Steel rail grinding maintenance operation method, device and equipment based on digital twinning

Abstract

The invention relates to a steel rail grinding maintenance operation method, device and equipment based on digital twinning. The method comprises the steps that a steel rail digital twinning model is constructed; acquiring real-time track data of the target steel rail; inputting the real-time rail data into the steel rail digital twinborn model to obtain the rail wear state of the target steel rail; according to the track abrasion state, the train operation timetable, the weather environment parameters and the maintenance resource scheduling information, an initial polishing maintenance operation scheme is generated; solving the multi-objective optimization model by taking the track smoothness improvement rate, the single-time grinding amount, the grinding wheel abrasion cost and the operation time as optimization objectives and taking the grinding pressure, the feeding speed and the grinding angle of the target steel rail as optimization variables to obtain a Pareto optimal solution set; and according to the Pareto optimal solution set, the initial polishing maintenance operation scheme is optimized, the target polishing maintenance operation scheme of the target steel rail is generated, and the precision of steel rail polishing maintenance operation is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of rail maintenance, in particular to a rail grinding maintenance operation method and device based on digital twinning, computer equipment and a storage medium. BACKGROUND

[0002] Long-term operation of trains can cause wave-shaped wear, cracks, and fat edges on the surface of the rails, affecting the smoothness and safety of train travel, exacerbating wheel-rail impact vibration, and accelerating the wear of rails and vehicle components. Therefore, it is necessary to perform grinding maintenance operations on the rails.

[0003] The traditional rail grinding maintenance operation mode highly depends on manual experience judgment and a preset fixed maintenance cycle. This mode has many drawbacks. Specifically, manual experience judgment is subjective and limited, making it difficult to fully and accurately grasp the actual state of the rails. Fixed cycle maintenance lacks flexibility and cannot be adjusted according to the real-time wear condition of the rails. This results in a lag in detection data feedback, which cannot timely reflect the latest state of the rails; the maintenance strategy is rigid and cannot develop personalized maintenance plans according to the actual condition of the rails; and the resource utilization rate is low, resulting in waste of human and material resources. SUMMARY

[0004] Therefore, it is necessary to provide a rail grinding maintenance operation method and device based on digital twinning, computer equipment and a storage medium to solve the problems of lag in detection data feedback and rigid maintenance strategy in the traditional technology.

[0005] In a first aspect, the present application provides a rail grinding maintenance operation method based on digital twinning, comprising:

[0006] Obtaining track geometry parameters, surface texture features and material attribute data of a target rail; constructing a rail digital twinning model according to the track geometry parameters, surface texture features and material attribute data;

[0007] Obtaining real-time track data of the target rail; inputting the real-time track data into the rail digital twinning model to obtain the track wear state of the target rail;

[0008] Obtaining train operation timetable, weather environment parameters and maintenance resource scheduling information; generating an initial grinding maintenance operation scheme for the target rail according to the track wear state, train operation timetable, weather environment parameters and maintenance resource scheduling information;

[0009] The track smoothness improvement rate, the single polishing amount, the grinding wheel wear cost, and the operation time of the target rail are used as the optimization objectives of the multi-objective optimization model, and the polishing pressure, the feed speed, and the polishing angle of the target rail are used as the optimization variables of the multi-objective optimization model, the multi-objective optimization model is solved, and a Pareto optimal solution set is obtained.

[0010] According to the Pareto optimal solution set, the initial polishing maintenance operation scheme is optimized to generate a target polishing maintenance operation scheme for the target rail. The target polishing maintenance operation scheme is used for polishing maintenance operation of the target rail.

[0011] In one embodiment, the initial polishing maintenance operation scheme for the target rail is generated according to the track wear state, the train operation timetable, the weather environment parameters, and the maintenance resource scheduling information, including:

[0012] Based on the long short-term memory network, the future wear trend of the target rail is obtained according to the train operation timetable and the weather environment parameters.

[0013] Based on the genetic algorithm, the construction vehicle path, the equipment allocation, and the human resource scheduling are optimized according to the maintenance resource scheduling information to minimize the empty running time and resource waste, and a resource scheduling optimization result is obtained.

[0014] Based on fuzzy logic, the operation risk level is quantified according to the track wear state, the weather environment parameters, and the maintenance resource scheduling information, and a safety evaluation result is obtained.

[0015] According to the future wear trend of the target rail, the resource scheduling optimization result, and the safety evaluation result, the initial polishing maintenance operation scheme for the target rail is obtained.

[0016] In one embodiment, the real-time track data of the target rail is obtained, including:

[0017] The multi-source heterogeneous data of the target rail collected through a multi-source data collection network is obtained. The multi-source data collection network includes a distributed optical fiber sensor array installed along the track of the target rail, a vehicle-mounted three-dimensional acceleration sensor, an infrared thermal imager, an ultrasonic flaw detector, and a wheel-rail force detection device.

