareto front search algorithm with the optimization objectives of minimizing construction costs, maximizing transportation efficiency, and minimizing safety risks, based on the line operation data, the environmental data, the maintenance priorities of each section, and the spatiotemporal distribution constraints of maintenance resources. The conflict coordination unit is used to adjust the initial maintenance plan information when the initial maintenance plan information indicates that there is a resource occupation conflict between different sections, so as to obtain the maintenance plan information of the target rail.

4. The system according to claim 1, characterized in that, The plan adjustment module is used for: In the event of a high-risk event, the maintenance priority of the section corresponding to the high-risk event shall be increased; Based on the maintenance priority of each section, the maintenance plan information of the target rail is adjusted using a preemptive scheduling algorithm to obtain the adjusted maintenance plan information.

5. The system according to claim 1, characterized in that, The system also includes a monitoring and feedback module; the monitoring and feedback module includes edge nodes deployed at the maintenance and construction site of the target rail; the monitoring and feedback module is connected to the collaborative optimization module; The monitoring and feedback module is used to collect on-site data of the maintenance and construction site in real time using the edge node, and obtain execution deviation data based on the on-site data and the maintenance plan information; The monitoring feedback module is also used to analyze the execution deviation data from each of the edge nodes to obtain the deviation analysis results of the target rail; The collaborative optimization module is used to adjust the maintenance plan information of the target rail according to the deviation analysis results, so as to obtain the adjusted maintenance plan information.

6. The system according to any one of claims 1 to 5, characterized in that, The system also includes a visualization interaction module; the visualization interaction module is connected to the data acquisition module, the collaborative optimization module, and the plan adjustment module. The visualization and interaction module is used to visualize the maintenance and construction progress information, maintenance resource distribution information, and risk event information of the target rail. The visualization and interaction module is also used to visualize the impact of maintenance operations on the train operation of the target rail based on the line operation data and the maintenance plan information.

7. A method for processing rail maintenance information, characterized in that, The method includes: Acquire condition monitoring data, maintenance resource data, track operation data, and environmental data for the target rail; The health status of each section in the target rail is evaluated based on the status detection data, and the maintenance priority of each section is obtained based on the health status evaluation results of each section. With the optimization objectives of minimizing construction costs, maximizing transportation efficiency, and minimizing safety risks, the maintenance plan information for the target rail is obtained based on the maintenance resource data, the line operation data, the environmental data, and the maintenance priority of each section. Based on the status detection data and environmental data, real-time risk detection is performed on the target rail; in the event of a high-risk event, the maintenance plan information of the target rail is adjusted to obtain the adjusted maintenance plan information.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method of claim 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method of claim 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method of claim 7.

Images