Data-driven multi-objective optimization method for environment-friendly gas arc-extinguishing system, and related device

Abstract

Disclosed in the present invention are a data-driven multi-objective optimization method for an environment-friendly gas arc-extinguishing system, and a related device. The method comprises: firstly, inputting collected key design variables of an environment-friendly gas arc-extinguishing system into a parametric circuit breaker cold-state simulation model for simulation, so as to output objective function values; using the key design variables and the corresponding objective function values to construct and train a data-driven model, so as to predict and evaluate a design space; and finally, combining the data-driven model with an optimization objective function for representing the breaking capability of a circuit breaker, and using a multi-objective genetic algorithm to output optimal design variables, so as to realize the optimization of the environment-friendly gas arc-extinguishing system. The method solves the problems of reliability and efficiency in traditional designs on the basis of multi-objective collaborative optimization and a data-driven model, and makes minor modifications to the structure of a circuit breaker to significantly improve the breaking performance of the circuit breaker, thereby improving the reliability and efficiency of circuit breaker design processes.

Description

Data-driven environmentally friendly gas arc-extinguishing system multi-objective optimization method and related equipment TECHNICAL FIELD

[0001] The present application belongs to the technical field of high-voltage circuit breakers, and particularly relates to a data-driven environmentally friendly gas arc-extinguishing system multi-objective optimization method and related equipment. BACKGROUND

[0002] High-voltage gas circuit breakers are important devices for control and protection of power systems. To ensure safe and reliable operation of the power grid, circuit breakers must have the ability to switch capacitive and inductive loads and effectively interrupt the rated short-circuit current, especially in the event of short-circuit faults and circuit breaker terminal faults. During current interruption, high-temperature arcs are generated between the electrodes as the moving and stationary arc contacts separate. Gas circuit breakers typically use the strong blowing effect of high-pressure gas in the nozzle upstream chamber to achieve arc cooling and extinguishing. Due to the complex structure of gas circuit breakers, the gas flow in the circuit breaker exhibits instability due to the influence of the variable flow path formed by the contacts, nozzles, and other structural components. Different nozzle and chamber structures and sizes result in different gas flow fields after contact separation. At the same time, changes in nozzle structure, under the influence of transient recovery voltage, change the electric field distribution between the contacts, thereby affecting the dielectric recovery strength. In addition, during high-current interruption, the dynamic distribution of temperature and gas density caused by hot gas must also be considered. Therefore, temperature, pressure, density, dielectric strength, and other gas properties collectively affect the breaking performance. These properties can conflict, and improving only one factor will not meet the current design requirements of circuit breakers.

[0003] The existing circuit breaker design method relies on experience for a large number of parameter adjustments and manual testing of key components such as nozzles, with poor reliability and relatively low efficiency. The previous optimization target focuses on traditional SF6 gas circuit breakers, and after replacing the gas medium, there will be a problem that the optimization method is not applicable. As a strong greenhouse gas with a global warming potential (GWP) of 35,000 times that of CO2, the use of SF6 is subject to increasingly stringent restrictions. In recent years, C4F7N has become the most promising SF6 replacement gas, with a GWP value of only 2210 and a dielectric strength about twice that of SF6. Traditional methods such as increasing the filling pressure and reducing the capacity are not sufficient to fully exploit the potential of C4F7N in circuit breaker interruption applications. TECHNICAL PROBLEM

[0004] The existing circuit breaker design method relies on experience for a large number of parameter adjustments and manual testing of key components such as nozzles, with poor reliability and relatively low efficiency. TECHNICAL SOLUTION

[0005] The application provides a data-driven environmentally-friendly gas arc-extinguishing system multi-objective optimization method and related equipment to solve the technical problems of poor reliability and relatively low efficiency caused by the fact that the existing circuit breaker design method only relies on experience to make a large number of parameter adjustments and manual tests on key components such as nozzles.

[0006] In order to achieve the above-mentioned purpose, the technical scheme of the application is as follows:

[0007] A data-driven environmentally-friendly gas arc-extinguishing system multi-objective optimization method comprises the following steps:

[0008] S1: Collecting key design variables of an environmentally-friendly gas arc-extinguishing system, inputting the key design variables into a pre-constructed parameterized circuit breaker cold-state simulation model, and outputting target function values;

[0009] S2: Constructing and training a data-driven model based on the key design variables and corresponding target function values to predict and evaluate a design space;

[0010] S3: Combining the trained data-driven model and a pre-constructed optimization target function, using a multi-objective genetic algorithm, and outputting optimal design variables to realize optimization of the environmentally-friendly gas arc-extinguishing system; wherein the optimization target function is used to represent the breaking capacity of the circuit breaker.

[0011] Further, in S1, the Morris method is used to perform sensitivity analysis on the collected key design variables, and the key design variables are divided into insensitive variables and highly sensitive variables;

[0012] The insensitive variables are kept at initial data, and the highly sensitive variables are randomly generated with a Latin hypercube sampling method to generate a plurality of sample points;

[0013] All sample points generated by the highly sensitive variables are input into the pre-constructed parameterized circuit breaker cold-state simulation model, and target function values are output.