[0018] The multi-source heterogeneous data is time-stamped and synchronized to obtain real-time track data.

[0019] In one embodiment, after the step of optimizing the initial polishing maintenance operation scheme according to the Pareto optimal solution set to generate the target polishing maintenance operation scheme for the target rail, the method further includes:

[0020] acquire actual track state data of the target rail after the grinding maintenance operation and predicted track state data; the predicted track state data is track state data of the target rail after the grinding maintenance operation predicted by the rail digital twin model;

[0021] In a case where a deviation between the predicted track state data and the actual track state data is greater than a preset deviation threshold, update model parameters of the rail digital twin model until the deviation is less than the preset deviation threshold.

[0022] In one of the embodiments, the method further comprises:

[0023] In a case where a sudden track damage or an environmental parameter mutation is detected, an emergency maintenance scheme is started.

[0024] In one of the embodiments, in a case where a sudden track damage or an environmental parameter mutation is detected, an emergency maintenance scheme is started, comprising:

[0025] In a case where a crack depth of a track surface of the target rail is greater than or equal to a preset depth threshold, the grinding maintenance operation on the target rail is stopped; and / or,

[0026] In a case where a track wear amplitude of the target rail is greater than or equal to a preset wear amplitude threshold, a grinding intensity and frequency of the target rail are adjusted; and / or,

[0027] In a case where an environmental temperature change of the target rail is greater than or equal to a preset temperature change threshold, a thermal expansion coefficient of the target rail is adjusted.

[0028] In one of the embodiments, the method further comprises:

[0029] Store track historical maintenance records, material performance parameters and environmental change data of the target rail to a database;

[0030] Extract training samples from the database; and train the rail digital twin model according to the training samples.

[0031] In a second aspect, the application further provides a rail grinding maintenance operation device based on digital twinning, comprising:

[0032] A digital twin model construction module is configured to acquire track geometric parameters, surface texture features and material attribute data of a target rail; and construct a rail digital twin model according to the track geometric parameters, the surface texture features and the material attribute data;

[0033] A wear state acquisition module is configured to acquire real-time track data of the target rail; and input the real-time track data to the rail digital twin model to acquire a track wear state of the target rail.

[0034] The initial grinding maintenance operation scheme generation module is configured to acquire a train operation timetable, weather environment parameters, and maintenance resource scheduling information; and generate an initial grinding maintenance operation scheme for the target rail according to track wear states, the train operation timetable, the weather environment parameters, and the maintenance resource scheduling information.

[0035] The multi-objective optimization model solution module is configured to take the track smoothness improvement rate, the single grinding amount, the grinding wheel wear cost, and the operation time of the target rail as optimization objectives of a multi-objective optimization model, take the grinding pressure, the feed speed, and the grinding angle of the target rail as optimization variables of the multi-objective optimization model, solve the multi-objective optimization model, and obtain a Pareto optimal solution set.

[0036] The target grinding maintenance operation scheme generation module is configured to optimize the initial grinding maintenance operation scheme according to the Pareto optimal solution set, and generate a target grinding maintenance operation scheme for the target rail; and the target grinding maintenance operation scheme is configured to be used for grinding maintenance operation on the target rail.

[0037] In a third aspect, the present application further provides a computer device, which comprises a memory and a processor, the memory stores a computer program, and the processor implements the method steps of the first aspect when executing the computer program.

[0038] In a fourth aspect, the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method steps of the first aspect.

[0039] The rail grinding maintenance operation method, device, computer equipment and computer readable storage medium based on digital twinning described above, by acquiring track geometric parameters, surface texture features and material attribute data of the target rail; constructing a rail digital twinning model according to the track geometric parameters, surface texture features and material attribute data; acquiring real-time track data of the target rail; inputting the real-time track data into the rail digital twinning model to obtain the track wear state of the target rail; acquiring train operation timetable, weather environment parameters and maintenance resource scheduling information; generating an initial grinding maintenance operation scheme of the target rail according to the track wear state, train operation timetable, weather environment parameters and maintenance resource scheduling information; taking the track smoothness improvement rate, single grinding amount, grinding wheel wear cost and operation time of the target rail as the optimization objectives of a multi-objective optimization model, and taking the grinding pressure, feed speed and grinding angle of the target rail as the optimization variables of the multi-objective optimization model, solving the multi-objective optimization model to obtain a Pareto optimal solution set; optimizing the initial grinding maintenance operation scheme according to the Pareto optimal solution set to generate a target grinding maintenance operation scheme of the target rail; the target grinding maintenance operation scheme is used for grinding maintenance operation of the target rail. According to the above content, by constructing the rail digital twinning model, the state of the target rail can be mastered, and then it is judged whether the target rail needs to be ground and maintained; by acquiring the real-time track data of the target rail, the synchronous updating of the rail digital twinning model and the physical track of the target rail can be ensured, and the real-time performance of the target rail data detection is ensured; since the train operation timetable, weather environment parameters and maintenance resource scheduling information are dynamically changing, according to the train operation timetable, weather environment parameters and maintenance resource scheduling information, the initial grinding maintenance operation scheme of the target rail is generated, which can ensure that the initial grinding maintenance operation scheme has dynamic adaptability and can quickly respond to real-time changes; by considering the track smoothness improvement rate, single grinding amount, grinding wheel wear cost and operation time of the target rail, the multi-objective optimization model is solved, which can improve the precision of the rail grinding maintenance operation. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other related drawings can be obtained by those skilled in the art without creating any inventive labor.

