Pantograph failure prediction method, system, medium, device and program product

Abstract

The application provides a pantograph fault prediction method, system, medium, equipment and program product, relates to the field of data monitoring, and comprises the following steps: acquiring a pantograph dynamics model; taking key parameters in the pantograph dynamics model as design variables, taking pantograph-catenary contact force as a target value, calling a parameter inversion calculation process to iteratively calculate a pantograph key parameter combination satisfying the target value; determining corresponding pantograph core components based on the pantograph key parameter combination; constructing equivalent proxy models corresponding to the pantograph core components; and determining the fault probability of each pantograph core component according to the stress distribution output by the equivalent proxy models corresponding to all the pantograph core components. The application can realize fine analysis of the pantograph core components, and then simulate the stress distribution of the pantograph core components in actual operation, thereby providing a direct basis for the evaluation of the fault probability.

Description

Technical Field

[0001] This invention relates to the field of data monitoring, and in particular to a pantograph fault prediction method, system, medium, device, and program product. Background Technology

[0002] With the rapid development of rail transit in my country, the technical requirements for high-speed trains are increasing. As the core component of the pantograph for power supply to high-speed trains, the pantograph-catenary system has a direct impact on the train's operational safety and energy efficiency due to its dynamic performance and contact stability.

[0003] Currently, the design and operation maintenance of the pantograph-catenary system of high-speed trains mainly rely on simulation and testing. Traditional methods depend on manual on-site measurement or catenary inspection vehicles, which are inefficient, labor-intensive, difficult to achieve real-time monitoring across the entire line, and prone to missed detections and false alarms. Recently, sensor threshold alarms or static image analysis have been widely used, but these methods are slow to respond to latent faults such as internal cracks in carbon sliding plates and fatigue deformation of the frame, and cannot quantify the mechanical state (such as stress concentration), leading to the failure of early warnings. Another method is offline monitoring based on electrical detection (such as resistance / current changes), but this detection method is susceptible to electromagnetic interference, can only identify "large offline" faults, and is difficult to detect small sparks and attitude anomalies; traditional numerical simulation (such as finite element analysis) is time-consuming (on the order of minutes), which cannot meet the second-level response requirements of high-speed trains.

[0004] Therefore, how to improve the fault detection of pantographs on high-speed trains in order to improve the operational safety and energy efficiency of the pantograph-catenary system is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] The purpose of this invention is to provide a pantograph fault prediction method, system, computer-readable storage medium, electronic device, and computer program product that can improve the accuracy and efficiency of pantograph fault detection for high-speed trains.

[0006] To address the aforementioned technical problems, this invention provides a pantograph fault prediction method, the specific technical solution of which is as follows:

[0007] Obtain the pantograph dynamics model;

[0008] Using the key parameters in the pantograph dynamics model as design variables and the pantograph-catenary contact force as the target value, the parameter inversion calculation process is called to iteratively calculate the combination of key pantograph parameters that meet the target value; the key parameters include at least one of the following: connection stiffness, damping, pantograph-catenary contact parameters, pantograph head spring stiffness, and damping.

[0009] The corresponding core components of the pantograph are determined based on the combination of key pantograph parameters.

[0010] Construct an equivalent proxy model corresponding to the core components of the pantograph;

[0011] The failure probability of each pantograph core component is determined based on the stress distribution output by the equivalent surrogate model corresponding to all the pantograph core components.

[0012] Optionally, obtaining the pantograph dynamics model includes:

[0013] Construct a rigid-flexible coupling dynamic simulation model with the same scale as the pantograph-net current collection experimental platform;

[0014] Set up simulation conditions, and execute dynamic experiments by calling the rigid-flexible coupling dynamic simulation model based on each simulation condition;

[0015] Extract the time-domain data of the pantograph-catenary contact force as a function of time during the dynamic experiment;

[0016] The pantograph dynamic model is obtained by using the time-domain data as the target value for parameter inversion.

[0017] Optionally, using the key parameters in the pantograph dynamics model as design variables, and with the pantograph-catenary contact force as the target value, the combination of key pantograph parameters that satisfies the target value is iteratively calculated by calling the parameter inversion calculation process, including:

[0018] Define the key parameters in the pantograph dynamics model, as well as the target value of the pantograph-catenary contact force;

[0019] Based on the key parameters and target values, the pantograph dynamics model is run to conduct a simulation experiment, and the simulation results are obtained.

