Reactor field-circuit coupling simulation calculation method, system and storage medium

Abstract

The present application discloses a method, system and storage medium for field-circuit coupling simulation calculation of a reactor. The method includes: determining an electromagnetic field model and a circuit model of the reactor to be analyzed; based on the electromagnetic field model and the circuit model, using an artificial intelligence model to perform resonance frequency analysis and field-circuit interaction prediction; based on the resonance frequency analysis result and the field-circuit interaction prediction result, determining the field-circuit coupling model of the reactor to be analyzed; using the boundary element method to perform calculations according to the field-circuit coupling model to obtain calculation results, so as to be able to shorten the calculation time and reduce the consumption of calculation resources while ensuring the accuracy of the simulation calculation.

Description

Technical Field

[0001] This application relates to the field of simulation technology, and in particular, to a method, system, and storage medium for simulating and calculating the field-circuit coupling of a reactor. Background Art

[0002] In a power system, a reactor, as an important electrical component, usually has functions such as controlling reactive power, filtering harmonics, and improving system stability. Specifically, through its unique inductance characteristics, a reactor is widely used in aspects such as current regulation, filtering, and power factor control. Whether in large-scale power transmission and transformation equipment or in delicate electronic circuits, the reactor plays a key role in ensuring the stable and safe operation of the system.

[0003] During the operation of a reactor, it will be closely coupled with complex factors such as the surrounding electromagnetic field and transmission lines. This coupling effect includes the interaction between the reactor and the electrical network and lines, which not only affects the operating efficiency of the power system but may also cause electromagnetic interference, resonance problems, etc. When the reactor is operating, the coupling effect between the inductive reactance of the reactor and capacitors or other components of the circuit (such as parasitic capacitors, etc.) will significantly change the inductance of the circuit, thereby affecting electrical parameters such as current, voltage, and power factor. With the increasing requirements of the power system for high efficiency, low loss, and high reliability, the design of reactors is becoming more and more precise and complex.

[0004] However, traditional methods for simulating and calculating the field-circuit coupling of reactors often rely on numerical simulation and a large amount of computing resources, resulting in a long calculation time. Summary of the Invention

[0005] To solve the above technical problems, embodiments of this application propose a method, system, and storage medium for simulating and calculating the field-circuit coupling of a reactor, which can shorten the calculation time and reduce the consumption of computing resources while ensuring the accuracy of the simulation calculation.

[0006] In a first aspect, embodiments of this application provide a method for simulating and calculating the field-circuit coupling of a reactor, including:

[0007] Determine the electromagnetic field model and circuit model of the reactor to be analyzed;

[0008] Based on the electromagnetic field model and the circuit model, use an artificial intelligence model to analyze the resonance frequency and predict the field-circuit interaction;

[0009] Based on the resonance frequency analysis result and the field-circuit interaction prediction result, determine the field-circuit coupling model of the reactor to be analyzed;

[0010] Use the boundary element method to perform calculations according to the field-circuit coupling model to obtain the calculation result;

[0011] Among them, the training method of the artificial intelligence model includes:

[0012] Obtain the historical simulation data of the sample reactor, where the historical simulation data includes historical electromagnetic field data and historical circuit data;

[0013] Based on the historical simulation data, train the deep learning model to be trained through a loss function to obtain the artificial intelligence model, where the loss function is constructed according to the resonance frequency corresponding to the sample reactor Build.

[0014] Optionally, the loss function includes a mean square error loss function, and the formula of the mean square error loss function includes:

[0015]

[0016] Among them, is the loss function, is the number of samples in the historical simulation data, is the true value of the i-th sample in the historical simulation data, is the predicted value of the i-th sample, represents the weight function corresponding to the frequency characterized by the i-th sample And, the smaller the difference between and , the larger the value of .

[0017] Optionally, the training of the deep learning model to be trained through a loss function based on the historical simulation data to obtain the artificial intelligence model includes:

[0018] Taking minimizing the loss function as the goal, using the gradient descent algorithm, and training the deep learning model to be trained based on the historical simulation data to obtain the artificial intelligence model.

[0019] Optionally, determining the field-circuit coupling model of the reactor to be analyzed based on the resonance frequency analysis result and the field-circuit interaction prediction result includes:

[0020] Determine the voltage-current boundary conditions based on the resonance frequency analysis result and the field-circuit interaction prediction result;

[0021] Determine the field-circuit coupling model of the reactor to be analyzed based on the voltage-current boundary conditions.

