Converter valve weak link solving method and device, storage medium and computer equipment

Abstract

The invention relates to the technical field of electrical equipment fault prediction, and discloses a converter valve weak link solving method and device, a storage medium and computer equipment, and the method comprises the steps: building a substructure model corresponding to a system of a to-be-discriminated converter valve, and carrying out the interpolation optimization, and obtaining a plurality of reduced-order substructure models; distributing the reduced-order substructure model to a plurality of processors for parallel processing, calculating an analysis result by using an isogeometric analysis method, solving the analysis result by using a multi-objective evolutionary algorithm, and performing optimization iteration on a solution of each finite element model by using a Pareto transfer strategy to obtain an optimal parameter set; and constructing a nonlinear equation according to the operation data of the converter valve to be discriminated, solving the nonlinear equation by using the optimal parameter set, and identifying a temperature abnormal point of the converter valve to determine a weak link. According to the method, the weak link identification speed and precision of the converter valve are improved, the temperature abnormal region is accurately positioned, and clear fault diagnosis information is provided for maintenance personnel.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical equipment fault prediction, and in particular to a method, device, storage medium and computer equipment for solving weak links of a converter valve. Background Art

[0002] Thyristor commutator valves are key equipment in high-voltage direct current projects. They have high current capacity and are particularly suitable for large-capacity, long-distance power transmission applications. Considering that the structure of thyristor commutator valves is very complex and that long-term operation in a harsh working environment with complex electromagnetic multi-physical fields will accelerate the aging process of the device and increase the failure rate, the reliability of commutator valve operation is relatively weak.

[0003] The weak links of the converter valve mostly refer to abnormally high temperature hot spots. At present, the operation and maintenance process of the converter valve mainly relies on manual inspection, robot inspection and regular shutdown and maintenance. In addition, the existing converter valve monitoring technology and valve hall monitoring methods are limited to the sensor volume structure and the stacking of valve towers. It is impossible to accurately perceive the working status of key components in the valve tower, and there are problems such as slow speed and low accuracy in judging the weak links of the converter valve. Summary of the invention

[0004] In view of this, the present application provides a method, device, storage medium and computer equipment for solving the weak link of a converter valve, the main purpose of which is to solve the technical problems of slow speed and low accuracy in identifying the weak link of a converter valve in the prior art.

[0005] According to a first aspect of the present invention, a method for solving weak links in a converter valve is provided, the method comprising:

[0006] Identify multiple subsystems of the converter valve to be identified, establish a substructure model corresponding to each of the subsystems, and perform interpolation optimization on the multiple substructure models to obtain multiple reduced-order substructure models;

[0007] Distributing the plurality of reduced-order substructure models to a plurality of processors for parallel processing, constructing a finite element model and calculating the analysis result of each finite element model using an isogeometric analysis method;

[0008] Determine the complexity of the multiple finite element models, and use a multi-objective evolutionary algorithm to solve the analysis results of the finite element models to obtain a solution of each finite element model, and use a Pareto transfer strategy to iterate the solution of each finite element model to obtain an optimal parameter set;

[0009] A nonlinear equation is constructed according to the operation data of the converter valve to be identified, the nonlinear equation is solved using the optimal parameter set, and the temperature abnormal point of the converter valve to be identified is identified to determine the weak link of the converter valve to be identified.

[0010] Optionally, performing interpolation optimization on the multiple substructure models respectively to obtain multiple reduced-order substructure models includes:

[0011] Collecting experimental data of the converter valve to be identified and preprocessing the experimental data;

[0012] Determining a target interpolation method based on data characteristics and data requirements of the experimental data;

[0013] An interpolation model is established according to the target interpolation method, and the substructure model is interpolated and optimized using the interpolation model to obtain an initial reduced-order substructure model;

[0014] Auxiliary variables are constructed, and model parameters of the initial reduced-order substructure model are adjusted based on the auxiliary variables to optimize the initial reduced-order substructure model to obtain a reduced-order substructure model.

[0015] Optionally, constructing auxiliary variables and adjusting model parameters of the initial reduced-order substructure model based on the auxiliary variables to optimize the initial reduced-order substructure model to obtain the reduced-order substructure model includes:

[0016] Obtaining the electron current equation and the hole current equation of the converter valve to be identified under one-dimensional conditions;

[0017] Construct auxiliary variables, obtain the electron current equation and hole current equation under different injection conditions based on the electric field distribution of the power chip in the converter valve to be identified, and then solve the electron current and hole current at discrete points in the electron current and hole current equation under one-dimensional conditions;

[0018] The reduced-order substructure model is determined according to the electron current equation and the hole current equation under the one-dimensional condition and the electron current and the hole current at the discrete points.

[0019] Optionally, allocating the plurality of reduced-order substructure models to a plurality of processors for parallel processing comprises:

[0020] Determining the complexity of each of the reduced-order substructure models based on the meshing level and computational complexity;

[0021] Determine computing units of a plurality of processors, match the computing units of the processors with the complexity of the reduced-order substructure model, and determine a processor corresponding to each of the reduced-order substructure models;

[0022] The plurality of processors are used to process the plurality of reduced-order substructure models in parallel.

[0023] Optionally, the constructing of finite element models and calculating the analysis results of each finite element model using isogeometric analysis method includes:

[0024] Constructing a finite element model of the reduced-order substructure model according to a transient thermal-structural weak coupling problem;

[0025] Based on the initial design parameters and initial constraint conditions, the finite element model is analyzed using an isogeometric analysis method to obtain an initial analysis result;

[0026] The finite element model is optimized based on the initial analysis result, and the optimized finite element model is re-estimated using a re-analysis algorithm to obtain an analysis result corresponding to the finite element model.