[0020] Compare the simulation results with the target value, and calculate the error value;

[0021] The design variables are adjusted iteratively using a set optimization algorithm until the error value meets the set error range, and then the combination of key pantograph parameters that meets the target value is output.

[0022] Optionally, constructing an equivalent proxy model corresponding to the core components of the pantograph includes:

[0023] Obtain the design variables and design space of the pantograph core component; the design space is the range of values ​​for the design variables.

[0024] Design experiments were performed on the pantograph core component to obtain performance data of the pantograph core component under different combinations of design variables;

[0025] The corresponding approximate model type is determined based on the data characteristics of the pantograph core components;

[0026] The approximate model corresponding to the approximate model type is initialized using the performance data to obtain the equivalent proxy model.

[0027] Optionally, after initializing the approximate model corresponding to the approximate model type using the performance data to obtain the equivalent proxy model, the method further includes:

[0028] The credibility of the approximate model is evaluated. If the approximate model is credible, it is used to replace the simulation program of the pantograph core component, and the equivalent proxy model is encapsulated into a standardized simulation file.

[0029] Optionally, determining the failure probability of each pantograph core component based on the stress distribution output by the equivalent surrogate model corresponding to all the pantograph core components includes:

[0030] The stress distribution output by the equivalent proxy model corresponding to all the pantograph core components is mapped into several heat maps;

[0031] The heat map is overlaid onto the digital twin of the pantograph to obtain a visual schematic diagram of the pantograph;

[0032] The failure probability of each core component of the pantograph is determined by using a set reliability analysis method and a visual schematic diagram of the pantograph.

[0033] The fault probability distribution map corresponding to the fault probability is superimposed on the pantograph visualization diagram, and different fault probabilities are represented by color coding.

[0034] The present invention also provides a pantograph fault prediction system, comprising:

[0035] The model acquisition module is used to acquire the pantograph dynamics model;

[0036] The key parameter determination module is used to take the key parameters in the pantograph dynamic model as design variables, take the pantograph-catenary contact force as the target value, and call the parameter inversion calculation process to iteratively calculate the combination of key pantograph parameters that meet the target value; the key parameters include at least one of connection stiffness, damping, pantograph-catenary contact parameters, pantograph head spring stiffness, and damping.

[0037] A pantograph core component setting module is used to determine the corresponding pantograph core component based on the combination of key pantograph parameters.

[0038] An equivalent proxy model construction module is used to construct an equivalent proxy model corresponding to the core components of the pantograph.

[0039] The failure probability prediction module is used to determine the failure probability of each pantograph core component based on the stress distribution output by the equivalent proxy model corresponding to all the pantograph core components.

[0040] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.

[0041] The present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method described above when it invokes the computer program in the memory.

[0042] This invention provides a method for predicting pantograph faults, comprising: acquiring a pantograph dynamic model; using key parameters in the pantograph dynamic model as design variables, and taking the pantograph-catenary contact force as the target value, iteratively calculating a combination of key pantograph parameters that meets the target value using a parameter inversion calculation process; the key parameters include at least one of connection stiffness, damping, pantograph-catenary contact parameters, pantograph head spring stiffness, and damping; and determining the corresponding pantograph core components based on the combination of key pantograph parameters.

[0043] Construct an equivalent proxy model corresponding to the core components of the pantograph; determine the failure probability of each core component of the pantograph based on the stress distribution output by the equivalent proxy models corresponding to all the core components of the pantograph.

[0044] This invention, by acquiring the pantograph's dynamic model and using its key parameters as design variables for parameter inversion calculation, can accurately determine the combination of key pantograph parameters that meet the target value of the pantograph-catenary contact force. This ensures that the contact force between the pantograph and the catenary meets design requirements during actual operation, thereby guaranteeing stable pantograph operation and reducing the risk of failures due to abnormal contact force. Secondly, by incorporating multiple factors, including connection stiffness, damping, pantograph-catenary contact parameters, and the stiffness and damping of the pantograph head spring, the analysis of the pantograph becomes more comprehensive, allowing for a more accurate understanding of its operating characteristics and providing a more reliable basis for subsequent fault prediction. By constructing an equivalent proxy model of the pantograph's core components, a refined analysis of these components can be achieved, simulating the stress distribution of the core components during actual operation, thus providing a direct basis for assessing the probability of failure. By determining the failure probability of each core component of the pantograph through the stress distribution output by the equivalent proxy model, the quantification and scientification of fault prediction are realized, enabling a more accurate assessment of fault risk and providing scientific decision support for pantograph maintenance and management.