[0022] Optionally, the method further includes:

[0023] In the case where the calculation result does not converge, modify the voltage-current boundary condition according to the calculation result;

[0024] Use the modified voltage-current boundary condition as the new voltage-current boundary condition, and thus return to the step of determining the field-circuit coupling model of the reactor to be analyzed based on the voltage-current boundary condition until the obtained calculation result converges, and output the convergent calculation result.

[0025] In a second aspect, an embodiment of the present application provides a reactor field-circuit coupling simulation calculation system, including:

[0026] A model determination module, configured to determine the electromagnetic field model and the circuit model of the reactor to be analyzed;

[0027] An analysis and prediction module, configured to perform resonance frequency analysis and field-circuit interaction prediction by using an artificial intelligence model based on the electromagnetic field model and the circuit model;

[0028] A field-circuit coupling module, configured to determine the field-circuit coupling model of the reactor to be analyzed based on the resonance frequency analysis result and the field-circuit interaction prediction result;

[0029] A calculation module, configured to use the boundary element method to perform calculations according to the field-circuit coupling model to obtain a calculation result;

[0030] Wherein, the training method of the artificial intelligence model includes:

[0031] Obtain historical simulation data of a sample reactor, where the historical simulation data includes historical electromagnetic field data and historical circuit data;

[0032] Based on the historical simulation data, perform model training on a deep learning model to be trained through a loss function to obtain the artificial intelligence model, where the loss function is constructed according to the resonance frequency corresponding to the sample reactor Build.

[0033] Optionally, the loss function includes a mean square error loss function, and the formula of the mean square error loss function includes:

[0034]

[0035] Wherein, is the loss function, is the number of samples in the historical simulation data, is the true value of the i-th sample in the historical simulation data, is the predicted value of the i-th sample, represents the weight function corresponding to the frequency characterized by the i-th sample, and, The smaller the difference with , the larger the value of .

[0036] Optionally, based on the historical simulation data, training the deep learning model to be trained through a loss function to obtain the artificial intelligence model, including:

[0037] Taking minimizing the loss function as the goal, using the gradient descent algorithm to train the deep learning model to be trained based on the historical simulation data to obtain the artificial intelligence model.

[0038] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the reactor field-circuit coupling simulation calculation method described in any one of the above are implemented.

[0039] In summary, the embodiments of the present application at least have the following beneficial effects:

[0040] By adopting the embodiments of the present application, by determining the electromagnetic field model and circuit model of the reactor to be analyzed; based on the electromagnetic field model and the circuit model, using the artificial intelligence model to perform resonance frequency analysis and field-circuit interaction prediction; based on the resonance frequency analysis result and the field-circuit interaction prediction result, determining the field-circuit coupling model of the reactor to be analyzed; using the boundary element method to perform calculations according to the field-circuit coupling model to obtain calculation results, it is possible to shorten the calculation time and reduce the consumption of calculation resources while ensuring the accuracy of the simulation calculation. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 is a schematic flowchart of the reactor field-circuit coupling simulation calculation method provided by the embodiment of the present application;

[0042] Figure 2 is a schematic diagram of the reactor field-circuit coupling simulation calculation provided by the embodiment of the present application;

[0043] Figure 3 is a schematic structural diagram of the reactor field-circuit coupling simulation calculation system provided by the embodiment of the present application. DETAILED DESCRIPTION

[0044] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0045] In the description of this application, the terms "first", "second", "third", etc. are only used for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second", "third", etc. may explicitly or implicitly include one or more of such features. In the description of this application, unless otherwise specified, the meaning of "a plurality" is two or more. In the description of this application, the term "comprising" and its variants are open-ended, that is, "including but not limited to". The term "based on" means "at least partially based on". The term "according to" means "at least partially according to". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments".

[0046] In the description of this application, it should be noted that unless otherwise clearly specified and limited, the terms "installed", "connected", and "coupled" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific situations.

[0047] In the description of this application, it should be noted that unless otherwise defined, all technical and scientific terms used in this application have the same meanings as those commonly understood by those skilled in the technical field to which this application belongs. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific situations.