[0041] Figure 1 An application environment diagram of a rail grinding maintenance operation method based on digital twinning in an embodiment;

[0042] Figure 2A flowchart of a rail grinding maintenance method based on digital twinning in an embodiment;

[0043] Figure 3 A flowchart of generating an initial rail grinding maintenance scheme for a target rail in an embodiment;

[0044] Figure 4 A structural block diagram of a rail grinding maintenance device based on digital twinning in an embodiment;

[0045] Figure 5 An internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION

[0046] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0047] It should be noted that the terms "first", "second", etc. used in the present 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 "include" and "have" used in the present application and any variations thereof are intended to cover non-exclusive inclusion. The term "a plurality of" used in the present application refers to two or more. The term "and / or" used in the present application refers to one of the options or any combination of multiple options.

[0048] The rail grinding maintenance method based on digital twinning provided by the embodiments of the present application can be applied to, for example, Figure 1The application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data required by the server 104 to process. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The terminal 102 obtains the track geometric parameters, surface texture features and material attribute data of the target rail; according to the track geometric parameters, surface texture features and material attribute data, a rail digital twin model is constructed; real-time track data of the target rail is obtained; the real-time track data is input into the rail digital twin model to obtain the track wear state of the target rail; the train operation timetable, weather environment parameters and maintenance resource scheduling information are obtained; according to the track wear state, the train operation timetable, the weather environment parameters and the maintenance resource scheduling information, an initial polishing maintenance operation scheme of the target rail is generated; the track smoothness improvement rate, the single polishing amount, the grinding wheel wear cost and the operation time of the target rail are taken as the optimization objectives of a multi-objective optimization model, and the polishing pressure, the feed speed and the polishing angle of the target rail are taken as the optimization variables of the multi-objective optimization model. The multi-objective optimization model is solved to obtain a Pareto optimal solution set; according to the Pareto optimal solution set, the initial polishing maintenance operation scheme is optimized to generate a target polishing maintenance operation scheme of the target rail; the target polishing maintenance operation scheme is used for polishing maintenance operation of the target rail. Among them, the terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, unmanned aerial vehicles, low-altitude flying vehicles, Internet of Things devices and portable wearable devices. The Internet of Things device can be a smart speaker, a smart TV, a smart air conditioner, a smart vehicle device, a projection device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 can be a standalone physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0049] In one embodiment, as shown in Figure 2 A rail polishing maintenance operation method based on digital twinning is provided. The method can be applied to a terminal, a server, or a system including a terminal and a server, and can be implemented through the interaction of the terminal and the server. The method includes the following steps:

[0050] In step S210, the track geometric parameters, surface texture features and material attribute data of the target rail are obtained; and a rail digital twin model is constructed according to the track geometric parameters, surface texture features and material attribute data.

[0051] The track geometry parameters are used to represent the geometric shape and positional relationship of the rail in three-dimensional space, including but not limited to gauge, alignment, vertical height deviation, and twist.

[0052] The surface texture features refer to the micro-geometric shape and damage marks of the rail contact surface, reflecting the history and current state of wheel-rail interaction. The surface texture features include but are not limited to cracks, wear, corrosion, crushing, and spalling.

[0053] The material attribute data refer to the chemical composition, physical properties, and mechanical properties of the rail, reflecting its load-carrying capacity and durability. The material attribute data include but are not limited to chemical composition, hardness, strength, toughness, and fatigue performance.

[0054] The geometric model is used to reflect the spatial shape of the track, the physical model is used to simulate the mechanical behavior of the track, and the behavior model is used to predict the track wear evolution.

[0055] In the embodiments of the present application, the track geometry parameters, surface texture features, and material attribute data are obtained through three-dimensional laser scanning and image recognition technology, and the geometric model, physical model, and behavior model construction methods in related technologies are used to establish a multi-dimensional virtual mapping system (rail digital twin model) containing the geometric model, physical model, and behavior model based on the track geometry parameters, surface texture features, and material attribute data.