[0014] Further, the Morris method is used to perform sensitivity analysis on the collected key design variables, wherein the average value and the standard deviation of the corresponding trajectory basic effect EE are used as a global sensitivity index to identify design variables that have a significant impact on breaking performance; the formula expressions of the average value and the standard deviation are as follows:

[0015]

[0016]

[0017] wherein, is a k-dimensional independent input, for outputting a response, for one of the values, is the number of layers; i is the i-th key design variable; r is the number of tracks.

[0018] Further, in S1, the parameterized circuit breaker cold-state simulation model is constructed as follows:

[0019] A two-dimensional model of the circuit breaker is drawn according to the initial structure of the circuit breaker, and meshing is performed, the key design variables are set as variable parameters to construct a parameterized circuit breaker geometric model, and automatic modeling of the geometric structure of the parameterized circuit breaker geometric model and autonomous updating of the mesh are realized;

[0020] The complete property parameter data of the environmental protection gas is array encoded, and a real gas model is built by combining a linear interpolation algorithm; a standard k-ε turbulent flow model is used to solve the exchange relationship between the momentum and energy of the gas medium under the action of the internal turbulent flow of the circuit breaker;

[0021] The parameterized circuit breaker geometric model, the real gas model and the turbulent flow model are coupled to construct a parameterized circuit breaker cold-state simulation model.

[0022] Further, in S2, a data set is established with the key design variables as input and the target function value as output, and a data-driven model is constructed using a support vector regression method, wherein the correlation coefficient R 2 is used as an index of the accuracy of the data-driven model:

[0023]

[0024] wherein N is the sample size, is the predicted value, is the actual value, is the average value of the actual value.

[0025] Further, in S3, the optimized design variables and the optimized target function value are output based on the trained data-driven model, the pre-constructed optimization target function is combined, the trade-off between multiple optimization targets is realized through the Pareto boundary, and the optimal design variables are output;

[0026] The optimization targets of the optimization target function include minimizing the ratio of the electric field strength and the density and maximizing the average pressure in the plenum, and are specifically expressed as:

[0027]

[0028] wherein Ω is the design space, g(X) represents the optimized plenum volume V Opt , and V BaseX is a key design variable;

[0029] ;

[0030] ;

[0031] represents the ratio of electric field intensity to gas density; represents the average pressure in the plenum.

[0032] Further comprising:

[0033] S4: generating an optimized circuit breaker simulation model based on the optimal design variable, and performing real CFD simulation verification on the optimized circuit breaker simulation model.

[0034] A data-driven environmentally friendly gas arc-extinguishing system multi-objective optimization system for realizing the steps of the data-driven environmentally friendly gas arc-extinguishing system multi-objective optimization method, comprising:

[0035] A simulation module for collecting key design variables of the environmentally friendly gas arc-extinguishing system, inputting the key design variables into a pre-constructed parameterized circuit breaker cold-state simulation model, and outputting target function values;

[0036] A data-driven model construction module for constructing and training a data-driven model based on the key design variables and corresponding target function values to predict and evaluate the design space;

[0037] An optimal design variable output module for combining the trained data-driven model and the pre-constructed optimization target function, using a multi-objective genetic algorithm, and outputting optimal design variables to realize optimization of the environmentally friendly gas arc-extinguishing system; wherein the optimization target function is used to represent the breaking capacity of the circuit breaker.

[0038] An apparatus comprising:

[0039] A memory for storing a computer program;

[0040] A processor for executing the computer program to realize the steps of the data-driven environmentally friendly gas arc-extinguishing system multi-objective optimization method.

[0041] A computer-readable storage medium storing a computer program, the computer program being executed by a processor to realize the steps of the data-driven environmentally friendly gas arc-extinguishing system multi-objective optimization method. Advantages

[0042] The application also provides a data-driven multi-objective optimization method for an environmentally friendly gas arc-extinguishing system, which comprises the following steps: inputting key design variables of the environmentally friendly gas arc-extinguishing system collected into a parameterized circuit breaker cold-state simulation model for simulation, so as to output a target function value; constructing and training a data-driven model by using the key design variables and the corresponding target function value to predict and evaluate a design space; and finally combining the data-driven model with an optimization target function for representing breaking capacity of the circuit breaker, and outputting optimal design variables by using a multi-objective genetic algorithm, so as to realize optimization of the environmentally friendly gas arc-extinguishing system.

[0043] Preferably, in the application, the Morris method is introduced to perform sensitivity analysis on the key design variables, the design variables are divided into insensitive variables and highly sensitive variables, and only the highly sensitive variables are sampled and simulated; this method reduces unnecessary calculation amount, improves simulation efficiency, and ensures accuracy of the optimization result.

[0044] Further preferably, in the application, the average value and the standard deviation of the basic effect are calculated as a global sensitivity index, which can more accurately identify the design variables that have a significant impact on the breaking performance, provides an important basis for subsequent optimization work, and helps to further improve the optimization effect.

[0045] Preferably, in the application, the construction steps of the parameterized circuit breaker cold-state simulation model comprise parameterization of a geometric model, establishment of a real gas model, and solution of a turbulent flow model, which can more accurately simulate the actual working state of the circuit breaker, and provides a reliable basis for subsequent simulation and optimization.