[0048] In a first aspect, referring to Figure 1 , a schematic flowchart of a method for simulating the field-circuit coupling of a reactor provided by an embodiment of this application is shown. The method includes steps S101 - S104, specifically as follows:

[0049] S101, determine the electromagnetic field model and circuit model of the reactor to be analyzed;

[0050] In one example, referring to Figure 2 , a reactor field model (i.e., the electromagnetic field model of the reactor) and a reactor circuit model (i.e., the circuit model of the reactor) can be pre-built so that they can be conveniently called when needed.

[0051] It should be noted that the electromagnetic field model and the circuit model can be used to reflect the performance changes of the reactor to be analyzed under different loads, different frequencies, and different working conditions.

[0052] In one example, a parametric field model of the reactor can also be established for building an electromagnetic field model. The three-dimensional model of the reactor can be accurately built according to the reactor type such as air, iron core, high frequency, and the actual operation scenario, which involves three aspects: geometric modeling, material parameter selection, and boundary condition setting. First, define the geometric shape of the reactor, including the dimensions and relative positions of the iron core, coil, and cooling system components, and select a coordinate system based on the geometric symmetry of the reactor, including the rectangular coordinate system and the cylindrical coordinate system. Then, determine the conductivity, permeability, and relative permeability of different materials in the reactor; consider the hysteresis effect and saturation magnetic induction intensity of the materials, set the hysteresis effect and nonlinear characteristics, and take into account the resistance of the coil winding and the loss caused by the current. Finally, define the current distribution in the windings of the reactor, and set the magnetic field in the external region of the reactor as an open boundary and a material with a permeability close to that of a vacuum according to the operating conditions. In addition, the method may further include: performing a preliminary resonance frequency analysis when building the electromagnetic field model based on the basic characteristics of the inductive element of the reactor, considering that significant changes occur in the relationship between the inductance value and the current and voltage near the resonance frequency, and improving the model accuracy through the results of the preliminary resonance frequency analysis to improve the accuracy of the parametric field model of the reactor in the circuit.

[0053] In one example, the electromagnetic field model can be constructed by solving Maxwell's equations, where Maxwell's equations can be expressed as:

[0054]

[0055] where, is the electric field, is the magnetic field, is the current density, is the charge density, is the permittivity, and B is the magnetic induction intensity.

[0056] In this embodiment, using Maxwell's equations to establish the electromagnetic field model of the reactor can accurately describe the electromagnetic field behavior in the reactor, ensure electromagnetic compatibility and prediction performance, and realize the accurate establishment of the electromagnetic field model of the reactor, providing a basis for the coupling of the field-circuit model.

[0057] In one example, the circuit model can be constructed in the following way.

[0058] The circuit part of the reactor usually consists of components such as inductors and transformers. The relationship between the current and voltage of the inductor part can be described by the following model formula:

[0059]

[0060] where, is the voltage across the inductor, is an inductor, is the current in the inductor, is the parasitic resistance in the circuit.

[0061] In an actual circuit, there will also be a parasitic capacitance, and there is a resonance frequency between it and the inductor:

[0062]

[0063] Among them, is the parasitic capacitance.

[0064] Accordingly, the relational function formula between the current and voltage of the inductor part can be modified to:

[0065]

[0066] Among them, is a parameter related to frequency, indicating that the inductance of the reactor changes with frequency. Thus, the above formula can be used to represent this circuit model.

[0067] It can be understood that by inputting the working conditions such as the current and voltage of the reactor into the above model, the characteristics such as the electric field strength and magnetic field strength of the reactor can be quickly predicted; in addition, the component parameters in the model can also be quickly adjusted according to the electromagnetic behavior of the reactor.

[0068] S102, based on the electromagnetic field model and the circuit model, use an artificial intelligence model to perform resonance frequency analysis and field-circuit interaction prediction;

[0069] It should be noted that the artificial intelligence model in this embodiment can be a related model trained in advance by using a general model training method, so that the model can learn the non-linear relationship between the electromagnetic field and the circuit, solve the problems of traditional coupling methods that require multiple iterative calculations and numerical simulations, large computational workload, and slow calculation speed, and facilitate the rapid and accurate establishment of the field-circuit coupling model of the reactor. The artificial intelligence model is suitable for taking the parameters of the electromagnetic field model and the circuit model as inputs respectively, and performing resonance frequency analysis and field-circuit interaction prediction based on this. Field-circuit interaction can refer to the interaction between the magnetic field (field) and the circuit (circuit).