[0056] In step S220, real-time track data of the target rail is obtained; the real-time track data is input into the rail digital twin model to obtain the track wear state of the target rail.

[0057] In the embodiments of the present application, the track data of the target rail can be collected in real time by a monitoring device installed on the target rail. The real-time track data is input into the rail digital twin model, and the rail digital twin model outputs the track wear state of the target rail.

[0058] In step S230, a train operation timetable, weather environment parameters, and maintenance resource scheduling information are obtained; and an initial grinding maintenance operation scheme of the target rail is generated based on the track wear state, the train operation timetable, the weather environment parameters, and the maintenance resource scheduling information.

[0059] The train operation timetable is a train operation plan formulated by the railway department, which specifies in detail the departure time, arrival time, stop station, running interval, and running speed of each train.

[0060] The weather environment parameters refer to the natural environmental conditions that affect railway operation, mainly including temperature, humidity, wind speed, rainfall, snowfall, visibility, lightning activity, etc. These parameters are collected in real time by environmental monitoring equipment such as weather stations, anemometers, and rain gauges.

[0061] Among them, maintenance resource scheduling information refers to the railway maintenance department's allocation and scheduling plan for resources such as manpower, equipment, and materials.

[0062] In this embodiment, the wear status of the rail is analyzed in real time based on the digital twin model of the rail. Combined with the train timetable (avoiding train passing time), weather environment parameters (avoiding operation in severe weather such as rain, snow, and strong winds), and maintenance resource scheduling information (such as the availability of grinding equipment and personnel), a dynamic grinding strategy scheme (initial grinding and maintenance operation scheme for the target rail) is generated.

[0063] Step S240: Using the track smoothness improvement rate of the target rail, the amount of grinding per pass, the wear cost of the grinding wheel, and the operation time as the optimization objectives of the multi-objective optimization model, and using the grinding pressure, feed speed, and grinding angle of the target rail as the optimization variables of the multi-objective optimization model, solve the multi-objective optimization model to obtain the Pareto optimal solution set.

[0064] The track smoothness improvement rate is an indicator that measures the degree of optimization of the track geometry after rail grinding. It is usually calculated by comparing the changes in track irregularity parameters (such as elevation, track alignment, level, and torsion) before and after grinding.

[0065] Among them, the amount of material removed from the surface of the rail by the grinding wheel in each grinding operation refers to the thickness or volume of material removed from the rail surface by the grinding wheel in each grinding operation.

[0066] Among them, grinding wheel wear cost refers to the expenses incurred by the consumption of grinding wheels during the grinding process, including grinding wheel purchase cost, replacement labor cost and downtime cost.

[0067] The working time refers to the total time required to complete the grinding of a section of rail, including preparation time, grinding time, equipment adjustment time, and finishing time.

[0068] Grinding pressure refers to the vertical force between the grinding wheel and the contact surface of the rail. Feed rate refers to the speed at which the grinding wheel moves along the longitudinal or transverse direction of the rail. Grinding angle refers to the angle between the axis of the grinding wheel and the longitudinal or transverse direction of the rail.

[0069] In this embodiment, a multi-objective optimization algorithm is employed, with track smoothness improvement rate, single grinding amount, grinding wheel cost, and track maintenance window time as optimization objectives, to generate a Pareto optimal solution set. The multi-objective optimization algorithm can be the NSGA-II algorithm.

[0070] Step S250: Based on the Pareto optimal solution set, optimize the initial grinding and maintenance operation plan to generate the target grinding and maintenance operation plan for the target rail; the target grinding and maintenance operation plan is used to perform grinding and maintenance operations on the target rail.

[0071] In this embodiment, the initial grinding and maintenance operation plan is generated considering the external environmental influences of train running time, weather factors, and maintenance resource scheduling; it is a roughly feasible grinding and maintenance operation plan. Based on the initial grinding and maintenance operation plan, considering the track smoothness improvement rate, single grinding volume, grinding wheel wear cost, and operation time, a Pareto optimal solution set is generated. According to the Pareto optimal solution set, the initial grinding and maintenance operation plan can be dynamically adjusted to obtain the target grinding and maintenance operation plan. For example, for a curve section (R=800m) with an average trackside grinding depth of 1.5mm, the initial grinding and maintenance operation plan is: pressure 50MPa, speed 2km / h, angle 20°. The target grinding and maintenance operation plan is: in this area, the pressure is reduced to 40MPa, the speed is reduced to 1km / h, and the angle is increased to 25°.

