Power equipment heat flow coupling field rapid calculation method and related device

Abstract

The invention belongs to the technical field of power equipment insulation structure design, and discloses a power equipment heat flow coupling field rapid calculation method and a related device. Processing unknown working conditions by using the trained KAN neural network agent model to obtain feature coefficients corresponding to the unknown working conditions; calculating to obtain a power equipment heat flow coupling field corresponding to an unknown working condition by using the calculated orthogonal basis vector and the characteristic coefficient corresponding to the unknown working condition; the orthogonal basis vector calculation process comprises the following steps: establishing a power equipment heat flow coupling field simulation model, and calculating to obtain simulation results corresponding to different working conditions; constructing a sample set through a simulation result; performing eigenorthogonal decomposition on the sample set to obtain feature coefficients and orthogonal basis vectors of the corresponding sample set under different working conditions; according to the method, rapid calculation of the heat flow coupling field of the power equipment can be met, and the accuracy of a calculation result can be ensured while the calculation efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of power equipment insulation structure design, and particularly relates to a method for rapidly calculating the thermal-fluid coupling field of power equipment and related devices. Background Art

[0002] In recent years, with the large-scale cross-research and application of modern information technologies such as big data, cloud computing, and artificial intelligence and energy technologies, digital technologies have developed comprehensively in multiple fields. To promote the transformation of the energy system towards digitalization and intelligentization, a digital and intelligent power grid should be used to support the construction of a new power system, and the development of energy equipment state recognition, reliability assessment, and fault diagnosis technologies based on artificial intelligence should be accelerated to improve on-site perception, computing, and data transmission and interaction capabilities.

[0003] With the construction and development of smart grids, big data and Digital Twin technologies have been initially applied in aspects such as power equipment state monitoring and analysis, fault identification and diagnosis, and the power Internet of Things. Various information acquisition systems and new intelligent data analysis platforms of power grid enterprises have been gradually built, laying a good foundation for the development and application of power equipment digital technologies. However, the digital technologies of power equipment mainly remain in the stages of offline modeling, simulation calculation, and visualization display. There are still problems such as limited sensor distribution range, poor timeliness of obtaining field quantity information, and low data intelligent analysis and processing capabilities, making it difficult to meet the requirements of all-round, real-time, and accurate perception of the state of power equipment. The research on core digital technologies of power equipment such as intelligent sensing and Digital Twin still needs to be further deepened. Digital Twin refers to the all-round virtual mapping of a physical entity in the space-time scale, so as to realize the real-time simulation and accurate prediction of the state information of the physical entity in the virtual space. Therefore, Digital Twin technology is the key to rapidly and accurately obtaining the state of field quantity information of power equipment and estimating its lifespan.

[0004] However, the low efficiency of multi-physical field coupling simulation calculation is a serious problem that hinders the visualization of global information and real-time evaluation and analysis of power equipment, and it is also a difficult problem in the application of digital twin technology to the digital field of power equipment. The core of power equipment digitization is the visualization and evaluation of state data throughout the life cycle. Digital twin technology, with multi-physical field simulation technology as one of the cores, is the key to the visualization of internal characteristics of current equipment. With the continuous improvement of the digitization and intelligence level of power equipment, the requirements for the timeliness and accuracy of multi-physical field simulation are also increasing day by day. The method of mainly using multi-physical field simulation and integrating a small amount of sensor data to correct the simulation results is the general trend. The large size of power equipment, the huge number of grid nodes, and the action of multiple non-linear physical fields result in long time-consuming and large computing resource consumption for multi-physical field simulation solutions. Currently, it is mainly offline simulation calculation, and it is difficult to achieve real-time and accurate calculation. Power equipment (such as transformers, GIS (Gas-Insulated Switchgear in English; Gas Insulated Switchgear in Chinese) or GIL (Gas-Insulated Transmission Line in English; Gas Insulated Transmission Line in Chinese)) has the characteristics of complex structure, numerous components, large differences in material properties, and harsh operating conditions, and is the most critical equipment in the power system. Therefore, it is of great significance to study a fast simulation method for multi-physical fields of power equipment and achieve second-level fast calculation of single-field and multi-field at key parts inside the equipment, which can provide technical support for building the essential safety system of power equipment. Summary of the Invention

[0005] In order to solve the problems existing in the prior art, the purpose of the present invention is to provide a fast calculation method and related device for the thermal-fluid coupling field of power equipment. The present invention can meet the fast calculation of the thermal-fluid coupling field of power equipment, and while improving the operation efficiency, it can also ensure the accuracy of the calculation results.