[0070] S103, based on the resonance frequency analysis result and the field-circuit interaction prediction result, determine the field-circuit coupling model of the to-be-analyzed reactor;

[0071] It should be noted that when the reactor is operating, the resonance frequency is usually closely related to the operating frequency of the system. Near the resonance frequency, the coupling effect between the inductive reactance of the reactor and the capacitance or other components of the circuit (such as parasitic capacitance, etc.) will significantly change the inductance of the circuit, thereby affecting electrical parameters such as current, voltage, and power factor. Therefore, in this embodiment, the resonance frequency analysis result can be used to assist the field-circuit interaction prediction result, so as to efficiently construct a more accurate field-circuit coupling model.

[0072] S104, using the boundary element method, calculate according to the field-circuit coupling model to obtain a calculation result.

[0073] Among them, the training method of the artificial intelligence model includes:

[0074] Obtain the historical simulation data of the sample reactor, where the historical simulation data includes historical electromagnetic field data and historical circuit data;

[0075] Based on the historical simulation data, train the deep learning model to be trained through a loss function to obtain the artificial intelligence model, where the loss function is constructed according to the resonance frequency corresponding to the sample reactor Build.

[0076] In an alternative embodiment, the loss function includes a mean square error loss function, and the formula of the mean square error loss function includes:

[0077]

[0078] Among them, is the loss function, is the number of samples in the historical simulation data, is the true value of the i-th sample in the historical simulation data, is the predicted value of the i-th sample, represents the weight function corresponding to the frequency characterized by the i-th sample, and, The smaller the difference between and the greater the value of

[0079] It should be noted that the true value and the predicted value in this embodiment can be embodied as parameters such as voltage, current, and electromagnetic field.

[0080] In this embodiment, different weights can be assigned to the prediction errors at different frequencies, and the maximum weight will occur at the resonance frequency At the closest frequency, so that when the frequency is far from the resonant frequency, the weight is small and the corresponding loss error has a small impact, in order to ensure a better fit to the impact that the frequency close to the resonant frequency will have on the reactor voltage and current, thereby learning the influence mechanism of the resonant frequency on the electromagnetic field and the circuit model, so that the artificial intelligence model can predict the change of the inductance value with the resonant frequency, as well as the distribution of voltage and current at different frequencies.

[0081] In an alternative embodiment, the model training of the deep learning model to be trained through a loss function based on the historical simulation data to obtain the artificial intelligence model includes:

[0082] With the goal of minimizing the loss function, using the gradient descent algorithm, based on the historical simulation data, perform model training on the deep learning model to be trained to obtain the artificial intelligence model.

[0083] In an example, the specific process of the gradient descent algorithm may include:

[0084] (1) Forward propagation: Calculate the predicted value of the network.

[0085] (2) Calculate the loss function: Calculate the loss function based on the predicted value and the actual value.

[0086] (3) Backward propagation: Calculate the gradient of the loss function with respect to each parameter in the model through the chain rule.

[0087] (4) Update parameters: Update the parameters according to the formula of the gradient descent method. For each parameter (for example, including weights and biases), the update rule is: . Wherein, are the neural network parameters (weights and biases), is the learning rate, which depends on the step size of each update, is the gradient of the loss function with respect to the parameter , , represent the updated parameter and the parameter before update in sequence.

[0088] In an alternative embodiment, the determination of the field-circuit coupling model of the reactor to be analyzed based on the resonant frequency analysis result and the field-circuit interaction prediction result includes:

[0089] Based on the resonant frequency analysis result and the field-circuit interaction prediction result, determine the voltage-current boundary conditions;

[0090] Based on the voltage-current boundary conditions, determine the field-circuit coupling model of the reactor to be analyzed.

[0091] In this embodiment, since the aforementioned artificial intelligence model has the ability to analyze resonance frequencies and predict field-circuit interactions, it can predict the mutual influence among voltage, current, and electromagnetic fields in a circuit. Furthermore, it can obtain more accurate voltage-current boundary conditions based on the resonance frequency analysis results and field-circuit interaction prediction results.

[0092] In one example, simulation tools (such as Ansys Maxwell + Simplorer, Comsol Multiphysics, etc.) can be used. Taking the resonance frequency analysis results and field-circuit interaction prediction results as conditions, field-circuit coupling simulation is carried out to simulate reasonable voltage-current boundary conditions, and accordingly, a field-circuit coupling model is configured.