[0027] Optionally, determining the complexity of the multiple finite element models and solving the analysis results of the finite element models using a multi-objective evolutionary algorithm to obtain a solution for each of the finite element models includes:

[0028] Determining the complexity of the finite element model using a complexity dynamic adjustment method, wherein the finite element model includes a low complexity model and a high complexity model;

[0029] According to the multi-objective optimization problem, relevant objective functions and multiple constraints are established. Based on minimizing the relevant objective functions, the multi-objective evolutionary algorithm is used to solve the analysis results of the finite element model to obtain the solution of each of the finite element models.

[0030] Optionally, the method of optimizing and iterating the solution of each finite element model using the Pareto transfer strategy to obtain an optimal parameter set includes:

[0031] Obtaining a solution to the low-complexity model, and using the solution to the low-complexity model as an initial search population for the high-complexity model;

[0032] The search population during iteration of the high-complexity model is determined, a local search function is obtained, and the local search function is updated based on the parameters of the high-complexity model and the search population to obtain an optimal parameter set.

[0033] According to a second aspect of the present invention, a device for solving weak links of a converter valve is provided, the device comprising:

[0034] A data acquisition module, used to acquire simulation data samples of the multi-physical field of the converter valve under all working conditions by using a preset multi-physical field simulation model of the converter valve;

[0035] A data extension module, used for constructing a least squares generative adversarial network, training the least squares generative adversarial network based on the simulation data sample to obtain a multi-physics field parameter sample, and combining the simulation data sample with the multi-physics field parameter sample to obtain an extended data sample;

[0036] A model evaluation module, used to preprocess the extended data samples, train and evaluate a preset evaluation model using the preprocessed extended data samples, and generate a target evaluation model;

[0037] The result output module is used to establish a fault prediction model based on the extended data sample and the target evaluation model, collect multi-physical field data of the converter valve, and use the fault prediction model to process the multi-physical field data of the converter valve to obtain a converter valve fault prediction result.

[0038] According to a third aspect of the present invention, there is provided a storage medium on which a computer program is stored, and when the program is executed by a processor, the above-mentioned method for solving the weak link of the converter valve is implemented.

[0039] According to a fourth aspect of the present invention, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned method for solving weak links of a converter valve when executing the program.

[0040] The present invention provides a method, device, storage medium and computer equipment for solving weak links of a converter valve. First, multiple subsystems of the converter valve to be identified are identified, a substructure model corresponding to each subsystem is established, and multiple substructure models are interpolated and optimized respectively to obtain multiple reduced-order substructure models, and then the multiple reduced-order substructure models are distributed to multiple processors for parallel processing, a finite element model is constructed and the analysis result of each finite element model is calculated using the isogeometric analysis method, then the complexity of the multiple finite element models is determined, and the analysis results of the finite element model are solved using a multi-objective evolutionary algorithm to obtain a solution for each finite element model, and the solution of each finite element model is optimized and iterated using a Pareto transfer strategy to obtain an optimal parameter set, and finally a nonlinear equation is constructed according to the operating data of the converter valve to be identified, the nonlinear equation is solved using the optimal parameter set, and the temperature abnormality point of the converter valve to be identified is identified to determine the weak link of the converter valve to be identified. The above method is based on establishing a substructure model for the subsystem of the converter valve, and reducing the order of the model through interpolation optimization, which greatly reduces the computational complexity and makes the simulation more efficient; using multiple processors to process multiple reduced-order substructure models in parallel can significantly accelerate the entire simulation process and improve the simulation efficiency; constructing a finite element model and combining it with the isogeometric analysis method can further improve the solution efficiency while maintaining high accuracy, and more accurately capture the complex physical field changes inside the converter valve; using a multi-objective evolutionary algorithm, it is suitable for solving problems with multiple conflicting goals, and using the Pareto transfer strategy to optimize and iterate the model solution can improve the accuracy of predicting temperature anomaly points; constructing nonlinear equations based on actual operating data, and using the optimized parameter set to solve them, can more realistically reflect the working status of the converter valve. The above method improves the speed and accuracy of identifying weak links in the converter valve, accurately locates the temperature anomaly area, and provides clear fault diagnosis information for maintenance personnel.

[0041] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0043] Figure 1 A schematic flow chart of a method for solving weak links of a converter valve provided by an embodiment of the present invention is shown;

[0044] Figure 2The electric field distribution diagram of the power chip in the thyristor converter valve in the method for solving the weak link of the converter valve provided by the embodiment of the present invention is shown;

[0045] Figure 3 A block diagram of an extended finite element method based on a reanalysis algorithm in a method for solving weak links of a converter valve provided by an embodiment of the present invention is shown;

[0046] Figure 4 A flow chart of a medium-geometry fast reanalysis algorithm of a method for solving weak links of a converter valve provided by an embodiment of the present invention is shown;

[0047] Figure 5 A junction temperature distribution cloud diagram of key components of a thyristor converter valve in a method for solving weak links of a converter valve provided by an embodiment of the present invention is shown;

[0048] Figure 6 A principle logic flow chart of a method for solving weak links of a converter valve provided by an embodiment of the present invention is shown;

[0049] Figure 7 A schematic structural diagram of a converter valve weak link solving device provided by an embodiment of the present invention is shown;

[0050] Figure 8 A schematic diagram of the device structure of a computer device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0051] The exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present application and to fully convey the scope of the present application to those skilled in the art.

[0052] The present application embodiment provides a method for solving weak links of a converter valve, such as Figure 1 As shown, the method comprises the following steps:

[0053] 101. Identify multiple subsystems of the converter valve to be identified, establish a substructure model corresponding to each subsystem, and perform interpolation optimization on the multiple substructure models to obtain multiple reduced-order substructure models.