[0072] The aforementioned rail grinding and maintenance method based on digital twins involves: acquiring the track geometry parameters, surface texture features, and material properties of the target rail; constructing a digital twin model of the rail based on these parameters; acquiring real-time track data of the target rail; inputting the real-time track data into the digital twin model to obtain the track wear status of the target rail; acquiring train timetables, weather parameters, and maintenance resource scheduling information; and then, based on the track wear status, train timetables, weather parameters, and maintenance resource scheduling information... The initial grinding and maintenance plan for the target rail is generated based on the information obtained. The objective of the multi-objective optimization model is to use the rail smoothness improvement rate, single grinding volume, grinding wheel wear cost, and operation time as the optimization objectives, and the grinding pressure, feed speed, and grinding angle of the target rail as the optimization variables. The Pareto optimal solution set is obtained by solving the multi-objective optimization model. Based on the Pareto optimal solution set, the initial grinding and maintenance plan is optimized to generate the target grinding and maintenance plan for the target rail. The target grinding and maintenance plan is used to perform grinding and maintenance operations on the target rail. As described above, this application, by constructing a digital twin model of the rail, can grasp the state of the target rail and thus determine whether the target rail needs grinding and maintenance. By acquiring real-time track data of the target rail, it can ensure the synchronous update of the digital twin model and the physical track of the target rail, ensuring the real-time nature of the target rail data detection. Since train timetables, weather parameters, and maintenance resource scheduling information are dynamically changing, generating an initial grinding and maintenance operation plan for the target rail based on these factors ensures that the initial grinding and maintenance operation plan is dynamically adaptable and can quickly respond to real-time changes. By considering the track smoothness improvement rate, single grinding volume, grinding wheel wear cost, and operation time of the target rail, solving the multi-objective optimization model can improve the accuracy of grinding and maintenance operations.

[0073] In one embodiment, acquiring real-time track data of the target rail includes:

[0074] Step S222: Acquire multi-source heterogeneous data of the target rail collected through a multi-source data acquisition network; the multi-source data acquisition network includes a distributed fiber optic sensor array installed along the track of the target rail, an on-board three-dimensional acceleration sensor, an infrared thermal imager, an ultrasonic flaw detector, and a wheel-rail force detection device.

[0075] In this embodiment, a fiber optic sensor array is distributed along the track to monitor track strain and temperature changes in real time. An onboard three-dimensional accelerometer captures the track vibration spectrum during train operation. An infrared thermal imager detects abnormal rail surface temperatures and identifies potential fatigue areas. An ultrasonic flaw detector and a wheel-rail force detection device are used for internal defect detection and wheel-rail contact force analysis, respectively.

[0076] Step S224: Timestamp synchronization of multi-source heterogeneous data to obtain real-time orbit data.

[0077] In this embodiment of the application, timestamp synchronization technology is used to synchronize the timestamps of multi-source heterogeneous data, ensuring the spatiotemporal consistency of the multi-source heterogeneous data, providing high-precision input for the rail digital twin model, and enhancing the comprehensiveness and real-time performance of track condition assessment.

[0078] In one embodiment, see Figure 3 Based on the track wear condition, train timetable, weather parameters, and maintenance resource scheduling information, an initial grinding and maintenance plan for the target rail is generated, including:

[0079] Step S310: Based on the Long Short-Term Memory network, the future wear trend of the target rail is obtained according to the train timetable and weather parameters.

[0080] In this embodiment of the application, a Long Short-Term Memory (LSTM) network is used to predict the future wear trend of the target rail based on data such as the time it takes for the train to pass the rail, the weight of the train passing the rail, and weather conditions.

[0081] Step S320: Based on the genetic algorithm, optimize the construction vehicle route, equipment allocation and manpower scheduling according to the maintenance resource scheduling information, minimize empty running time and resource waste, and obtain the resource scheduling optimization result.

[0082] In this embodiment, a multi-objective optimization function is established, with idle time and resource waste as optimization objectives and construction vehicle routes, equipment allocation, and manpower scheduling as optimization variables. A genetic algorithm is then used to solve the multi-objective optimization function, generating optimized resource scheduling results.

[0083] Step S330: Based on fuzzy logic, the risk level of the operation is quantified according to the track wear status, weather environmental parameters, and maintenance resource scheduling information to obtain a safety assessment result.

[0084] Among them, fuzzy logic transforms qualitative factors (such as "harsh environment" and "aging equipment") into quantitative risk values ​​(0~1) through membership functions, and then calculates the comprehensive risk level through fuzzy rule base and defuzzification.

[0085] In this embodiment of the application, fuzzy logic is used to assess the operational risk level based on track wear status, weather environmental parameters, and maintenance resource scheduling information, thereby obtaining a safety assessment result.

[0086] Step S340: Based on the future wear trend of the target rail, the resource scheduling optimization results, and the safety assessment results, obtain the initial grinding and maintenance operation plan for the target rail.

[0087] In this embodiment of the application, a multi-objective optimization algorithm is used to obtain an initial grinding and maintenance operation plan for the target rail, with the optimization objectives of maximizing the maintenance effect after grinding, minimizing the cost, and minimizing the risk.