[0093] In an alternative implementation, the method further includes:

[0094] In the case where the calculation result does not converge, modify the voltage-current boundary condition according to the calculation result;

[0095] Use the modified voltage-current boundary condition as the new voltage-current boundary condition, and thus return to the step of determining the field-circuit coupling model of the reactor to be analyzed based on the voltage-current boundary condition until the obtained calculation result converges, and output the converged calculation result.

[0096] In this embodiment, since the influence of resonance frequency on the circuit inductance and the resulting current and voltage fluctuations are considered, it is ensured that in each calculation step of the iteration, the boundary condition can adapt to the frequency change, thereby improving the calculation accuracy and efficiency. In addition, according to the modification of the boundary condition, the reactor field-circuit coupling model can be quickly updated using the new voltage-current boundary condition, avoiding the complex process of recalculating the electromagnetic field model and / or circuit model each time.

[0097] In one example, the boundary element method can use a boundary element algorithm (BEM, Boundary Element Method) based on resonance frequency analysis to handle the dynamic coupling form considering resonance frequency between the reactor and the circuit. The formula of this boundary element algorithm includes:

[0098]

[0099] where, is the field quantity (electric field or magnetic field) at the field point at time t with the resonance frequency , is the boundary surface, is the boundary condition function, representing the source intensity (current, voltage) at the boundary and including the time (characterized by time t) and frequency The related dynamic effect is the frequency-dependent Green's function.

[0100] In this embodiment, the boundary element algorithm has the following advantages:

[0101] (1) High efficiency: The boundary element method can reduce the solution dimension of three-dimensional problems to two dimensions, thus greatly reducing the amount of calculation. Especially when dealing with reactors with complex geometries, it has significant computational advantages.

[0102] (2) Accuracy: The boundary element method can accurately handle the coupling problem between the electromagnetic field and the circuit, and is applicable to large-scale power systems and complex electrical equipment.

[0103] (3) Flexibility: The boundary element method is applicable to various types of boundary conditions and can well handle various coupling forms between the reactor and the circuit, such as static, dynamic, time domain, and frequency domain.

[0104] Based on the above corresponding embodiments, the present application can achieve the following beneficial effects:

[0105] 1. By performing geometric modeling, material parameter selection, and boundary condition setting on the reactor in actual operation, a rapid establishment of an electromagnetic field model that conforms to the actual operating conditions of the reactor can be achieved. Through the external circuit characteristics during the operation of the reactor, a parameterized circuit model of the reactor that conforms to the actual operation of the reactor can be established. Through resonance frequency analysis, the accuracy of the electromagnetic field model and the circuit model can be improved, reflecting the performance changes of the reactor under different loads, different frequencies, and different operating conditions.

[0106] 2. Using an artificial intelligence model (such as Figure 2 the regression neural network deep learning model shown in), through a large amount of simulation data, learn the complex non-linear relationship between the electromagnetic field model and the circuit model of the reactor, apply it to the field-circuit model coupling process, learn the influence mechanism of the resonance frequency on the field-circuit coupling model, realize automatic interactive prediction calculation of the field-circuit model, and obtain more accurate voltage and current boundary conditions, so as to quickly and accurately establish the field-circuit coupling model of the reactor.

[0107] 3. Use the boundary element algorithm to solve the field-circuit coupling model of the reactor considering the influence of the resonance frequency, modify the voltage and current boundary conditions of the reactor according to the calculation results, quickly update the field-circuit coupling model of the reactor and perform calculations until convergence, avoiding the complex process of recalculating the electromagnetic field model, greatly reducing the amount of calculation, and facilitating the rapid calculation of the field-circuit coupling of the reactor.

[0108] Second aspect, correspondingly, the embodiments of the present application further provide a reactor field-circuit coupling simulation calculation system, which can implement all processes of the reactor field-circuit coupling simulation calculation method provided in the above embodiments.