[0054] Among them, taking the KPE4500-72 thyristor converter valve as an example, it is first necessary to decompose the entire converter valve and identify the key components or subsystems that constitute the converter valve. The subsystems include but are not limited to thyristors, heat sinks, capacitors, resistors, etc. Each subsystem has its specific functions and physical characteristics; for each identified subsystem, a mathematical or physical model that can reflect its main characteristics is established, which can accurately capture the dynamic behavior of the subsystem and how it interacts with other subsystems. For example, for thyristors, it may be necessary to consider its conduction characteristics and thermal characteristics; for heat sinks, it is necessary to consider its heat dissipation efficiency, etc., and then each substructure model is optimized by applying interpolation technology or other numerical methods. The purpose is to reduce the degrees of freedom in the model without sacrificing too much accuracy. The reduced-order substructure model obtained can perform calculations and analysis faster while maintaining sufficient accuracy to predict temperature anomalies and other potential problems.

[0055] In the embodiment of the present application, the reduced-order substructure model reduces the amount of calculation, making the simulation process more efficient and easier to understand and maintain. Each substructure model is relatively independent, and new components can be easily added or existing components can be modified as needed, thereby enhancing the flexibility of the system. Through detailed modeling of each subsystem, the working conditions inside the converter valve can be analyzed more carefully, so that potential problem areas can be discovered earlier, and the weak links of temperature anomalies can be identified more quickly and accurately. After the substructure model is established, it is necessary to use existing high-precision model calculation results or test data to further improve these models. Through model reduction technology, it is possible to use existing data sets for interpolation to obtain a more accurate model.

[0056] 102. Allocate multiple reduced-order substructure models to multiple processors for parallel processing, construct finite element models, and use isogeometric analysis to calculate the analysis results of each finite element model.

[0057] Among them, parallel computing is achieved by assigning different reduced-order substructure models to multiple processors or computing cores, and each processor is responsible for processing one or several substructure models; the finite element model is a numerical simulation technology that discretizes a continuous system into a series of small units, and then solves partial differential equations or other mathematical expressions on these units to obtain an approximate solution to the entire system; the isogeometric analysis method is an advanced finite element analysis method that uses the same basis functions in computer-aided design to perform geometric description and approximation of field variables. Compared with traditional finite element methods, the isogeometric analysis method can provide higher accuracy and better smoothness, especially when dealing with fields of complex shapes and high-order continuity. The isogeometric analysis method solves each finite element model to obtain the response of each substructure under specific working conditions, such as stress distribution, temperature field, electromagnetic field, etc. The analysis results can be used to evaluate the working status of each substructure and identify potential problem areas.

[0058] In the embodiments of the present application, the use of a distributed computing method can make full use of modern multi-core CPUs or cluster computing resources, significantly speed up the entire simulation process, and greatly shorten the overall calculation time through parallel processing; the isogeometric analysis method provides more accurate results than the traditional finite element method, which helps to better predict the thermal behavior and other physical phenomena inside the converter valve, thereby improving the safety and reliability of equipment operation; the fast and accurate computing power makes this technical solution suitable for application in real-time monitoring systems to promptly detect abnormal conditions of the converter valve.

[0059] 103. Determine the complexity of multiple finite element models, and use a multi-objective evolutionary algorithm to solve the analysis results of the finite element models to obtain the solution of each finite element model. Use the Pareto transfer strategy to optimize and iterate the solution of each finite element model to obtain the optimal parameter set.

[0060] Among them, the complexity of each finite element model is evaluated, including factors such as mesh density, unit type, and material properties. The complexity is usually proportional to the computational cost, that is, the more complex the model, the more computing resources and time it requires; the multi-objective evolutionary algorithm is a global search algorithm that can find the optimal compromise solution between multiple conflicting objectives. The multi-objective evolutionary algorithm is used to deal with multi-objective optimization problems. Specifically applied in this application, it can be used to find the best parameter set so that the computational cost can be minimized while ensuring a certain accuracy; the isogeometric rapid reanalysis technology uses the information in the initial analysis results. When the structure undergoes a small modification, the rapid reanalysis technology can provide new accurate estimates at a lower cost, avoiding the need to start a complete finite element analysis from scratch after each modification, thereby greatly saving computing time; the variable complexity method combines the advantages of low-complexity models and high-complexity models. During the iteration process, a low-complexity model is first used to quickly explore the possible solution space, and then switched to a high-complexity model when approaching the optimal solution to ensure the accuracy of the final result; pre-training can be based on historical data or existing knowledge to help the algorithm converge to a good solution faster, thereby accelerating the entire optimization process.

[0061] In the embodiments of the present application, by combining the multi-objective evolutionary algorithm with the variable complexity method, the overall computing cost can be significantly reduced while ensuring high precision, the speed of the optimization process is accelerated, and the complexity of the model can be adjusted according to different needs. It is suitable for both rapid evaluation in the preliminary design stage and the needs of later refined design; the isogeometric rapid reanalysis technology reduces unnecessary repeated calculations and improves computing efficiency; the Pareto transfer strategy helps to improve the quality of the initial solution, while the multi-objective evolutionary algorithm ensures that the quality of the solution is continuously improved throughout the optimization process until the optimal state is reached; due to the overall improvement in computing speed, it can better support real-time monitoring and dynamic adjustment, and can respond quickly to changes.

[0062] 104. Construct a nonlinear equation based on the operating data of the converter valve to be identified, solve the nonlinear equation using the optimal parameter set, identify the temperature abnormal point of the converter valve to be identified, and determine the weak link of the converter valve to be identified.