[0046] Preferably, in the application, the support vector regression method is used to construct the data-driven model, and the accuracy of the model is evaluated by using a correlation coefficient, which can efficiently process a large amount of data and construct a high-precision prediction model, and provides strong support for subsequent optimization work.

[0047] Preferably, in the application, the trade-off between multiple optimization objectives is realized by using a Pareto boundary, that is, the optimal design variables are output by iterative calculation of the multi-objective genetic algorithm, which can comprehensively consider multiple optimization objectives, find an optimal compromise solution, and thus meet the overall performance requirements of the system.

[0048] Preferably, in the present application, at the end of the optimization process, the optimized circuit breaker simulation model is generated based on the optimal design variables, and the real CFD simulation verification is carried out, so as to ensure the reliability and practicability of the optimization result, and provide strong support for actual production. BRIEF DESCRIPTION OF DRAWINGS

[0049] Fig. 1 is a schematic diagram of a parameterized circuit breaker cold-state simulation model provided by an embodiment of the present application;

[0050] Fig. 2 is a Max (E / ρ) and P̅ time distribution diagram of SF6 and C4F7N mixed gas provided by an embodiment of the present application; wherein (a) is SF6; (b) is C4F7N mixed gas.

[0051] Fig. 3 is a Morris sensitivity index µ, µ* and σ relative to output Max (E / ρ) and P̅ provided by an embodiment of the present application; wherein (a) is SF6; (b) is C4F7N mixed gas; wherein, in (a), the left one and the left two are Max (E / ρ) corresponding to SF6; the right one and the right two are P̅ corresponding to SF6; in (b), the left one and the left two are Max (E / ρ) corresponding to C4F7N mixed gas; the right one and the right two are P̅ corresponding to C4F7N mixed gas.

[0052] Fig. 4 is a target function prediction accuracy diagram of SF6 provided by an embodiment of the present application; wherein (a) and (b) are random forest prediction accuracy diagrams; (c) and (d) are SVR data-driven model prediction accuracy diagrams.

[0053] Fig. 5 is a convergence process diagram of Pareto front generated by the optimization process of SF6 and C4F7N gas provided by an embodiment of the present application; wherein (a) is SF6; (b) is C4F7N mixed gas.

[0054] Fig. 6 is a simulation result comparison diagram of the optimization design and the basic design of SF6 and C4F7N gas provided by an embodiment of the present application; wherein (a) is SF6; (b) is C4F7N mixed gas.

[0055] Fig. 7 is a flowchart of a data-driven environmentally friendly gas arc-extinguishing system multi-objective optimization method provided by an embodiment of the present application;

[0056] Fig. 8 is a flowchart of a data-driven environmentally friendly gas arc-extinguishing system multi-objective optimization method provided by the present application;

[0057] Fig. 9 is a structural schematic diagram of a data-driven environmentally friendly gas arc-extinguishing system multi-objective optimization system provided by the present application. Embodiments of the present application

[0058] This invention provides a data-driven multi-objective optimization method for an environmentally friendly gas arc extinguishing system, as shown in Figure 8, comprising the following steps:

[0059] S1: Collect key design variables of the environmentally friendly gas arc extinguishing system, input the key design variables into the pre-built parameterized circuit breaker cold simulation model, and output the objective function value; specifically, use the Morris method to perform sensitivity analysis on the collected key design variables, and divide the key design variables into insensitive variables and highly sensitive variables.

[0060] Keep insensitive variables in the initial data, and randomly generate multiple sample points for highly sensitive variables using the Latin hypercube sampling method;

[0061] All sample points generated by the highly sensitive variables are input into the pre-built parameterized circuit breaker cold simulation model, and the objective function value is output.

[0062] Here, the Morris method is used to perform sensitivity analysis on the key design variables collected, where the average value of the basic effect EE of the corresponding trajectory is used. and standard deviation As a global sensitivity index, it identifies design variables that significantly affect breaking performance; average value and standard deviation The formula is expressed as follows:

[0063]

[0064]

[0065] in, Given k-dimensional independent inputs, To output the response, for One of the values, denoted as the layer number; i represents the i-th key design variable; and r represents the number of trajectories.

[0066] The steps for constructing the cold-state simulation model of the parametric circuit breaker are as follows:

[0067] A two-dimensional model of the circuit breaker is drawn based on the initial structure of the circuit breaker and meshed. Key design variables are set as variable parameters to construct a parametric circuit breaker geometric model, thereby realizing automatic geometric modeling of the parametric circuit breaker geometric model and autonomous mesh updating.

[0068] The complete physical property parameters of the environmentally friendly gas are arrayed and combined with a linear interpolation algorithm to build a real gas model; the exchange relationship between momentum and energy of the gas medium under the action of turbulence inside the circuit breaker is solved using the standard k-ε turbulence model.

[0069] The parameterized circuit breaker geometric model, the real gas model and the turbulence model are coupled to obtain a cold state simulation model of the parameterized circuit breaker.

[0070] S2: A data-driven model is constructed and trained based on the key design variables and the corresponding target function values to predict and evaluate the design space.