[0109] See Figure 3 , which shows a schematic structural diagram of the reactor field-circuit coupling simulation calculation system provided by the embodiments of the present application. The reactor field-circuit coupling simulation calculation system includes:

[0110] A model determination module 301, configured to determine the electromagnetic field model and circuit model of the reactor to be analyzed;

[0111] An analysis and prediction module 302, configured to perform resonance frequency analysis and field-circuit interaction prediction based on the electromagnetic field model and the circuit model by using an artificial intelligence model;

[0112] A field-circuit coupling module 303, configured to determine the field-circuit coupling model of the reactor to be analyzed based on the resonance frequency analysis result and the field-circuit interaction prediction result;

[0113] A calculation module 304, configured to use the boundary element method to perform calculations according to the field-circuit coupling model to obtain a calculation result.

[0114] Wherein, the training method of the artificial intelligence model includes:

[0115] Obtain historical simulation data of the sample reactor, wherein the historical simulation data includes historical electromagnetic field data and historical circuit data;

[0116] Based on the historical simulation data, perform model training on the deep learning model to be trained through a loss function to obtain the artificial intelligence model, wherein the loss function is constructed according to the resonance frequency corresponding to the sample reactor Build.

[0117] In an optional implementation manner, the loss function includes a mean square error loss function, and the formula of the mean square error loss function includes:

[0118]

[0119] Wherein, is the loss function, is the number of samples in the historical simulation data, is the true value of the i-th sample in the historical simulation data, is the predicted value of the i-th sample, represents the weight function corresponding to the frequency characterized by the i-th sample, and, and The smaller the difference between them, the The larger the value of

[0120] In an alternative embodiment, the method of training the deep learning model to be trained based on the historical simulation data through a loss function to obtain the artificial intelligence model includes:

[0121] Taking minimizing the loss function as the goal, using the gradient descent algorithm to train the deep learning model to be trained based on the historical simulation data to obtain the artificial intelligence model.

[0122] In an alternative embodiment, the method of determining the field-circuit coupling model of the reactor to be analyzed based on the resonance frequency analysis result and the field-circuit interaction prediction result includes:

[0123] Determining the voltage-current boundary conditions based on the resonance frequency analysis result and the field-circuit interaction prediction result;

[0124] Determining the field-circuit coupling model of the reactor to be analyzed based on the voltage-current boundary conditions.

[0125] In an alternative embodiment, the system further includes an iteration module, and the iteration module is configured to:

[0126] In the case where the calculation result does not converge, modifying the voltage-current boundary conditions according to the calculation result;

[0127] Taking the modified voltage-current boundary conditions as the new voltage-current boundary conditions, and thus returning to the step of determining the field-circuit coupling model of the reactor to be analyzed based on the voltage-current boundary conditions until the obtained calculation result converges, and outputting the converged calculation result.

[0128] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the reactor field-circuit coupling simulation calculation method described in any one of the above are implemented.

[0129] In summary, the embodiments of the present application at least have the following beneficial effects:

[0130] By adopting the embodiments of the present application, by determining the electromagnetic field model and the circuit model of the reactor to be analyzed; based on the electromagnetic field model and the circuit model, using the artificial intelligence model to perform resonance frequency analysis and field-circuit interaction prediction; based on the resonance frequency analysis result and the field-circuit interaction prediction result, determining the field-circuit coupling model of the reactor to be analyzed; using the boundary element method to perform calculations according to the field-circuit coupling model to obtain a calculation result, it is possible to shorten the calculation time and reduce the consumption of calculation resources while ensuring the simulation calculation accuracy.

[0131] Through the description of the above embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus a necessary hardware platform, and of course, it can also be implemented entirely through hardware. Based on this understanding, all or part of the technical solution of this application that contributes to the background art can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM (Read-Only Memory), RAM (Random Access Memory), magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0132] The above is the preferred embodiment of this application. It should be noted that for those of ordinary skill in the art, without departing from the principle of this application, several improvements and refinements can still be made, and these improvements and refinements are also regarded as the protection scope of this application.