[0045] The present invention also provides a pantograph fault prediction system, a computer-readable storage medium, an electronic device, and a computer program product, which have the above-mentioned beneficial effects, and will not be elaborated here. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0047] Figure 1 A flowchart of a pantograph fault prediction method provided in an embodiment of the present invention;

[0048] Figure 2 This is a schematic diagram of the pantograph dynamics model construction provided in an embodiment of the present invention;

[0049] Figure 3 This is a schematic diagram illustrating the process of generating the equivalent proxy model of the upper arm provided in an embodiment of the present invention;

[0050] Figure 4 This is a schematic diagram illustrating the cross-platform 3D graphical implementation process provided in an embodiment of the present invention;

[0051] Figure 5 This is a schematic diagram of a pantograph fault prediction system provided in an embodiment of the present invention;

[0052] Figure 6 This is a structural diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0054] See Figure 1 , Figure 1 A flowchart of a pantograph fault prediction method provided in an embodiment of the present invention is shown. The method includes:

[0055] S101: Obtain the pantograph dynamics model;

[0056] S102: Using the key parameters in the pantograph dynamic model as design variables, and taking the pantograph-catenary contact force as the target value, the parameter inversion calculation process is called to iteratively calculate the combination of key pantograph parameters that meet the target value; the key parameters include at least one of the following: connection stiffness, damping, pantograph-catenary contact parameters, pantograph head spring stiffness, and damping.

[0057] S103: Determine the corresponding pantograph core components based on the combination of key pantograph parameters;

[0058] S104: Construct an equivalent proxy model corresponding to the core components of the pantograph;

[0059] S105: Determine the failure probability of each pantograph core component based on the stress distribution output by the equivalent proxy model corresponding to all the pantograph core components.

[0060] There are no restrictions on how the pantograph dynamic model is constructed. The dynamic model of the pantograph is established by combining theoretical analysis and experimental verification. This model needs to consider various forces and motion characteristics of the pantograph during operation, including the interaction force between the pantograph head and the contact wire, the vibration characteristics of the pantograph, and its relationship with factors such as train speed.

[0061] One feasible implementation method may include the following steps:

[0062] The first step is to construct a rigid-flexible coupling dynamic simulation model that is proportional to the current collection experimental platform of the pantograph and wire mesh.

[0063] The second step is to set up simulation conditions and, based on each simulation condition, call the rigid-flexible coupling dynamic simulation model to perform dynamic experiments.

[0064] The third step is to extract the time-domain data of the change of the pantograph-catenary contact force over time during the dynamic experiment.

[0065] The fourth step is to use the time-domain data as the target value to perform parameter inversion and obtain the pantograph dynamic model.

[0066] See Figure 2 , Figure 2 This is a schematic diagram illustrating the construction of the pantograph dynamics model provided in an embodiment of the present invention. Figure 2The pantograph-catenary system is divided into three parts: a six-degree-of-freedom platform, a robotic arm, and the pantograph. In implementation, precise geometric models of the pantograph and contact network are created using 3D modeling software, based on the actual dimensions and structure of the current collection experimental platform. The model dimensions must be completely consistent with the actual experimental platform, including the pantograph's sliding plate, support, connecting components, and the contact network's conductor and suspension device. During the construction of the rigid-flexible coupling dynamic simulation model, corresponding material properties, such as elastic modulus, density, and Poisson's ratio, need to be assigned to each component. The pantograph sliding plate is typically made of carbon fiber, while the contact network conductor is made of copper alloy. Other structural components have their parameters set according to the actual materials. Simultaneously, the flexible components of the pantograph (such as the sliding plate and the pantograph head) are coupled with the rigid components (such as the pantograph frame and connecting parts). A rigid-flexible coupling dynamic model is established using multibody dynamics software, and the deformation characteristics of the flexible components are introduced by defining the modal analysis results of the flexible body. Furthermore, the contact relationship between the pantograph sliding plate and the contact network conductor needs to be defined in the simulation model. The calculation method for contact force is set, including the calculation formulas for normal contact force and tangential contact force, taking into account factors such as friction coefficient and contact pressure.