[0063] Among them, since the working state of the converter valve is affected by many factors, and there are often complex nonlinear relationships between these factors, it is usually necessary to construct a nonlinear equation describing the internal physical phenomena of the converter valve based on the actual operating data of the converter valve to accurately reflect this complexity; the optimal parameter set previously obtained by multi-objective evolutionary algorithm and other optimization techniques is substituted into the nonlinear equation, so that the equation can more accurately reflect the actual situation, and the nonlinear equation is solved by numerical method to obtain the specific working state of each subsystem. By analyzing the solution results, the area where the temperature exceeds the normal range, that is, the temperature anomaly point, is identified. Among them, the temperature anomaly is usually an early sign of equipment overheating or local failure. Based on the location and nature of the temperature anomaly point, combined with the structural characteristics and working principle, it is judged which parts are the weak links of the converter valve. The weak links may be caused by design defects, material fatigue, cooling system failure and other reasons.

[0064] In the embodiment of the present application, by constructing a nonlinear equation based on actual operating data and using an optimized parameter set, the actual working state of the converter valve can be simulated more accurately, thereby improving the accuracy of fault diagnosis, and being able to quickly identify potential problem areas, providing clear guidance for operation and maintenance personnel, and helping to take action faster, reducing downtime and maintenance costs; discovering temperature anomalies in advance helps to take preventive measures to avoid serious failures caused by overheating and extend the service life of equipment; accurately locating weak links can enable targeted maintenance and inspection to avoid unnecessary large-scale inspections, thereby reducing overall maintenance costs.

[0065] The present invention provides a method, device, storage medium and computer equipment for solving weak links of a converter valve. First, multiple subsystems of the converter valve to be identified are identified, a substructure model corresponding to each subsystem is established, and multiple substructure models are interpolated and optimized respectively to obtain multiple reduced-order substructure models, and then the multiple reduced-order substructure models are distributed to multiple processors for parallel processing, a finite element model is constructed and the analysis result of each finite element model is calculated using the isogeometric analysis method, then the complexity of the multiple finite element models is determined, and the analysis results of the finite element model are solved using a multi-objective evolutionary algorithm to obtain a solution for each finite element model, and the solution of each finite element model is optimized and iterated using a Pareto transfer strategy to obtain an optimal parameter set, and finally a nonlinear equation is constructed according to the operating data of the converter valve to be identified, the nonlinear equation is solved using the optimal parameter set, and the temperature abnormality point of the converter valve to be identified is identified to determine the weak link of the converter valve to be identified. The above method is based on establishing a substructure model for the subsystem of the converter valve, and reducing the order of the model through interpolation optimization, which greatly reduces the computational complexity and makes the simulation more efficient; using multiple processors to process multiple reduced-order substructure models in parallel can significantly accelerate the entire simulation process and improve the simulation efficiency; constructing a finite element model and combining it with the isogeometric analysis method can further improve the solution efficiency while maintaining high accuracy, and more accurately capture the complex physical field changes inside the converter valve; using a multi-objective evolutionary algorithm, it is suitable for solving problems with multiple conflicting goals, and using the Pareto transfer strategy to optimize and iterate the model solution can improve the accuracy of predicting temperature anomaly points; constructing nonlinear equations based on actual operating data, and using the optimized parameter set to solve them, can more realistically reflect the working status of the converter valve. The above method improves the speed and accuracy of identifying weak links in the converter valve, accurately locates the temperature anomaly area, and provides clear fault diagnosis information for maintenance personnel.

[0066] Specifically, in the above-mentioned embodiment, multiple substructure models are interpolated and optimized respectively to obtain multiple reduced-order substructure models, including first collecting experimental data of the converter valve to be identified and preprocessing the experimental data; then determining the target interpolation method based on the data characteristics and data requirements of the experimental data; then establishing an interpolation model according to the target interpolation method, and using the interpolation model to interpolate and optimize the substructure model to obtain an initial reduced-order substructure model; finally, constructing auxiliary variables, and adjusting the model parameters of the initial reduced-order substructure model based on the auxiliary variables to optimize the initial reduced-order substructure model to obtain a reduced-order substructure model.

[0067] In this embodiment, data is collected from the actual operation of the converter valve to be identified or from a specially designed experiment. The data includes key parameters such as temperature distribution, current, voltage, and mechanical stress. The quality and quantity of the experimental data directly affect the accuracy of subsequent analysis. The collected data is cleaned to remove noise and outliers. Data standardization and normalization may also be included to ensure data consistency and comparability. Then, according to the characteristics of the experimental data and the analysis requirements, a suitable interpolation method is selected to ensure that sufficient accuracy is maintained while simplifying the model. Based on the selected interpolation method, a mathematical model is established to describe the relationship between data points. The interpolation model is used to interpolate the original sub-data points. The structural model is interpolated and optimized to reduce the degrees of freedom in the model while retaining its key characteristics as much as possible. Then, a simplified, low-dimensional substructure model is generated through the interpolation model, namely the initial reduced-order substructure model, which can accurately reflect the behavior of the original substructure to a certain extent. The introduction of auxiliary variables can help adjust and optimize the model parameters. The parameters of the initial reduced-order substructure model are adjusted by auxiliary variables to further improve the accuracy and applicability of the model. Through the iterative optimization process, the model is continuously improved until satisfactory performance indicators are achieved. The optimized reduced-order substructure model can more accurately represent the dynamic behavior of the actual system and has higher computational efficiency.

[0068] Furthermore, auxiliary variables are constructed, and model parameters of the initial reduced-order substructure model are adjusted based on the auxiliary variables to optimize the initial reduced-order substructure model to obtain the reduced-order substructure model, including first obtaining the electron current equation and the hole current equation of the converter valve to be identified under one-dimensional conditions, and then constructing auxiliary variables, obtaining the electron current equation and the hole current equation under different injection conditions based on the electric field distribution of the power chip in the converter valve to be identified, and then solving the electron current and the hole current at discrete points in the electron current and the hole current equation under one-dimensional conditions, and finally determining the reduced-order substructure model according to the electron current equation and the hole current equation under one-dimensional conditions and the electron current and the hole current at discrete points.