[0088] In one embodiment, after optimizing the initial grinding and maintenance operation plan based on the Pareto optimal solution set to generate the target grinding and maintenance operation plan for the target rail, the method further includes:

[0089] Step S251: Obtain the actual track condition data and predicted track condition data of the target rail after grinding and maintenance operations; the predicted track condition data is the track condition data of the target rail after grinding and maintenance operations predicted by the rail digital twin model.

[0090] Step S252: If the deviation between the predicted track condition data and the actual track condition data is greater than a preset deviation threshold, the model parameters of the rail digital twin model are updated until the deviation is less than the preset deviation threshold.

[0091] In this embodiment, when the rail digital twin model predicts the track condition of a target rail, the predicted track condition data is recorded, and then the actual track condition data of the target rail is recorded and compared. If there is a significant error between the predicted and actual track condition data, the rail digital twin model is updated. For example, based on the current rail condition, weather conditions, and train timetable, the rail digital twin model predicts that the normal service life of the rail is three months, but the rail needs maintenance after two months of use. In this case, the rail condition, weather conditions, and train timetable data are recorded and updated in the rail digital twin model. When the data of other rails is the same as the recorded data, the predicted service life output by the rail digital twin model is two months.

[0092] In one embodiment, the rail grinding and maintenance method based on digital twins further includes:

[0093] Step S260: In the event of a sudden track damage or a sudden change in environmental parameters, activate the emergency maintenance plan.

[0094] Sudden track damage refers to severe damage to rails or track components caused by unforeseen factors within a short period of time (minutes to hours), exceeding the conventional monitoring threshold and potentially leading to a safety accident. Specifically, it includes, but is not limited to, rail fractures, weld cracks, sleeper failures, and foreign object intrusion.

[0095] Among them, sudden changes in environmental parameters refer to significant changes in key environmental indicators (such as temperature, humidity, wind speed, rainfall, etc.) within a short period of time during construction or operation, exceeding the safe operation threshold.

[0096] In this embodiment, an emergency maintenance plan is activated upon detection of sudden track damage or a sudden change in environmental parameters. This emergency maintenance plan may involve terminating the target grinding and maintenance operation, or adjusting the grinding intensity and frequency.

[0097] In one embodiment, upon detection of sudden track damage or a sudden change in environmental parameters, an emergency repair plan is initiated, including:

[0098] Step S262: If the crack depth on the target rail surface is greater than or equal to a preset depth threshold, stop the grinding and repair work on the target rail; and / or,

[0099] Among them, the track surface crack depth refers to the maximum penetration depth of the crack formed on the rail surface due to fatigue, wear or external impact, perpendicular to the rail surface.

[0100] The preset depth threshold can be set according to actual needs.

[0101] In this embodiment of the application, when the depth of the crack on the track surface exceeds a preset depth threshold, such as 2mm, a first-level response is immediately initiated, and the grinding and maintenance work should be stopped immediately.

[0102] Step S264: If the track corrugation amplitude of the target rail is greater than or equal to a preset corrugation amplitude threshold, adjust the grinding intensity and frequency of the target rail; and / or,

[0103] Among them, the track corrugation amplitude refers to the vertical height difference of the periodic corrugations formed on the surface of the rail due to long-term wear, that is, the vertical distance between the crest and the trough.

[0104] The preset wave amplitude threshold can be set according to actual needs.

[0105] In this embodiment of the application, when the track corrugation amplitude exceeds the preset corrugation amplitude threshold, such as 0.3mm, a secondary response is initiated to adjust the polishing force and frequency.

[0106] Step S266: When the ambient temperature change of the target rail is greater than or equal to the preset temperature change threshold, adjust the thermal expansion coefficient of the target rail.

[0107] Among them, ambient temperature change refers to the rise and fall of air temperature in the orbital area over a short period of time (such as several hours).

[0108] The preset temperature change threshold can be set according to actual needs.

[0109] The coefficient of thermal expansion is a physical quantity that characterizes the thermal expansion properties of an object. Specifically, it refers to the relative change in length or volume of an object per unit length or volume when the temperature increases by 1°C. For steel rails, the coefficient of thermal expansion mainly focuses on their linear expansion characteristics, that is, the amount of expansion and contraction along the length of the rail when the temperature changes. This coefficient reflects the sensitivity of the rail material to temperature changes.

[0110] In this embodiment of the application, when the ambient temperature changes abruptly beyond a preset temperature change threshold, such as 10°C, a three-level response is initiated to correct the coefficient of thermal expansion.

[0111] This application embodiment utilizes a tiered response mechanism to quickly respond to emergencies, minimize the risk of track damage, and ensure operational safety.