[0067] When setting up simulation conditions, various simulation conditions are defined based on the actual operating scenario and research needs. Common conditions include different operating speeds (e.g., low, medium, and high speeds), different contact wire tensions, different changes in contact wire height, and different pantograph lifting pressures. In the dynamic simulation software, corresponding parameters are set according to the defined conditions. For example, the pantograph's operating speed, the contact wire tension, and the geometric changes of the conductor are adjusted. After the simulation conditions and parameters are determined, the simulation software can be started to run the dynamic simulation experiment. The simulation software can calculate the dynamic behaviors such as the interaction force, trajectory, and vibration response between the pantograph and the contact wire based on the set conditions and model parameters. During the simulation experiment, simulation results are recorded in real time, including key data such as the pantograph's position, velocity, acceleration, and contact force. This data will serve as the basis for subsequent analysis.

[0068] Contact force data between the pantograph and the overhead contact line is extracted from the output of dynamic simulation software. Typically, this data is stored as a time series, including normal and tangential contact forces. To ensure accuracy, preliminary processing of the extracted contact force data can be performed, such as noise removal and smoothing. During data analysis, time-domain analysis can be conducted on the processed contact force data to observe its variation over time. Analyzing the peak value, frequency, and fluctuation range of the contact force reveals characteristics reflecting the interaction between the pantograph and the overhead contact line.

[0069] Parameter inversion yields a pantograph dynamics model that most closely approximates actual operating conditions, improving the model's prediction accuracy and reliability. No specific limitations are placed on the parameter inversion methods that can be used, including but not limited to least squares, genetic algorithms, and particle swarm optimization. The objective function is typically the error between the target value (time-domain data) and the model's predicted value. The selected optimization algorithm is used to optimize the parameters in the pantograph dynamics model. During optimization, the model parameters are continuously adjusted to minimize the objective function value, meaning the model-predicted contact force is closest to the actual time-domain data. After optimization, the obtained pantograph dynamics model is validated using some unoptimized time-domain data. By comparing the model's predictions with the actual data, the model's accuracy and reliability are evaluated.

[0070] Specifically, key parameters in the pantograph dynamics model and target values ​​for pantograph-catenary contact force can be set first. Then, the pantograph dynamics model can be run based on the key parameters and target values ​​to conduct simulation experiments and obtain simulation results.

[0071] Compare the simulation results with the target values, calculate the error value, and then iteratively adjust the design variables using the set optimization algorithm until the error value meets the set error range. Finally, output the combination of key pantograph parameters that meets the target value.

[0072] Based on the physical meaning of the pantograph dynamics model and actual requirements, key parameters affecting the pantograph-catenary contact force are selected. Simultaneously, target values ​​for the pantograph-catenary contact force are set based on actual operational requirements or experimental data. Target values ​​can be the average value, peak value, or fluctuation range of the contact force. For example, the target value can be set as an average contact force within a certain range (e.g., 20-30 N), with a fluctuation range not exceeding 10 N.

[0073] Input the key parameter values ​​set in the first step into the pantograph dynamic model, start the dynamic simulation software, and run the simulation experiment. Based on the set key parameters, calculate the interaction process between the pantograph and the overhead contact line, and obtain the simulation results. Extract the simulation results from the simulation software, focusing on the time-domain data of the pantograph-catenary contact force as a function of time, for subsequent error calculation.

[0074] When calculating the error value, you can choose an appropriate error calculation method, such as root mean square error (RMSE), mean absolute error (MAE), or maximum error.

[0075] Choose a suitable optimization algorithm, such as a genetic algorithm, particle swarm optimization, or gradient descent. During optimization, first initialize the values ​​of the design variables (i.e., key parameters), run the pantograph dynamics model, obtain simulation results, and calculate the error value. Use the optimization algorithm to adjust the values ​​of the design variables to reduce the error value. Repeat the above process until the error value is no greater than the set error interval. When the error value meets the set error interval, output the current combination of design variables (key parameters). These parameter combinations ensure that the simulation results of the pantograph dynamics model are as close as possible to the target values.

[0076] In step S103, based on the key parameter combinations obtained in S102, the structure and function of the pantograph are analyzed to identify the core components directly related to the key parameters. For example, the stiffness and damping of the connection points may be related to the pantograph's support structure, while the stiffness and damping of the bow head spring are related to the bow head assembly. By analyzing the impact of key parameters on pantograph performance, the core components of the pantograph are identified, avoiding the computational complexity and resource waste caused by a comprehensive analysis of the entire pantograph.