[0071] In S2, a data set is established with the key design variables as input and the target function values as output, and a support vector regression method is used to construct the data-driven model, wherein the correlation coefficient R 2 As an index of the accuracy of the data-driven model:

[0072]

[0073] Wherein N is the sample size, is the predicted value, is the actual value, is the average value of the actual value.

[0074] S3: The trained data-driven model and the pre-constructed optimization objective function are combined, and a multi-objective genetic algorithm is used to output the optimal design variable to realize the optimization of the environmentally friendly gas arc-extinguishing system; wherein the optimization objective function is used to represent the breaking capacity of the circuit breaker.

[0075] In S3, the optimized design variable and the optimization objective function value are output based on the trained data-driven model, and the pre-constructed optimization objective function is combined to realize the trade-off between multiple optimization objectives through the Pareto boundary, and the optimal design variable is output;

[0076] Wherein, the optimization objectives of the optimization objective function include minimizing the ratio of electric field intensity and density and maximizing the average pressure in the plenum, which are specifically represented as:

[0077]

[0078] Wherein, Ω is the design space, g(X) represents the optimized plenum volume V Opt , which is not greater than the reference design V Base ; X is the key design variable;

[0079] ;

[0080] ;

[0081] represents the ratio of electric field intensity and gas density; represents the average pressure in the plenum.

[0082] S4: generating an optimized circuit breaker simulation model based on the optimal design variables, and performing real CFD simulation verification on the optimized circuit breaker simulation model.

[0083] As shown in FIG. 9, the application further provides a data-driven multi-objective optimization system of an environmentally-friendly gas arc-extinguishing system, comprising: a simulation module, configured to collect key design variables of the environmentally-friendly gas arc-extinguishing system, input the key design variables into a pre-constructed parameterized cold-state simulation model of a circuit breaker, and output a target function value; a data-driven model construction module, configured to construct and train a data-driven model based on the key design variables and the corresponding target function value to predict and evaluate a design space; and an optimal design variable output module, configured to combine the trained data-driven model and a pre-constructed optimization target function, output optimal design variables by using a multi-objective genetic algorithm, and realize optimization of the environmentally-friendly gas arc-extinguishing system; wherein the optimization target function is used to represent breaking capacity of the circuit breaker.

[0084] The application further provides a device, comprising: a memory configured to store a computer program; and a processor configured to implement the steps of the data-driven multi-objective optimization method of the environmentally-friendly gas arc-extinguishing system when executing the computer program.

[0085] The processor implements the steps of the data-driven multi-objective optimization method of the environmentally-friendly gas arc-extinguishing system when executing the computer program, for example: collecting key design variables of the environmentally-friendly gas arc-extinguishing system, inputting the key design variables into a pre-constructed parameterized cold-state simulation model of a circuit breaker, and outputting a target function value; constructing and training a data-driven model based on the key design variables and the corresponding target function value to predict and evaluate a design space; combining the trained data-driven model and a pre-constructed optimization target function, outputting optimal design variables by using a multi-objective genetic algorithm, and realizing optimization of the environmentally-friendly gas arc-extinguishing system; wherein the optimization target function is used to represent breaking capacity of the circuit breaker.

[0086] Alternatively, the processor implements the functions of the modules in the system when executing the computer program, for example: a simulation module, configured to collect key design variables of the environmentally-friendly gas arc-extinguishing system, input the key design variables into a pre-constructed parameterized cold-state simulation model of a circuit breaker, and output a target function value; a data-driven model construction module, configured to construct and train a data-driven model based on the key design variables and the corresponding target function value to predict and evaluate a design space; and an optimal design variable output module, configured to combine the trained data-driven model and a pre-constructed optimization target function, output optimal design variables by using a multi-objective genetic algorithm, and realize optimization of the environmentally-friendly gas arc-extinguishing system; wherein the optimization target function is used to represent breaking capacity of the circuit breaker.

[0087] Exemplarily, the computer program can be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present application. The one or more modules / units can be a series of computer program instruction segments capable of completing preset functions, which are used to describe the execution process of the computer program in the data-driven environmentally friendly gas arc-extinguishing system multi-objective optimization device. For example, the computer program can be divided into a simulation module, a data-driven model construction module, and an optimal design variable output module; the specific functions of each module are as follows: the simulation module is used to collect key design variables of the environmentally friendly gas arc-extinguishing system, input the key design variables into a pre-constructed parameterized circuit breaker cold-state simulation model, and output a target function value; the data-driven model construction module is used to construct and train a data-driven model based on the key design variables and the corresponding target function value to predict and evaluate the design space; the optimal design variable output module is used to combine the trained data-driven model and the pre-constructed optimization target function, adopt a multi-objective genetic algorithm, and output optimal design variables to realize optimization of the environmentally friendly gas arc-extinguishing system; wherein, the optimization target function is used to represent the breaking capacity of the circuit breaker.

[0088] The data-driven environmentally friendly gas arc-extinguishing system multi-objective optimization device can be a desktop computer, a notebook, a palm computer, and a cloud server, etc. The data-driven environmentally friendly gas arc-extinguishing system multi-objective optimization device can include, but is not limited to, a processor, a memory. Those skilled in the art can understand that the above is an example of the data-driven environmentally friendly gas arc-extinguishing system multi-objective optimization device, and does not constitute a limitation on the data-driven environmentally friendly gas arc-extinguishing system multi-objective optimization device, which can include more components than the above, or combine certain components, or different components, for example, the data-driven environmentally friendly gas arc-extinguishing system multi-objective optimization device can also include an input / output device, a network access device, a bus, etc.