[0069] In this embodiment, the electron current and hole current equations under one-dimensional conditions are:

[0070]

[0071] Where n and p are the electron and hole concentrations in the base region, respectively, n = Δp + N B , p=Δp+n si 2 / N B ;n si is the intrinsic carrier concentration of silicon; μ n and μ p are the electron and hole mobilities, respectively; E is the electric field intensity;

[0072] The electric field distribution of the power chip in the thyristor commutator valve is as follows: Figure 2 As shown, combined with the relationship i ce =i p +i n and Δn=Δp, the electric field strength E in the current equation can be eliminated, and the electron current and hole current equations taking into account different injection conditions are obtained as shown;

[0073]

[0074] This application proposes a quick solution of auxiliary variable K, which can effectively speed up the solution:

[0075]

[0076] Based on the base charge continuity equation, the electron current and hole current at the discrete point can be obtained as

[0077]

[0078] Where, 0≤i≤N P -1;N P is the number of discrete units; n i =Δp i +N B ;p i =Δp+n si 2 / N B ; The method provided in this application has the advantages of high efficiency and accuracy when processing large-scale nonlinear solutions.

[0079] Specifically, in the above embodiment, multiple reduced-order substructure models are distributed to multiple processors for parallel processing, including first determining the complexity of each reduced-order substructure model based on the mesh division level and the computational complexity, then determining the computing units of multiple processors, matching the computing units of the processors with the complexity of the reduced-order substructure models, determining the processor corresponding to each reduced-order substructure model, and finally using multiple processors to process the multiple reduced-order substructure models in parallel.

[0080] In this embodiment, the computational tasks of multiple reduced-order substructure models are assigned to multiple processors for parallel processing. The computational unit size is allocated according to the complexity of each part of the model. Independent finite element analysis is performed on each substructure. Parallel processing is performed between the processors, which can effectively improve the computational efficiency. Each processor can independently perform parallel processing on a reduced-order substructure model, which can increase the computational speed and thus speed up the analysis process. For complex valve section structures, the number of processor allocation units can be increased in areas with fine mesh division, and the analysis can be simplified for unimportant areas.

[0081] The specific formula can be expressed as:

[0082]

[0083] Among them, G i Indicates that the i-th processor independently calculates; G = UF, G represents the global stiffness matrix, U is the unknown displacement vector, and F is the external force vector; G = G1 + G2 + ... + G n , the global stiffness matrix G is decomposed into the sum of the local stiffness matrices of multiple reduced-order substructure models;

[0084] Through parallel processing of multiple processors, matrix calculations can be completed faster. Each processor is responsible for an independent substructure and does not need to wait for the results of other processors. Parallel computing effectively reduces the overall calculation time in large-scale finite element analysis and greatly improves the efficiency of identifying weak links in the converter valve.

[0085] Specifically, in the above embodiment, a finite element model is constructed and the analysis results of each finite element model are calculated using the isogeometric analysis method, including first constructing a finite element model of a reduced-order substructure model based on a transient thermal-structural weak coupling problem, and then analyzing the finite element model based on initial design parameters and initial constraints using the isogeometric analysis method to obtain initial analysis results, and finally optimizing the finite element model based on the initial analysis results, and re-estimating the optimized finite element model using a re-analysis algorithm to obtain analysis results corresponding to the finite element model.

[0086] In this embodiment, the isogeometric fast reanalysis technology is used to solve the fast calculation of the multi-field finite element model. The reanalysis algorithm uses the initial analysis information to quickly estimate the modified structure, and can obtain more accurate analysis results at a lower computational cost. The reanalysis algorithm block diagram is shown in FIG. Figure 3As shown in the figure, compared with traditional finite element analysis, the reanalysis algorithm can obtain more accurate analysis results at a lower computational cost. Among them, CA computational analysis refers to a detailed computational analysis of the current design scheme to evaluate its performance; IFU nonlinear influence factor (Influence Function Unit) involves factors that consider nonlinear effects; IC initial conditions (Initial Conditions) refer to the initial state set when the analysis begins; MGR multi-level grid (Multi-Grid Refinement) is a method to improve the calculation accuracy by gradually refining the grid; in the optimization process, it is necessary to define an objective function as a criterion for measuring the pros and cons of the design scheme. Usually, a neural network model is used to construct the objective function, which can capture the nonlinear relationship in the complex design space; design variables refer to parameters that can be changed and will affect the performance of the final product. Variables are parameters that are expected to be optimized to find the best setting; constraint functions specify some restrictions that the design must meet, such as size restrictions, strength requirements, etc.; and the global optimization toolbox is a collection of various optimization algorithms that aims to find the optimal solution, including PSO particle swarm optimization (ParticleSwarm Optimization). Optimization, a heuristic search algorithm that imitates the foraging behavior of bird flocks; EGO, an optimization method based on agent models; DOE, a statistical method for planning experiments to maximize information acquisition; the direction of information flow. Starting from the design variables and constraint functions, after a series of analysis and optimization steps, the optimized objective function is finally formed.

[0087] Figure 4 The flow chart of the isogeometric fast reanalysis algorithm is introduced, and a fast optimization model for transient thermal-structural weak coupling problems and a corresponding closed-loop optimization design framework are proposed. In the actual engineering field, the mathematical model based on the structural optimization problem can usually be expressed as:

[0088] findx={x1,x2,...,x k ,...,x n}

[0089] minf(x)=[f1(x),f2(x),…,f m (x)] T

[0090]

[0091] Among them, x is the finite element submodel block, f(x) is the optimization objective function, g i (x) is the i-th equality constraint, h i (x) is the i-th inequality constraint, x k,min and x k,max are the minimum and maximum values ​​of the finite element sub-model block, respectively.