[0077] In step S104, an equivalent surrogate model is constructed for each core component of the pantograph. The equivalent surrogate model can be implemented by simplifying the physical model, using numerical methods (such as finite element analysis), or by data-driven methods (such as machine learning models). This model needs to accurately reflect the stress distribution of the pantograph's core components during actual operation. For example, for the pantograph's support structure, an equivalent surrogate model can be constructed using finite element analysis software to simulate the stress distribution under different operating conditions.

[0078] In one feasible implementation approach, the construction process of the equivalent proxy model can be as follows:

[0079] The first step is to obtain the design variables and design space of the pantograph core component; the design space is the range of values ​​for the design variables.

[0080] The second step is to conduct design experiments on the pantograph core component to obtain performance data of the pantograph core component under different combinations of design variables.

[0081] The third step is to determine the corresponding approximate model type based on the data characteristics of the pantograph core components.

[0082] Fourth step: Initialize the approximate model corresponding to the approximate model type using the performance data to obtain the equivalent proxy model.

[0083] Identify the core components of the pantograph system, such as the pantograph slide, pantograph head, and pantograph frame. For each core component, determine its design variables. Design variables can be geometric parameters (such as the length, width, and thickness of the slide), material properties (such as elastic modulus and density), and operating parameters (such as lifting pressure and contact force). Define a reasonable range of values ​​for each design variable, i.e., the design space.

[0084] Based on the design variables and design space determined in the first step, design the experimental plan. Experimental design methods (such as Latin hypercube design or orthogonal experimental design) can be used to reasonably arrange the experimental points to ensure that the experiment covers all areas of the design space. Prepare the necessary equipment and materials for the experiment, including prototypes of the pantograph core components, test platforms, sensors, etc. Adjust the values ​​of the design variables one by one according to the experimental design plan, and conduct the experiment.

[0085] Analyze the acquired performance data to understand its characteristics. Based on these characteristics, select an appropriate approximation model type. This approximation model type includes, but is not limited to, multinomial models, vector machine models, and neural network models.

[0086] Based on the selected approximation model type, the model is initialized using performance data. The initialized model is then validated using data not used in model training to evaluate its predictive accuracy. Common validation metrics include root mean square error (RMSE) and mean absolute error (MAE). Based on the validation results, the model is optimized and adjusted. For example, model parameters (such as the order of the polynomial, the number of layers in the neural network, and the number of nodes) are adjusted to improve predictive accuracy. After optimization and adjustment, the final equivalent surrogate model is obtained. This model can be used to quickly predict the performance of the pantograph's core components under different combinations of design variables. Thus, an equivalent surrogate model that accurately reflects the performance of the pantograph's core components is obtained. This model can replace complex physical experiments or numerical simulations, quickly evaluate the performance of different design schemes, and significantly improve the efficiency and accuracy of design optimization.

[0087] For example, see the boom. Figure 3 , Figure 3 This is a schematic diagram of the generation process of the equivalent surrogate model of the upper arm provided in the embodiment of the present invention. The magnitude of the force on the upper arm during the pantograph-catenary contact motion under different working conditions is extracted. The sample is sampled through the ISIGHT platform, and the stress and deformation results of the upper arm under all sample working conditions are calculated. The equivalent surrogate model of the upper arm with FMU (Functional Mock-up Unit) as the carrier is generated through sample training. It is used for rapid performance prediction of the diagnostic system with a response rate of milliseconds.

[0088] In one feasible implementation, after obtaining the equivalent proxy model, the credibility of the approximate model is evaluated. If the approximate model is credible, the approximate model is used to replace the simulation program of the pantograph core component, and the equivalent proxy model is packaged into a standardized simulation file.

[0089] In step S105, the stress distribution output from the equivalent surrogate model of each pantograph core component is combined with the fatigue limit, ultimate tensile strength, and other characteristics of the material. The failure probability of each pantograph core component is calculated using probabilistic statistical methods (such as Monte Carlo simulation). Specifically, based on the stress distribution, the stress changes of the component during long-term operation are simulated to assess the probability that it exceeds the material limit, thereby determining the failure probability.