[0089] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor or the like, which is a control center of the data-driven environmentally-friendly gas arc-extinguishing system multi-objective optimization, and is connected to various parts of the data-driven environmentally-friendly gas arc-extinguishing system multi-objective optimization device through various interfaces and lines.

[0090] The memory can be used to store the computer programs and / or modules, and the processor realizes various functions of the data-driven environmentally-friendly gas arc-extinguishing system multi-objective optimization device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory.

[0091] The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), etc.; and the data storage area can store data created according to use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, for example, a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory devices.

[0092] The application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the steps of the data-driven environmentally-friendly gas arc-extinguishing system multi-objective optimization method.

[0093] If the modules / units of the data-driven environmentally-friendly gas arc-extinguishing system multi-objective optimization system are realized in the form of software function units and sold or used as independent products, the modules / units can be stored in a computer readable storage medium.

[0094] Based on such understanding, all or part of the processes in the above-mentioned data-driven environmentally-friendly gas arc-extinguishing system multi-objective optimization method can be implemented by a computer program instructing relevant hardware, the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned data-driven environmentally-friendly gas arc-extinguishing system multi-objective optimization method when executed by a processor. The computer program includes computer program codes, which can be in the form of source codes, object codes, executable files or preset intermediate forms, etc.

[0095] The computer-readable storage medium can include any entity or device, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. that can carry the computer program codes.

[0096] It should be noted that the contents contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction, for example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0097] The present application will be further described below in conjunction with the embodiments and the accompanying drawings:

[0098] Example 1

[0099] As described in the background, there are reliability and efficiency problems in the traditional optimization method; and the traditional methods of increasing the filling pressure and reducing the capacity are not sufficient to fully exploit the potential of C4F7N in the application of circuit breaker interruption; therefore, it is necessary to propose an efficient and reliable multi-objective optimization design method for new environmentally-friendly gas circuit breakers to support the equipment research and development and engineering application of high-performance high-voltage environmentally-friendly gas switch.

[0100] In order to solve the above-mentioned problems, the present application provides a data-driven environmentally-friendly gas arc-extinguishing system multi-objective optimization method, which first determines two circuit breaker optimization objective functions, and uses the Morris method to quickly screen the design variables for facilitating dimension reduction of the design space; secondly, a parameterized GCB geometric model is established, and after reasonable sampling of the design variables, real CFD simulation is performed; then, a precise data-driven model is constructed to predict and evaluate the design space; finally, according to the response values of the data-driven model and the multi-objective genetic algorithm, the multi-objective optimal GCB geometric shape is searched; the CFD evaluation of the optimization result confirms the effectiveness of the design framework.

[0101] As shown in FIG. 7, the embodiment provides a data-driven environmentally friendly gas arc-extinguishing system multi-objective optimization method, specifically comprising:

[0102] Step 1: Propose multiple optimization objective functions that can represent the breaking performance of the circuit breaker: that is, propose two optimization objective functions, one of which is to reduce the ratio of electric field strength to gas density, which can improve the breakdown voltage, that is, improve the ability of the circuit breaker to break capacitive current; the second is to increase the average gas pressure in the pressure chamber, which can form a strong gas blowing effect at the current zero moment to accelerate the recovery of gas medium strength and improve the ability of the circuit breaker to break large short-circuit current, specifically:

[0103] (1) When breaking smaller capacitive short-circuit current, the arc effect has less impact on gas flow. The circuit breaker needs to have good electrical breaking capacity and withstand a recovery voltage of up to twice the rated voltage on both sides without medium breakdown. The interaction of gas flow density and electric stress in the nozzle area determines the dielectric breakdown of the gas circuit breaker when breaking capacitive current. According to the empirical formula, the critical breakdown voltage is usually a function of the ratio of electric field strength E to gas density p ( ):

[0104]

[0105] Where a and b are experimental coefficients.

[0106] Therefore, one of the optimization objectives is to improve the ability of the circuit breaker to break capacitive current, that is, to improve the breakdown voltage and reduce . The optimization objective function expression is:

[0107]

[0108] (2) When breaking large capacitive short-circuit current of up to tens of kA, the circuit breaker needs to have good thermal breaking capacity and be able to withstand the rapid rise of transient recovery voltage between contacts without arc reignition. Therefore, strong gas cooling effect is needed to reduce medium conductivity and minimize post-arc current. The gas cooling effect depends on the pressure upstream of the arc area or the pressure ratio between the upstream and downstream areas. The higher the pressure in the gas chamber, the faster the convective cooling gas flow rate and the faster the medium heat dissipation, thereby improving the interrupting capacity of the circuit breaker. The second optimization objective function is determined as:

[0109]

[0110] Step 2: Determine the key design variables of the circuit breaker and their value range, and sort and select the design variables based on sensitivity analysis;

[0111] (1) According to the actual structure of the circuit breaker and the previous optimization design experience, the key design variables of the circuit breaker are determined, including the length, radius and volume of the nozzle upstream and downstream, etc. At the same time, the variable reference value and value range are determined considering the typical circuit breaker structure basis and the actual production allowed range.