[0092] Specifically, in the above embodiment, the complexity of multiple finite element models is determined, and the analysis results of the finite element models are solved using a multi-objective evolutionary algorithm to obtain the solution of each finite element model, including first determining the complexity of the finite element model using a complexity dynamic adjustment method, wherein the finite element model includes a low-complexity model and a high-complexity model, and then establishing relevant objective functions and multiple constraints based on the multi-objective optimization problem, and based on minimizing the relevant objective functions, using a multi-objective evolutionary algorithm to solve the analysis results of the finite element model to obtain the solution of each finite element model.

[0093] In this embodiment, the multi-objective evolutionary algorithm is combined with the variable complexity method. According to the characteristics of low computational cost of low-complexity models and high precision of high-complexity models, the computational cost is reduced while ensuring the computational accuracy of high-complexity models, thereby improving the optimization efficiency. It is proposed that the multi-objective evolutionary algorithm is combined with the variable complexity method to make full use of the characteristics of low computational cost of low-complexity models and high precision of high-complexity models. While ensuring the computational accuracy of high-complexity models, we can improve the solution efficiency by reducing the computational cost. For the rapid identification of weak links in the converter valve, the innovative proposed minimization of CMOP (Constrained Multi-Objective Optimization Problem) can be expressed as follows:

[0094]

[0095] where x∈S is the w-dimensional decision vector in the search space S, f(x) represents the r-dimensional objective function, and s h (x) represents the hth constraint, e is the number of inequality constraints, t h (x) represents the hth equality constraint, and (qe) is the number of equality constraints.

[0096] Furthermore, the Pareto transfer strategy is used to optimize and iterate the solution of each finite element model to obtain the optimal parameter set, including first obtaining the solution of the low-complexity model, using the solution of the low-complexity model as the initial search population of the high-complexity model, then determining the search population during the iteration of the high-complexity model, obtaining the local search function, and updating the local search function based on the parameters of the high-complexity model and the search population to obtain the optimal parameter set.

[0097] In this embodiment, the PT (Pareto Transfer) strategy is used to select the low-complexity model solution as the initial search population of the high-complexity model, so that the high-complexity model can replace the low-complexity model for local search, reduce the optimization times of the high-complexity model, and achieve the purpose of quickly solving and identifying the weak links of the converter valve. The PT strategy can be used to select the low-complexity model solution as the initial search population of the high-complexity model to reduce the optimization times of the high-complexity model, which can not only improve the discrimination efficiency, but also further improve the accuracy.

[0098] Among them, let the low complexity model solution be X low ,

[0099]

[0100] in, is the initial search population of the high-complexity model, and the low-complexity model solution is migrated to the high-complexity model through the PT strategy. The parameters of the high-complexity model will be gradually adjusted to approach the optimal solution. Assume that the parameters of the high-complexity model are θ high ;

[0101] Local search for high complexity models:

[0102]

[0103] It means that the high-complexity model searches the population at the t+1th iteration, and the local search function uses the high-complexity model parameters and the current search population to update, thus reducing the solution time;

[0104] X opt =Optimize(X high )

[0105] Among them, X opt It represents the optimal parameter set obtained through the complete solution process, effectively improving the calculation efficiency and accuracy. Through this step, different complexity models are used to accelerate the identification of weak links in the converter valve.

[0106] Finally, a complete data-state prediction nonlinear equation fast iterative solution method is constructed to quickly and accurately find temperature anomalies and identify the weak links of the converter valve. Figure 5 It is a junction temperature distribution cloud diagram of key components of thyristor converter valves. Through a fast iterative solution method, the abnormal temperature points of the converter valves are quickly identified in the finite element simulation analysis. Tests have proved that the method provided in this application can speed up the solution speed and improve the efficiency of identifying weak links in the converter valves.

[0107] In summary, the principle and logic flow of the method for solving the weak link of the converter valve provided in this application is as follows: Figure 6 shown.

[0108] Further, as Figure 1 The specific implementation of the method, the embodiment of the present application provides a device for solving the weak link of the converter valve, such as Figure 7 As shown, the device includes: a model reduction module 201, a parallel processing module 202, an optimization iteration module 203 and a weak link solving module 204.

[0109] The model order reduction module 201 is used to identify multiple subsystems of the converter valve to be identified, establish a substructure model corresponding to each subsystem, and perform interpolation optimization on the multiple substructure models to obtain multiple reduced-order substructure models;

[0110] A parallel processing module 202 is used to distribute the multiple reduced-order substructure models to multiple processors for parallel processing, construct a finite element model and calculate the analysis result of each finite element model using an isogeometric analysis method;

[0111] The optimization iteration module 203 is used to determine the complexity of multiple finite element models, and solve the analysis results of the finite element models using a multi-objective evolutionary algorithm to obtain a solution for each finite element model, and optimize and iterate the solution of each finite element model using a Pareto transfer strategy to obtain an optimal parameter set;

[0112] The weak link solving module 204 is used to construct a nonlinear equation according to the operating data of the converter valve to be identified, solve the nonlinear equation using an optimal parameter set, identify the temperature abnormal point of the converter valve to be identified, and determine the weak link of the converter valve to be identified.

[0113] In a specific application scenario, the model reduction module 201 can be specifically used to collect experimental data of the converter valve to be identified and preprocess the experimental data; determine the target interpolation method based on the data characteristics and data requirements of the experimental data; establish an interpolation model according to the target interpolation method, and use the interpolation model to interpolate and optimize the substructure model to obtain an initial reduced-order substructure model; construct auxiliary variables, and adjust the model parameters of the initial reduced-order substructure model based on the auxiliary variables to optimize the initial reduced-order substructure model to obtain a reduced-order substructure model.