[0090] In one feasible implementation, when assessing the failure probability of the pantograph's core components, a 3D graphical representation can be used to render the pantograph's 3D status in real time, overlaying a failure probability heatmap and a stress distribution cloud map. This allows maintenance personnel to remotely perform multi-angle interactive analysis and quickly locate potential hazards. This function is significantly superior to a single-platform solution, improving dispatch response efficiency. A feasible specific implementation process can be as follows:

[0091] The first step is to map the stress distribution output by the equivalent proxy model corresponding to all the pantograph core components into several heat maps;

[0092] The second step is to overlay the heat map onto the digital twin of the pantograph to obtain a visual schematic diagram of the pantograph.

[0093] The third step is to determine the failure probability of each pantograph core component using a set reliability analysis method and the aforementioned pantograph visualization diagram.

[0094] Step 4: Overlay the fault probability distribution map corresponding to the fault probability onto the pantograph visualization diagram, and use color coding to represent different fault probabilities.

[0095] See Figure 4 , Figure 4 This is a schematic diagram illustrating the cross-platform 3D visualization implementation process provided in this embodiment of the invention. A 3D visualization system can be developed based on Unity URP (Universal Render Pipeline), mapping the stress distribution output by the equivalent proxy model to a heatmap, which is then overlaid onto the pantograph digital twin. The XR interaction protocol supports visualization terminals for pantograph status monitoring. This visualization terminal can include VR headsets (remote experts), mobile devices (vehicle engineers), PC consoles (dispatch centers), etc., further enabling multi-terminal synchronous viewing of fault probability heatmaps.

[0096] This invention, through obtaining the pantograph's dynamic model and using its key parameters as design variables for parameter inversion calculation, can accurately determine the combination of key pantograph parameters that meet the target value of the pantograph-catenary contact force. This ensures that the contact force between the pantograph and the catenary meets design requirements during actual operation, thereby guaranteeing stable pantograph operation and reducing the risk of failures due to abnormal contact force. Secondly, by incorporating multiple factors, including connection stiffness, damping, pantograph-catenary contact parameters, and the stiffness and damping of the pantograph head spring, the analysis of the pantograph becomes more comprehensive, allowing for a more accurate understanding of its operating characteristics and providing a more reliable basis for subsequent fault prediction. Furthermore, by constructing an equivalent proxy model of the pantograph's core components, a refined analysis of these components can be achieved, simulating the stress distribution of the core components during actual operation, thus providing a direct basis for assessing the probability of failure. By using the stress distribution output by the equivalent surrogate model, the failure probability of each pantograph core component is determined, realizing the quantification and scientification of failure prediction. This enables a more accurate assessment of failure risks and provides scientific decision support for the maintenance and management of the pantograph.

[0097] See Figure 5 , Figure 5 This is a schematic diagram of a pantograph fault prediction system provided in an embodiment of the present invention. The system includes:

[0098] The model acquisition module is used to acquire the pantograph dynamics model;

[0099] The key parameter determination module is used to take the key parameters in the pantograph dynamic model as design variables, take the pantograph-catenary contact force as the target value, and call the parameter inversion calculation process to iteratively calculate the combination of key pantograph parameters that meet the target value; the key parameters include at least one of connection stiffness, damping, pantograph-catenary contact parameters, pantograph head spring stiffness, and damping.

[0100] A pantograph core component setting module is used to determine the corresponding pantograph core component based on the combination of key pantograph parameters.

[0101] An equivalent proxy model construction module is used to construct an equivalent proxy model corresponding to the core components of the pantograph.

[0102] The failure probability prediction module is used to determine the failure probability of each pantograph core component based on the stress distribution output by the equivalent proxy model corresponding to all the pantograph core components.

[0103] Based on the above embodiments, as a preferred embodiment, the model acquisition module includes:

[0104] The model building unit is used to build a rigid-flexible coupling dynamic simulation model with the same scale as the pantograph-net current collection experimental platform;

[0105] The simulation experiment unit is used to set up simulation conditions and, based on each simulation condition, call the rigid-flexible coupling dynamic simulation model to execute dynamic experiments.

[0106] The data extraction unit is used to extract time-domain data of the change of the bow-catenary contact force over time during the dynamic experiment.

[0107] The model generation unit is used to perform parameter inversion using the time-domain data as the target value to obtain the pantograph dynamic model.

[0108] Based on the above embodiments, as a preferred embodiment, the key parameter determination module is a module for performing the following steps:

[0109] Define the key parameters in the pantograph dynamics model, as well as the target value of the pantograph-catenary contact force;

[0110] Based on the key parameters and target values, the pantograph dynamics model is run to conduct a simulation experiment, and the simulation results are obtained.