[0112] (2) Through sensitivity analysis, the uncertainty in the model output can be qualitatively attributed to the model input, so as to identify the design variables with less impact on the output and determine the interaction effect of each input variable of the model. The global sensitivity analysis is realized by taking the average value of the corresponding trajectory elementary effect (Elementary Effects, EE) And the standard deviation As the global sensitivity index, and the sensitivity of the design variables is sorted.

[0113]

[0114] Among them, is the k-dimensional independent input of the model, is the output response, is one value in , and is the number of layers.

[0115] The input parameters are randomly sampled at p levels in the k-dimensional unit hypercube. At the random starting point, the operation is repeated for each input, called trajectory, and then the corresponding EE can be calculated. For the r trajectories constructed, the sensitivity index can be derived:

[0116]

[0117]

[0118] In the above formula, the arithmetic mean and absolute mean of the EE of the ith variable are represented as And . The greater the value, the stronger the sensitivity of the variable. σ i is the standard deviation of EE, which is used to measure the nonlinearity and / or interaction effect of the ith variable. If σ i is large, it is considered to have a nonlinearity effect or interact with at least one other variable; the Morris method involves fewer model executions and can provide qualitative sensitivity results.

[0119] Step 3: Based on the initial structure of the circuit breaker, the parameterized cold-state simulation model of the circuit breaker is constructed considering the key design variables;

[0120] (1) According to the initial structure of the circuit breaker, a two-dimensional model of the circuit breaker is drawn and meshed using ANSYS modeling tools, the key design variables are set as variable parameters, a parameterized circuit breaker geometric model is constructed, and automatic modeling of the geometric structure and self-updating of the mesh are realized; the model structure can be dynamically modified and the regional mesh can be automatically updated according to the value range of the design variables.

[0121] (2) A real gas model is built, the complete physical property parameter data of the environmental gas are array coded and combined with the linear interpolation algorithm, the gas physical property parameter data (including the density p, enthalpy h, sound speed c, viscosity coefficient m, thermal conductivity l, electrical conductivity s and constant-pressure specific heat Cp of the gas) under different temperatures and pressures are introduced into the control equation set for calculation and solving. The standard k-ε turbulence model is used to solve the exchange relationship between the momentum and energy of the gas medium under the action of the internal turbulence of the circuit breaker.

[0122] (3) The above parameterized circuit breaker geometric model is coupled with the real gas model and the turbulence model, and a corresponding circuit breaker magnetohydrodynamic cold-state simulation model is constructed.

[0123] Step 4: effectively sample the design variables and perform real CFD simulation to obtain the corresponding relationship between the objective function and the design variables;

[0124] (1) Based on the design variable sensitivity ranking in step 2, the insensitive variables are kept at the base value, and the highly sensitive variables are generated into 100 uniform design variable sample sets through Latin hypercube experimental design, and the model sample set corresponding to the design variable sample is generated based on the parameterized model.

[0125] (2) For all sampling points, real CFD simulation is performed using computational fluid dynamics solving software, i.e. input into the parameterized circuit breaker cold-state simulation model for simulation; the dynamic distribution characteristics of the pressure field, airflow field, electromagnetic field, etc. in the high-voltage circuit breaker arc-extinguishing chamber are obtained. And extract the corresponding relationship between the objective function and the design variables.

[0126] Step 5: Use the design variable values and objective function values at the sampling points as training data to build a data-driven model to predict and evaluate the design space;

[0127] Based on the real simulation results obtained in step 4, a data set is established with the design variable values as the input and the objective function values as the output. The data set is randomly divided into training data and test data in the ratio of 80:20. To solve the challenge of small sample data fitting, the support vector regression (SVR) method is used to build a data-driven model, which maps the input space to a high-dimensional feature space, and realizes low-dimensional nonlinear regression prediction by determining the optimal hyperplane.

[0128] The design variables are input, normalized by the min-max method, and the two objective functions are output. The optimal hyperparameters of the data-driven model are determined based on the Bayesian optimization principle. In addition, the k-fold (k=5) cross-validation (CV) method is used to ensure that the model has good generalization ability and avoids overfitting. The correlation coefficient (R 2 ) is used as an indicator of the accuracy of the data-driven model. The closer to 1, the higher the prediction accuracy of the model. 2

[0129]

[0130] where N is the sample size, is the predicted value, is the actual value, is the average value of the actual value.

[0131] Step 6: Combine the response values of the data-driven model with the multi-objective genetic algorithm to determine the optimal design variables of the circuit breaker;

[0132] The data-driven model established in step 5 outputs a large amount of corresponding data of optimization design variables and optimization objective function values. Through the Pareto boundary, the trade-off between multiple optimization objectives is realized, and the optimal design variable scheme is selected. The optimization objective of the present application is to minimize the ratio of electric field strength and density, while maximizing the average pressure in the plenum, which is represented as:

[0133]

[0134] where Ω is the design space, g(X) represents the optimized plenum volume V Opt is not greater than the baseline design V Base .