[0112] In one embodiment, the rail grinding and maintenance method based on digital twins further includes:

[0113] Step S270: Store the target rail's track history maintenance records, material performance parameters, and environmental change data into the database.

[0114] Among them, the historical maintenance record of the rails refers to the systematic archive of all maintenance activities during the entire life cycle of the rails from when they are put into use to when they are taken out of use.

[0115] Among them, material performance parameters are quantitative indicators that describe the inherent properties of rail materials, including strength, coefficient of thermal expansion, fatigue limit, wear rate, crack propagation rate, etc.

[0116] Among them, environmental change data refers to dynamic monitoring data of the external environment in which the rails are located.

[0117] Step S272: Extract training samples from the database; train the digital twin model of the rail based on the training samples.

[0118] In this embodiment, the database continuously records new data and extracts training samples from the database to train the rail digital twin model, which enables the rail digital twin model to be dynamically updated and improves the accuracy of the output data of the rail digital twin model.

[0119] It should be understood that although the steps in the flowcharts of the above embodiments 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 above embodiments 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.

[0120] Based on the same inventive concept, this application also provides a digital twin-based rail grinding and maintenance device for implementing the aforementioned digital twin-based rail grinding and maintenance method. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the digital twin-based rail grinding and maintenance device provided below can be found in the limitations of the digital twin-based rail grinding and maintenance method described above, and will not be repeated here.

[0121] In one exemplary embodiment, please refer to Figure 4 A rail grinding and maintenance operation device based on digital twin is provided, comprising:

[0122] The digital twin model construction module 410 is used to acquire the track geometry parameters, surface texture features, and material property data of the target rail; and to construct a digital twin model of the rail based on the track geometry parameters, surface texture features, and material property data.

[0123] The wear status acquisition module 420 is used to acquire real-time track data of the target rail; the real-time track data is input into the digital twin model of the rail to obtain the track wear status of the target rail;

[0124] The initial grinding and maintenance operation plan generation module 430 is used to obtain train timetables, weather environmental parameters, and maintenance resource scheduling information; and to generate an initial grinding and maintenance operation plan for the target rail based on the rail wear status, train timetables, weather environmental parameters, and maintenance resource scheduling information.

[0125] The multi-objective optimization model solving module 440 is used to solve the multi-objective optimization model with the track smoothness improvement rate, single grinding amount, grinding wheel wear cost and operation time of the target rail as the optimization objectives, and the grinding pressure, feed speed and grinding angle of the target rail as the optimization variables, to obtain the Pareto optimal solution set.

[0126] The target grinding and maintenance operation plan generation module 450 is used to optimize the initial grinding and maintenance operation plan based on the Pareto optimal solution set and generate the target grinding and maintenance operation plan for the target rail; the target grinding and maintenance operation plan is used to perform grinding and maintenance operations on the target rail.

[0127] The various modules in the aforementioned digital twin-based rail grinding and maintenance device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0128] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a rail grinding and maintenance operation method based on digital twins. 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 an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0129] Those skilled in the art will understand that Figure 5 The structures shown are merely block diagrams of some structures related to the present application and do not constitute a limitation on the computer equipment to which the present application is applied. Specific computer equipment may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements. In one embodiment, a computer equipment is provided, including a memory and a processor. The memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the aforementioned rail grinding and repair operation method based on digital twins. The steps of the rail grinding and repair operation method based on digital twins described above can be steps from one of the rail grinding and repair operation methods based on digital twins in the various embodiments described above.

[0130] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, causes the processor to perform the steps of the aforementioned rail grinding and repair operation method based on digital twins. The steps of the rail grinding and repair operation method based on digital twins described above can be the steps from one of the rail grinding and repair operation methods based on digital twins in the various embodiments described above.

[0131] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, causes the processor to perform the steps of the aforementioned rail grinding and maintenance method based on digital twins. The steps of the rail grinding and maintenance method based on digital twins described above can be the steps in one of the rail grinding and maintenance methods based on digital twins from the various embodiments described above.

[0132] 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.

[0133] 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. When executed, the computer program 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.

[0134] 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.

[0135] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this 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 method for rail grinding and maintenance based on digital twins, characterized in that, The method includes: Obtain the track geometry parameters, surface texture features, and material property data of the target rail; construct a digital twin model of the rail based on the track geometry parameters, surface texture features, and material property data; Obtain real-time track data of the target rail; input the real-time track data into the digital twin model of the rail to obtain the track wear status of the target rail; Obtain train timetables, weather parameters, and maintenance resource scheduling information; based on the track wear status, train timetables, weather parameters, and maintenance resource scheduling information, generate an initial grinding and maintenance plan for the target rail; The objective of the multi-objective optimization model is to use the track smoothness improvement rate, single grinding amount, grinding wheel wear cost, and operation time of the target rail as optimization objectives, and the grinding pressure, feed speed, and grinding angle of the target rail as optimization variables. The multi-objective optimization model is solved to obtain the Pareto optimal solution set. Based on the Pareto optimal solution set, the initial grinding and maintenance operation plan is optimized to generate the target grinding and maintenance operation plan for the target rail; the target grinding and maintenance operation plan is used to perform grinding and maintenance operations on the target rail.