[0111] Compare the simulation results with the target value, and calculate the error value;

[0112] The design variables are adjusted iteratively using a set optimization algorithm until the error value meets the set error range, and then the combination of key pantograph parameters that meets the target value is output.

[0113] Based on the above embodiments, as a preferred embodiment, the equivalent proxy model construction module is a module used to execute the steps:

[0114] Obtain the design variables and design space of the pantograph core component; the design space is the range of values ​​for the design variables.

[0115] Design experiments were performed on the pantograph core component to obtain performance data of the pantograph core component under different combinations of design variables;

[0116] The corresponding approximate model type is determined based on the data characteristics of the pantograph core components;

[0117] The approximate model corresponding to the approximate model type is initialized using the performance data to obtain the equivalent proxy model.

[0118] Based on the above embodiments, as a preferred embodiment, it further includes:

[0119] The model evaluation module is used to evaluate the credibility of the approximate model. If the approximate model is credible, the approximate model is used to replace the simulation program of the pantograph core component, and the equivalent proxy model is encapsulated into a standardized simulation file.

[0120] Based on the above embodiments, as a preferred embodiment, the fault probability prediction module is a module for performing the following steps:

[0121] The stress distribution output by the equivalent proxy model corresponding to all the pantograph core components is mapped into several heat maps;

[0122] The heat map is overlaid onto the digital twin of the pantograph to obtain a visual schematic diagram of the pantograph;

[0123] The failure probability of each core component of the pantograph is determined by using a set reliability analysis method and a visual schematic diagram of the pantograph.

[0124] The fault probability distribution map corresponding to the fault probability is superimposed on the pantograph visualization diagram, and different fault probabilities are represented by color coding.

[0125] The present invention also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method described in the above method embodiments.

[0126] It is understood that if the methods in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0127] The computer-readable storage medium provided in this embodiment includes the method mentioned above, and has the same effect.

[0128] The present invention also provides an electronic device, see [link to relevant documentation]. Figure 6 The present invention provides a structural diagram of an electronic device, as shown in the embodiment of the invention. Figure 6 As shown, it may include a processor 1410 and a memory 1420.

[0129] The processor 1410 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 1410 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 1410 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 1410 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 1410 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0130] The memory 1420 may include one or more computer-readable storage media, which may be non-transitory. The memory 1420 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 1420 is used to store at least the following computer program 1421, which, after being loaded and executed by the processor 1410, is capable of implementing the relevant steps in the methods executed by the electronic device side as disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 1420 may also include an operating system 1422 and data 1423, etc., and the storage method may be temporary storage or permanent storage. The operating system 1422 may include Windows, Linux, Android, etc.

[0131] In some embodiments, the electronic device may further include a display screen 1430, an input / output interface 1440, a communication interface 1450, a sensor 1460, a power supply 1470, and a communication bus 1480.

[0132] certainly, Figure 6 The structure of the electronic device shown does not constitute a limitation on the electronic device in the embodiments of the present invention. In practical applications, the electronic device may include more than […]. Figure 6 More or fewer components as shown, or combinations of certain components.

[0133] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. As the system provided in the embodiments corresponds to the method provided in the embodiments, the description is relatively simple; relevant parts can be found in the method section.

[0134] This article uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. It should be noted that those skilled in the art can make several improvements and modifications to the present invention without departing from the principles of the present invention, and these improvements and modifications also fall within the protection scope of the present invention.

[0135] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method for predicting pantograph faults, characterized in that, include: Obtain the pantograph dynamics model; Using the key parameters in the pantograph dynamics model as design variables and the pantograph-catenary contact force as the target value, the parameter inversion calculation process is called to iteratively calculate the combination of key pantograph parameters that meet the target value; the key parameters include at least one of the following: connection stiffness, damping, pantograph-catenary contact parameters, pantograph head spring stiffness, and damping. The corresponding core components of the pantograph are determined based on the combination of key pantograph parameters. Construct an equivalent proxy model corresponding to the core components of the pantograph; The failure probability of each pantograph core component is determined based on the stress distribution output by the equivalent proxy model corresponding to all the pantograph core components. The process of obtaining the pantograph dynamics model includes: Construct a rigid-flexible coupling dynamic simulation model with the same scale as the pantograph-net current collection experimental platform; Set up simulation conditions, and execute dynamic experiments by calling the rigid-flexible coupling dynamic simulation model based on each simulation condition; Extract the time-domain data of the pantograph-catenary contact force as a function of time during the dynamic experiment; Using the time-domain data as the target value, parameter inversion is performed to obtain the pantograph dynamic model; The construction of the equivalent proxy model corresponding to the core component of the pantograph includes: Obtain the design variables and design space of the pantograph core component; the design space is the range of values ​​for the design variables. Design experiments were performed on the pantograph core component to obtain performance data of the pantograph core component under different combinations of design variables; The corresponding approximate model type is determined based on the data characteristics of the pantograph core components; The approximate model corresponding to the approximate model type is initialized using the performance data to obtain the equivalent proxy model.