Claims

1. A field-circuit coupling simulation calculation method for a reactor, characterized in that including: Determine the electromagnetic field model and circuit model of the reactor to be analyzed; Based on the electromagnetic field model and the circuit model, use an artificial intelligence model to perform resonance frequency analysis and field-circuit interaction prediction; Based on the resonance frequency analysis result and the field-circuit interaction prediction result, determine the field-circuit coupling model of the reactor to be analyzed; Use the boundary element method to calculate according to the field-circuit coupling model to obtain a calculation result; Among them, the training method of the artificial intelligence model includes: Obtain the historical simulation data of the sample reactor, where the historical simulation data includes historical electromagnetic field data and historical circuit data; Based on the historical simulation data, the deep learning model to be trained is trained through a loss function to obtain the artificial intelligence model, wherein the loss function is constructed according to the resonance frequency corresponding to the sample reactor constructed; Among them, the determining the field-circuit coupling model of the reactor to be analyzed based on the resonance frequency analysis result and the field-circuit interaction prediction result includes: Based on the resonance frequency analysis result and the field-circuit interaction prediction result, determine the voltage-current boundary conditions; Based on the voltage-current boundary conditions, determine the field-circuit coupling model of the reactor to be analyzed; Among them, the method further includes: In the case where the calculation result does not converge, modify the voltage-current boundary conditions according to the calculation result; Use the modified voltage-current boundary conditions as the new voltage-current boundary conditions, and thus return to the step of determining the field-circuit coupling model of the reactor to be analyzed based on the voltage-current boundary conditions until the obtained calculation result converges, and output the converged calculation result.

2. The field-circuit coupling simulation calculation method of the reactor according to claim 1, characterized in that The loss function includes the mean square error loss function, and the formula of the mean square error loss function includes: Among them, is the loss function, is the number of samples in the historical simulation data, is the true value of the i-th sample in the historical simulation data, is the predicted value of the i-th sample, represents the frequency characterized by the i-th sample corresponding weight function, and, and the smaller the difference between them, the larger the value of 3. The reactor field-circuit coupling simulation calculation method according to claim 1, wherein The training the deep learning model to be trained through the loss function based on the historical simulation data to obtain the artificial intelligence model includes: Taking minimizing the loss function as the goal, using the gradient descent algorithm, and training the deep learning model to be trained based on the historical simulation data to obtain the artificial intelligence model.

4. A reactor field-circuit coupling simulation calculation system, characterized in that, including: A model determination module for determining the electromagnetic field model and circuit model of the reactor to be analyzed; An analysis and prediction module for performing resonance frequency analysis and field-circuit interaction prediction using an artificial intelligence model based on the electromagnetic field model and the circuit model; A field-circuit coupling module for determining the field-circuit coupling model of the reactor to be analyzed based on the resonance frequency analysis result and the field-circuit interaction prediction result; A calculation module for using the boundary element method to calculate according to the field-circuit coupling model to obtain a calculation result; Among them, the training method of the artificial intelligence model includes: Obtain the historical simulation data of the sample reactor, where the historical simulation data includes historical electromagnetic field data and historical circuit data; Based on the historical simulation data, the deep learning model to be trained is trained through a loss function to obtain the artificial intelligence model, wherein the loss function is constructed according to the resonance frequency corresponding to the sample reactor ; Among them, the determining the field-circuit coupling model of the reactor to be analyzed based on the resonance frequency analysis result and the field-circuit interaction prediction result includes: Based on the resonance frequency analysis result and the field-circuit interaction prediction result, determine the voltage-current boundary conditions; Based on the voltage-current boundary conditions, determine the field-circuit coupling model of the reactor to be analyzed; The system further includes an iteration module, and the iteration module is used for: In the case where the calculation result does not converge, modify the voltage-current boundary conditions according to the calculation result; Take the modified voltage and current boundary conditions as the new voltage and current boundary conditions, and thus return the step of determining the field-circuit coupling model of the reactor to be analyzed based on the voltage and current boundary conditions until the obtained calculation results converge, and output the converged calculation results.

5. The reactor field-circuit coupling simulation calculation system according to claim 4, wherein The loss function includes the mean square error loss function, and the formula of the mean square error loss function includes: Among them, is the loss function, is the number of samples in the historical simulation data, is the true value of the i-th sample in the historical simulation data, is the predicted value of the i-th sample, represents the frequency characterized by the i-th sample corresponding weight function, and, and the smaller the difference between them, the larger the value of 6. The reactor field-circuit coupling simulation calculation system according to claim 4, wherein Based on the historical simulation data, training the deep learning model to be trained through a loss function to obtain the artificial intelligence model, including: Taking minimizing the loss function as the goal, using the gradient descent algorithm, training the deep learning model to be trained based on the historical simulation data to obtain the artificial intelligence model.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the reactor field-circuit coupling simulation calculation method according to any one of claims 1-3.

Images