2. The rail grinding and maintenance method based on digital twins according to claim 1, characterized in that, The initial grinding and maintenance plan for the target rail is generated based on the rail wear condition, the train timetable, the weather parameters, and the maintenance resource scheduling information, including: Based on a long short-term memory network, the future wear trend of the target rail is obtained according to the train timetable and the weather environment parameters. Based on the genetic algorithm, and according to the maintenance resource scheduling information, the construction vehicle routes, equipment allocation and manpower scheduling are optimized to minimize empty running time and resource waste, and the resource scheduling optimization results are obtained. Based on fuzzy logic, the operational risk level is quantified according to the track wear status, the weather environment parameters, and the maintenance resource scheduling information to obtain a safety assessment result; Based on the future wear trend of the target rail, the resource scheduling optimization results, and the safety assessment results, an initial grinding and maintenance operation plan for the target rail is obtained.

3. The rail grinding and maintenance method based on digital twins according to claim 1, characterized in that, The acquisition of real-time track data of the target rail includes: Acquire multi-source heterogeneous data of the target rail collected through a multi-source data acquisition network; the multi-source data acquisition network includes a distributed fiber optic sensor array installed along the track of the target rail, an on-board three-dimensional accelerometer, an infrared thermal imager, an ultrasonic flaw detector, and a wheel-rail force detection device; The real-time orbit data is obtained by synchronizing the timestamps of the multi-source heterogeneous data.

4. The rail grinding and maintenance method based on digital twins according to claim 1, characterized in that, After the step of optimizing the initial grinding and maintenance operation plan based on the Pareto optimal solution set to generate the target grinding and maintenance operation plan for the target rail, the method further includes: The actual track condition data and predicted track condition data of the target rail after grinding and maintenance are obtained; the predicted track condition data are the track condition data of the target rail after grinding and maintenance predicted by the rail digital twin model. If the deviation between the predicted track condition data and the actual track condition data is greater than a preset deviation threshold, the model parameters of the rail digital twin model are updated until the deviation is less than the preset deviation threshold.

5. The rail grinding and maintenance method based on digital twins according to claim 1, characterized in that, The method further includes: In the event of sudden track damage or a sudden change in environmental parameters, an emergency maintenance plan will be activated.

6. The rail grinding and maintenance method based on digital twins according to claim 5, characterized in that, The emergency maintenance plan, which is activated upon detection of sudden track damage or a sudden change in environmental parameters, includes: If the crack depth on the target rail surface is greater than or equal to a preset depth threshold, the grinding and repair work on the target rail shall be stopped; and / or, If the track corrugation amplitude of the target rail is greater than or equal to a preset corrugation amplitude threshold, adjust the grinding intensity and frequency of the target rail; and / or, When the ambient temperature change of the target rail is greater than or equal to a preset temperature change threshold, the coefficient of thermal expansion of the target rail is adjusted.

7. The rail grinding and maintenance method based on digital twins according to any one of claims 1 to 6, characterized in that, The method further includes: The track maintenance history, material performance parameters, and environmental change data of the target rail are stored in the database; Training samples are extracted from the database; the rail digital twin model is trained based on the training samples.

8. A rail grinding and maintenance operation device based on digital twin, characterized in that, include: The digital twin model construction module is used to acquire the track geometry parameters, surface texture features, and material property data of the target rail; and to construct a digital twin model of the rail based on the track geometry parameters, surface texture features, and material property data. The wear status acquisition module is used to acquire real-time track data of the target rail; The real-time track data is input into the digital twin model of the rail to obtain the track wear status of the target rail; The initial grinding and maintenance operation plan generation module is used to obtain train timetables, weather environmental parameters, and maintenance resource scheduling information; and to generate an initial grinding and maintenance operation plan for the target rail based on the rail wear status, the train timetable, the weather environmental parameters, and the maintenance resource scheduling information. The multi-objective optimization model solving module is used to solve the multi-objective optimization model with the track smoothness improvement rate, single grinding amount, grinding wheel wear cost and operation time of the target rail as the optimization objectives, and the grinding pressure, feed speed and grinding angle of the target rail as the optimization variables, to obtain the Pareto optimal solution set. The target grinding and maintenance operation plan generation module is used to optimize the initial grinding and maintenance operation plan based on the Pareto optimal solution set to generate the target grinding and maintenance operation plan for the target rail; the target grinding and maintenance operation plan is used to perform grinding and maintenance operations on the target rail.

9. 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 according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images