2. The pantograph fault prediction method according to claim 1, characterized in that, Using the key parameters in the pantograph dynamics model as design variables, and with the pantograph-catenary contact force as the target value, the combination of key pantograph parameters that meets the target value is iteratively calculated using the parameter inversion calculation process. This combination includes: Define the key parameters in the pantograph dynamics model, as well as the target value of the pantograph-catenary contact force; Based on the key parameters and target values, the pantograph dynamics model is run to conduct a simulation experiment, and the simulation results are obtained. Compare the simulation results with the target value, and calculate the error value; The design variables are adjusted iteratively using a set optimization algorithm until the error value meets the set error range, and then the combination of key pantograph parameters that meets the target value is output.

3. The method according to claim 1, characterized in that, After initializing the approximate model corresponding to the approximate model type using the performance data to obtain the equivalent proxy model, the process further includes: The credibility of the approximate model is evaluated. If the approximate model is credible, it is used to replace the simulation program of the pantograph core component, and the equivalent proxy model is encapsulated into a standardized simulation file.

4. The pantograph fault prediction method according to claim 1, characterized in that, The failure probability of each pantograph core component is determined based on the stress distribution output by the equivalent surrogate model corresponding to all of the pantograph core components, including: The stress distribution output by the equivalent proxy model corresponding to all the pantograph core components is mapped into several heat maps; The heat map is overlaid onto the digital twin of the pantograph to obtain a visual schematic diagram of the pantograph; The failure probability of each core component of the pantograph is determined by using a set reliability analysis method and a visual schematic diagram of the pantograph. The fault probability distribution map corresponding to the fault probability is superimposed on the pantograph visualization diagram, and different fault probabilities are represented by color coding.

5. A pantograph fault prediction system, characterized in that, include: The model acquisition module is used to acquire the pantograph dynamics model; The key parameter determination module is used to take the key parameters in the pantograph dynamic model as design variables, take the pantograph-catenary contact force as the target value, and call the parameter inversion calculation process to iteratively calculate the combination of key pantograph parameters that meet the target value; the key parameters include at least one of connection stiffness, damping, pantograph-catenary contact parameters, pantograph head spring stiffness, and damping. A pantograph core component setting module is used to determine the corresponding pantograph core component based on the combination of key pantograph parameters. An equivalent proxy model construction module is used to construct an equivalent proxy model corresponding to the core components of the pantograph. The failure probability prediction module is used to determine the failure probability of each pantograph core component based on the stress distribution output by the equivalent proxy model corresponding to all the pantograph core components. The model acquisition module includes: The model building unit is used to build a rigid-flexible coupling dynamic simulation model with the same scale as the pantograph-net current collection experimental platform; The simulation experiment unit is used to set up simulation conditions and, based on each simulation condition, call the rigid-flexible coupling dynamic simulation model to execute dynamic experiments. The data extraction unit is used to extract time-domain data of the change of the bow-catenary contact force over time during the dynamic experiment. The model generation unit is used to perform parameter inversion using the time-domain data as the target value to obtain the pantograph dynamic model. The equivalent proxy model construction module is used to execute the steps. Obtain the design variables and design space of the pantograph core component; the design space is the range of values ​​for the design variables. Design experiments were performed on the pantograph core component to obtain performance data of the pantograph core component under different combinations of design variables; The corresponding approximate model type is determined based on the data characteristics of the pantograph core components; The approximate model corresponding to the approximate model type is initialized using the performance data to obtain the equivalent proxy model.

6. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed, implements the steps of the method as described in any one of claims 1 to 4.

8. A computer program product, characterized in that, It includes a computer program that, when executed, implements the steps of the method as described in any one of claims 1 to 4.

Images