[0114] In a specific application scenario, the model reduction module 201 can also be used to obtain the electron current equation and the hole current equation of the converter valve to be identified under one-dimensional conditions; construct auxiliary variables, obtain the electron current equation and the hole current equation under different injection conditions based on the electric field distribution of the power chip in the converter valve to be identified, and then solve the electron current and the hole current at discrete points in the electron current and the hole current equation under one-dimensional conditions; determine the reduced-order substructure model based on the electron current equation and the hole current equation under one-dimensional conditions and the electron current and the hole current at discrete points.

[0115] In a specific application scenario, the parallel processing module 202 can be used to determine the complexity of each reduced-order substructure model based on the mesh division level and the computational complexity; determine the computing units of multiple processors, match the computing units of the processors with the complexity of the reduced-order substructure model, and determine the processor corresponding to each reduced-order substructure model; and use multiple processors to process multiple reduced-order substructure models in parallel.

[0116] In a specific application scenario, the parallel processing module 202 can also be used to construct a finite element model of a reduced-order substructure model based on a transient thermal-structural weak coupling problem; based on initial design parameters and initial constraints, the finite element model is analyzed using an isogeometric analysis method to obtain initial analysis results; based on the initial analysis results, the finite element model is optimized, and the optimized finite element model is re-estimated using a re-analysis algorithm to obtain analysis results corresponding to the finite element model.

[0117] In a specific application scenario, the optimization iteration module 203 can be used to determine the complexity of the finite element model using a dynamic complexity adjustment method, wherein the finite element model includes a low-complexity model and a high-complexity model; relevant objective functions and multiple constraints are established according to a multi-objective optimization problem, and based on minimizing the relevant objective functions, the analysis results of the finite element model are solved using a multi-objective evolutionary algorithm to obtain a solution for each finite element model.

[0118] In a specific application scenario, the optimization iteration module 203 can also be used to obtain the solution of a low-complexity model, and use the solution of the low-complexity model as the initial search population of a high-complexity model; determine the search population during the iteration of the high-complexity model, obtain the local search function, and update the local search function based on the parameters of the high-complexity model and the search population to obtain the optimal parameter set.

[0119] It should be noted that for other corresponding descriptions of the functional units involved in the weak link solving device for a converter valve provided in this embodiment, reference can be made to Figure 1 The corresponding description in will not be repeated here.

[0120] Based on the above Figure 1 The method shown, accordingly, this embodiment also provides a storage medium, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned method for solving the weak link of the converter valve is implemented.

[0121] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product. The software product to be identified can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the method for solving the weak links of the converter valve in each implementation scenario of the present application.

[0122] Based on the above Figure 1 The method shown, and Figure 7 In order to achieve the above-mentioned purpose, the embodiment of the converter valve weak link solving device is shown. Figure 8 As shown, this embodiment also provides a physical device for solving the weak link of the converter valve, which includes a communication bus, a processor, a memory and a communication interface, and may also include an input and output interface and a display device, wherein each functional unit can communicate with each other through the bus. The memory stores a computer program, and the processor is used to execute the program stored in the memory and execute the method for solving the weak link of the converter valve in the above embodiment.

[0123] Optionally, the physical device may also include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.

[0124] Those skilled in the art will appreciate that the structure of the physical device for solving the weak link of a converter valve provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or a combination of certain components, or different arrangements of components.

[0125] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware of the physical device and the software resources to be identified, and supports the operation of the information processing program and other software and / or programs to be identified. The network communication module is used to realize the communication between the components inside the storage medium, and the communication with other hardware and software in the information processing physical device.

[0126] Through the description of the above implementation methods, the technical personnel in this field can clearly understand that the present application can be implemented by means of software plus the necessary general hardware platform, or by hardware. By applying the technical solution of the present application, firstly, multiple subsystems of the converter valve to be identified are identified, a substructure model corresponding to each subsystem is established, and multiple substructure models are interpolated and optimized respectively to obtain multiple reduced-order substructure models, and then multiple reduced-order substructure models are distributed to multiple processors for parallel processing, a finite element model is constructed and the analysis result of each finite element model is calculated using the isogeometric analysis method, and then the complexity of multiple finite element models is determined, and the analysis results of the finite element model are solved using a multi-objective evolutionary algorithm to obtain the solution of each finite element model, and the solution of each finite element model is optimized and iterated using the Pareto transfer strategy to obtain the optimal parameter set, and finally a nonlinear equation is constructed according to the operating data of the converter valve to be identified, and the nonlinear equation is solved using the optimal parameter set, and the temperature abnormal point of the converter valve to be identified is identified to determine the weak link of the converter valve to be identified. The above method is based on establishing a substructure model for the subsystem of the converter valve, and reducing the order of the model through interpolation optimization, which greatly reduces the computational complexity and makes the simulation more efficient; using multiple processors to process multiple reduced-order substructure models in parallel can significantly accelerate the entire simulation process and improve the simulation efficiency; constructing a finite element model and combining it with the isogeometric analysis method can further improve the solution efficiency while maintaining high accuracy, and more accurately capture the complex physical field changes inside the converter valve; using a multi-objective evolutionary algorithm, it is suitable for solving problems with multiple conflicting goals, and using the Pareto transfer strategy to optimize and iterate the model solution can improve the accuracy of predicting temperature anomaly points; constructing nonlinear equations based on actual operating data, and using the optimized parameter set to solve them, can more realistically reflect the working status of the converter valve. The above method improves the speed and accuracy of identifying weak links in the converter valve, accurately locates the temperature anomaly area, and provides clear fault diagnosis information for maintenance personnel.

[0127] Those skilled in the art will appreciate that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily necessary for implementing the present application. Those skilled in the art will appreciate that the modules in the devices in the implementation scenario can be distributed in the devices of the implementation scenario according to the description of the implementation scenario, or can be changed accordingly and located in one or more devices different from the present implementation scenario. The modules of the above-mentioned implementation scenario can be combined into one module, or can be further split into multiple submodules.