[0135] Step 7: Based on the optimal design variables, the reliability of the true CFD simulation results of the circuit breaker structure model is verified.

[0136] Based on the optimal design variable values obtained from the multi-objective optimization model, an optimized circuit breaker simulation model is generated, and a true CFD simulation is carried out. The values of the optimization objective functions obtained from the simulation are observed to see if they correspond to the values calculated by the data-driven model, and the reliability of the results is verified.

[0137] Example 2

[0138] In this embodiment, the data-driven multi-objective optimization method for the environmentally friendly gas arc-extinguishing system provided in embodiment 1 is implemented and applied in combination with specific examples, as follows:

[0139] ​Based on the structure of a certain air-operated circuit breaker, a parametric geometric model as shown in Figure 1 was established and meshed using ANSYS Workbench software. Combining design experience and actual engineering requirements, the design variables affecting airflow and electric field distribution were determined to include the upstream profile of the nozzle (radius X4, length X2, inclination X3), the downstream profile (radius X5, lengths X6 and X7, inclination X1), and the compressor cylinder volume (length X8, height X9). The value ranges of each variable are listed in Table 1.

[0140] Table 1 shows the value range of key design variables.

[0141]

[0142] First, based on the basic structure of the circuit breaker, a realistic gas model of a mixture of SF6 and C4F7N gases was introduced to conduct realistic CFD cold-state simulations, thereby understanding and optimizing the physical processes related to the target. Figure 2 shows the arc-extinguishing chamber containing the SF6 and C4F7N gas mixture after the moving and stationary contacts separate. The variation of maximum and average pressure within the compressor chamber. The C4F7N mixture exhibits significant pressure oscillations, primarily due to the higher sound velocity of the main component, CO2, which favors rapid flow. This causes the pressure to increase rapidly to higher levels, followed by a faster decay compared to SF6.

[0143] Then, the Morris method based on randomized OAT (one variable at a time) experiments was used to conduct sensitivity analysis on the circuit breaker design variables under different gas conditions. The average values ​​of the corresponding basic effects (EE) for different design variables for the two gases are shown. µ* and standard deviation As shown in Figure 3, analysis of Figure 3 reveals that, within the SF6 gas range, design variables X7 and X8 are both located in the lower left corner of the scatter plot for Target 1, meaning they have a significant impact on (…). ) max The impact of X8 on the model is relatively small. However, in objective 2, X8 exhibits stronger sensitivity, while the variables with lower sensitivity are X4 and X7. Considering both objectives, we determined that the impact of X7 on the overall output of the model is negligible. Similarly, the same analysis was performed on the C4F7N mixture, where X6, X7, and X8 were considered relatively insensitive design variables for both objectives. Therefore, the design variables with less impact were kept with the initial data, while the highly sensitive design variables were randomly generated with 100 sample points using the Latin hypercube sampling method, as shown in Table 2.

[0144] Table 2 shows the design variables for different gas sensitivity levels.

[0145]

[0146] Real CFD simulations were performed at all sampling points to generate the dataset and build the data-driven model. Figure 4 shows the prediction accuracy of the SVR data-driven model for SF6. The diagonal line indicates the highest prediction accuracy; it can be seen that the prediction accuracy of SVR is very high, and the R 2 values of the two objectives are 0.9329 and 0.9997, respectively.

[0147] Based on the constructed SVR data-driven model, the multi-objective optimization of the circuit breaker was carried out, and the convergence history of the Pareto boundary generated by the two gases is shown in Figure 5. The points of different colors represent the state of convergence of the optimization in different generations. The NSGA-II algorithm performs 1000 iterations for each gas type, and 50 individuals are evaluated each iteration. Therefore, up to 50,000 different circuit breaker geometries were evaluated for performance, and convergence was observed at the 500th iteration. The green star on the Pareto boundary represents the optimal design selected according to the actual engineering applicability. For comparison, the performance of the target function of the initial baseline design is represented by a red star. By intuitively comparing the geometric distance between the two stars, it can be seen that the optimization effect is obvious, and two conflicting objectives can be considered comprehensively. In order to further clarify the effectiveness of the data-driven model and the optimization program, a real CFD evaluation was carried out on the selected optimized design. The actual value obtained by the CFD simulation and the predicted value of the SVR model are shown in Table 3. The maximum error of the predicted value is 0.573%, and the minimum error is 0.097%, which again confirms the accuracy of the SVR data-driven model.

[0148] Table 3 is the result table of the optimized design

[0149]

[0150] As shown in Figure 5, Figure 5 shows the simulation results of the two objective functions under the optimized design structure and the original design structure. After optimization, compared with the baseline design, the pressure drop of SF6 ) max is reduced by about 7.4%, and the average pressure in the cavity is increased by about 14.1%. Similarly, for C4F7N mixed gas, the pressure drop is reduced by about 3.4%, and the average pressure in the compression chamber is increased by about 4.2%. max

[0151] The above embodiment is only one of the implementation manners capable of realizing the technical scheme of the present application, and the scope of protection claimed by the present application is not limited to the above embodiment only, but also includes any changes, substitutions and other implementation manners easily thought of by those skilled in the art within the technical scope disclosed by the present application.​​

Claims

1. A data-driven multi-objective optimization method for environmentally friendly gas quenching system, characterized in that, The method comprises the following steps: S1: Collecting key design variables of the environmentally friendly gas arc extinguishing system, inputting the key design variables into a pre-constructed parameterized circuit breaker cold-state simulation model, and outputting a target function value; S2: Based on the key design variables and the corresponding target function value, a data-driven model is constructed and trained to predict and evaluate the design space; S3: Combined with the trained data-driven model and the pre-constructed optimization objective function, a multi-objective genetic algorithm is used to output the optimal design variables to optimize the environmentally friendly gas arc extinguishing system; wherein the optimization objective function is used to represent the breaking capacity of the circuit breaker.