[0128] The above serial numbers of this application are only for description and do not represent the advantages and disadvantages of the implementation scenarios. The above disclosure is only a few specific implementation scenarios of this application, but this application is not limited to them, and any changes that can be thought of by technicians in this field should fall within the scope of protection of this application.

Claims

1. A method for solving weak links of a converter valve, characterized in that: include: Identify multiple subsystems of the converter valve to be identified, establish a substructure model corresponding to each of the subsystems, and perform interpolation optimization on the multiple substructure models to obtain multiple reduced-order substructure models; Distributing the plurality of reduced-order substructure models to a plurality of processors for parallel processing, constructing a finite element model and calculating the analysis result of each finite element model using an isogeometric analysis method; Determine the complexity of the multiple finite element models, and use a multi-objective evolutionary algorithm to solve the analysis results of the finite element models to obtain a solution of each finite element model, and use a Pareto transfer strategy to iterate the solution of each finite element model to obtain an optimal parameter set; A nonlinear equation is constructed according to the operation data of the converter valve to be identified, the nonlinear equation is solved using the optimal parameter set, and the temperature abnormal point of the converter valve to be identified is identified to determine the weak link of the converter valve to be identified.

2. The method according to claim 1, characterized in that The interpolation optimization is performed on the plurality of substructure models respectively to obtain a plurality of reduced-order substructure models, including: Collecting experimental data of the converter valve to be identified and preprocessing the experimental data; Determining a target interpolation method based on data characteristics and data requirements of the experimental data; An interpolation model is established according to the target interpolation method, and the substructure model is interpolated and optimized using the interpolation model to obtain an initial reduced-order substructure model; Auxiliary variables are constructed, and model parameters of the initial reduced-order substructure model are adjusted based on the auxiliary variables to optimize the initial reduced-order substructure model to obtain a reduced-order substructure model.

3. The method according to claim 2, characterized in that The constructing of auxiliary variables, and adjusting the model parameters of the initial reduced-order substructure model based on the auxiliary variables to optimize the initial reduced-order substructure model to obtain the reduced-order substructure model, includes: Obtaining the electron current equation and the hole current equation of the converter valve to be identified under one-dimensional conditions; Construct auxiliary variables, obtain the electron current equation and hole current equation under different injection conditions based on the electric field distribution of the power chip in the converter valve to be identified, and then solve the electron current and hole current at discrete points in the electron current and hole current equation under one-dimensional conditions; The reduced-order substructure model is determined according to the electron current equation and the hole current equation under the one-dimensional condition and the electron current and the hole current at the discrete points.

4. The method according to claim 1, characterized in that: The step of distributing the plurality of reduced-order substructure models to a plurality of processors for parallel processing comprises: Determining the complexity of each of the reduced-order substructure models based on the meshing level and computational complexity; Determine computing units of a plurality of processors, match the computing units of the processors with the complexity of the reduced-order substructure model, and determine a processor corresponding to each of the reduced-order substructure models; The plurality of processors are used to process the plurality of reduced-order substructure models in parallel.

5. The method according to claim 1, characterized in that The step of constructing a finite element model and calculating the analysis results of each finite element model using an isogeometric analysis method includes: Constructing a finite element model of the reduced-order substructure model according to a transient thermal-structural weak coupling problem; Based on the initial design parameters and initial constraint conditions, the finite element model is analyzed using an isogeometric analysis method to obtain an initial analysis result; The finite element model is optimized based on the initial analysis result, and the optimized finite element model is re-estimated using a re-analysis algorithm to obtain an analysis result corresponding to the finite element model.

6. The method according to claim 1, characterized in that The determining the complexity of the plurality of finite element models and solving the analysis results of the finite element models using a multi-objective evolutionary algorithm to obtain a solution for each of the finite element models includes: Determining the complexity of the finite element model using a complexity dynamic adjustment method, wherein the finite element model includes a low complexity model and a high complexity model; According to the multi-objective optimization problem, relevant objective functions and multiple constraints are established. Based on minimizing the relevant objective functions, the multi-objective evolutionary algorithm is used to solve the analysis results of the finite element model to obtain the solution of each of the finite element models.

7. The method according to claim 6, characterized in that The Pareto transfer strategy is used to iterate the optimization of each solution of the finite element model to obtain an optimal parameter set, including: Obtaining a solution to the low-complexity model, and using the solution to the low-complexity model as an initial search population for the high-complexity model; The search population during iteration of the high-complexity model is determined, a local search function is obtained, and the local search function is updated based on the parameters of the high-complexity model and the search population to obtain an optimal parameter set.

8. A device for solving weak links of a converter valve, characterized in that: The device comprises: A model reduction module, used for identifying multiple subsystems of the converter valve to be identified, establishing a substructure model corresponding to each of the subsystems, and performing interpolation optimization on the multiple substructure models to obtain multiple reduced-order substructure models; A parallel processing module, used for distributing the plurality of reduced-order substructure models to a plurality of processors for parallel processing, constructing a finite element model and calculating the analysis result of each finite element model by using an isogeometric analysis method; An optimization iteration module, used to determine the complexity of the multiple finite element models, and solve the analysis results of the finite element models using a multi-objective evolutionary algorithm to obtain a solution of each finite element model, and optimize and iterate the solution of each finite element model using a Pareto transfer strategy to obtain an optimal parameter set; The weak link solving module is used to construct a nonlinear equation according to the operating data of the converter valve to be identified, solve the nonlinear equation using the optimal parameter set, identify the temperature abnormal point of the converter valve to be identified to determine the weak link of the converter valve to be identified.

9. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images