2. The data-driven environmentally friendly gas quenching system multi-objective optimization method of claim 1, wherein, In S1, the sensitivity of the collected key design variables is analyzed by the Morris method, and the key design variables are divided into insensitive variables and highly sensitive variables; The insensitive variables are kept at the initial data, and the highly sensitive variables are randomly generated by the Latin hypercube sampling method to generate multiple sample points; All sample points generated by the highly sensitive variables are input into the pre-constructed parameterized circuit breaker cold-state simulation model, and the target function value is output.

3. The data-driven environmentally friendly gas quenching system multi-objective optimization method of claim 2, wherein, The sensitivity of the collected key design variables is analyzed by using the Morris method, wherein the average value of the corresponding trajectory basic effect EE and the standard deviation are taken as the global sensitivity index to identify the design variables that have a significant impact on the breaking performance; the formula expressions of the average value and the standard deviation are as follows: wherein for k-dimensional independent inputs, to output a response, For one of the values in the set of values, The number of layers; i is the i-th key design variable; r is the number of trajectories.

4. The data-driven environmentally friendly gas quenching system multi-objective optimization method of claim 1, wherein, In S1, the construction steps of the parameterized circuit breaker cold-state simulation model are as follows: According to the initial structure of the circuit breaker, a two-dimensional model of the circuit breaker is drawn and meshed, and the key design variables are set as variable parameters to construct a parameterized circuit breaker geometric model, realizing automatic modeling of the geometric structure of the parameterized circuit breaker geometric model and self-updating of the mesh; The complete physical property parameter data of the environmentally friendly gas is array encoded and combined with a linear interpolation algorithm to build a real gas model; the standard k-ε turbulence model is used to solve the exchange relationship between the momentum and energy of the gas medium under the action of the internal turbulence of the circuit breaker; The parameterized circuit breaker geometric model, the real gas model and the turbulence model are coupled to construct the parameterized circuit breaker cold-state simulation model.

5. The data-driven environmentally friendly gas quenching system multi-objective optimization method of claim 1, wherein, In S2, a data set is established with the key design variables as input and the objective function value as output, and a data-driven model is constructed using the support vector regression method, wherein the correlation coefficient R 2 is used as an index of the accuracy of the data-driven model. where N is the sample size, for the predicted value, for the actual value, The average value of the actual value.

6. The data-driven environmentally friendly gas quenching system multi-objective optimization method of claim 1, wherein, In S3, based on the trained data-driven model, the optimization design variables and the optimization target function value are output, combined with the pre-constructed optimization objective function, and the trade-off between multiple optimization objectives is realized through the Pareto boundary to output the optimal design variables; Wherein, the optimization objectives of the optimization objective function include minimizing the ratio of electric field strength and density and maximizing the average pressure in the plenum, which is specifically expressed as: wherein Ω is the design space, g(X) represents the optimized plenum volume V Opt , not greater than the reference design V Base ; X is the key design variable; ； ； represents the ratio of the electric field strength to the gas density; Indicates the average pressure in the plenum.

7. The data-driven environmentally friendly gas quenching system multi-objective optimization method of claim 1, wherein, Further comprising: S4: Generating an optimized circuit breaker simulation model based on the optimal design variables, and performing real CFD simulation verification on the optimized circuit breaker simulation model.

8. A data-driven environmentally friendly gas quenching system multi-objective optimization system for implementing the steps of the data-driven environmentally friendly gas quenching system multi-objective optimization method of any one of claims 1-7, characterized in that, The method comprises the following steps: A simulation module for collecting key design variables of the environmentally friendly gas arc extinguishing system, inputting the key design variables into a pre-constructed parameterized circuit breaker cold-state simulation model, and outputting a target function value; A data-driven model construction module for constructing and training a data-driven model based on the key design variables and the corresponding target function value to predict and evaluate the design space; An optimal design variable output module is used to combine the trained data-driven model and the pre-constructed optimization objective function, adopt a multi-objective genetic algorithm, and output optimal design variables to achieve optimization of the environmentally friendly gas arc extinguishing system; wherein the optimization objective function is used to represent the breaking capacity of the circuit breaker.

9. An apparatus, comprising: The computer program is executed by the processor to implement the steps of the data-driven multi-objective optimization method of the environmentally friendly gas arc extinguishing system according to any one of claims 1-7. The computer program is executed by the processor to implement the steps of the data-driven multi-objective optimization method of the environmentally friendly gas arc extinguishing system according to any one of claims 1-7. ​ 10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. ​

Images