[0006] To achieve the above object, the present invention adopts the following technical solutions: A fast calculation method for the thermal-fluid coupling field of power equipment includes the following processes: Obtain unknown operating conditions; Use the trained KAN neural network surrogate model (Kolmogorov-Arnold Network) to process the unknown operating conditions to obtain the characteristic coefficients corresponding to the unknown operating conditions; Using the calculated orthogonal basis vectors and the characteristic coefficients corresponding to unknown operating conditions, calculate the heat-fluid coupling field of the power equipment corresponding to the unknown operating conditions; wherein, the calculation process of the orthogonal basis vectors includes: establishing a simulation model of the heat-fluid coupling field of the power equipment; using the simulation model of the heat-fluid coupling field of the power equipment, calculating the simulation results of the heat-fluid coupling field of the power equipment corresponding to different operating conditions; constructing a sample set through the simulation results of the heat-fluid coupling field of the power equipment; performing proper orthogonal decomposition on the sample set to obtain the characteristic coefficients of the sample set corresponding to different operating conditions and the orthogonal basis vectors.

[0007] Preferably, the simulation result of the heat-fluid coupling field of the power equipment is temperature or flow velocity.

[0008] Preferably, the input of the KAN neural network surrogate model is the operating condition, and the output is the characteristic coefficient; When the simulation result of the heat-fluid coupling field of the power equipment is temperature, the number of neurons in the output layer of the KAN neural network surrogate model is the same as the dimension of the characteristic coefficient corresponding to the temperature; When the simulation result of the heat-fluid coupling field of the power equipment is flow velocity, the number of neurons in the output layer of the KAN neural network surrogate model is the same as the dimension of the characteristic coefficient corresponding to the flow velocity.

[0009] Preferably, the step of using the simulation model of the heat-fluid coupling field of the power equipment to calculate the simulation results of the heat-fluid coupling field of the power equipment corresponding to different operating conditions includes: Using the finite element numerical calculation method or the finite volume numerical calculation method for the simulation model of the heat-fluid coupling field of the power equipment to calculate the simulation results of the heat-fluid coupling field of the power equipment corresponding to different operating conditions.

[0010] Preferably, the step of using the calculated orthogonal basis vectors and the characteristic coefficients corresponding to unknown operating conditions to calculate the heat-fluid coupling field of the power equipment corresponding to the unknown operating conditions includes: Multiplying the characteristic coefficients corresponding to the unknown operating conditions by the orthogonal basis vectors, and then adding the average value of the sample set to obtain the heat-fluid coupling field of the power equipment corresponding to the unknown operating conditions.

[0011] Preferably, the power equipment is a transformer winding, a transformer bushing, a gas-insulated switchgear or a gas-insulated transmission line.

[0012] Preferably: when the power equipment is a transformer winding, the operating conditions include the temperature at the oil duct inlet, the flow velocity at the oil duct inlet and the heat source density of the winding; When the power equipment is a transformer bushing, a gas-insulated switchgear or a gas-insulated transmission line, the operating conditions include the current of the central current-carrying conductor and the ambient temperature.

[0013] The present invention also provides a system for implementing the above-mentioned fast calculation method of the thermal-fluid coupling field of power equipment, including: A data acquisition module: used to acquire unknown operating conditions; A first calculation module: used to process the unknown operating conditions by using the pre-trained KAN neural network surrogate model to obtain the characteristic coefficients corresponding to the unknown operating conditions; A second calculation module: used to calculate the thermal-fluid coupling field of the power equipment corresponding to the unknown operating conditions by using the calculated orthogonal basis vectors and the characteristic coefficients corresponding to the unknown operating conditions; wherein, the calculation process of the orthogonal basis vectors includes: establishing a simulation model of the thermal-fluid coupling field of the power equipment; using the simulation model of the thermal-fluid coupling field of the power equipment to calculate the simulation results of the thermal-fluid coupling field of the power equipment corresponding to different operating conditions; constructing a sample set through the simulation results of the thermal-fluid coupling field of the power equipment; performing proper orthogonal decomposition on the sample set to obtain the characteristic coefficients of the sample set corresponding to different operating conditions and the orthogonal basis vectors.

[0014] The present invention also provides an electronic device, including: One or more processors; A storage device, on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the fast calculation method of the thermal-fluid coupling field of the power equipment as described above in the present invention.

[0015] The present invention also provides a storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the fast calculation method of the thermal-fluid coupling field of the power equipment as described above in the present invention.

[0016] Compared with the prior art, the present invention has the following beneficial effects: The rapid calculation method for the thermal-fluid coupling field of power equipment in the present invention, considering that the dimensions of the input and output parameters of the KAN neural network surrogate model should not be too many, which will affect the training accuracy and efficiency, and in order to improve the calculation speed, the data of the sample set is reduced in dimension through proper orthogonal decomposition (i.e., POD decomposition), and the rapid calculation of the thermal-fluid coupling field of power equipment is realized through the KAN neural network surrogate model, greatly reducing the operation time of the thermal field, and at the same time ensuring that the influence on the calculation accuracy is within a certain control range. And in the rapid calculation method for the thermal-fluid coupling field of power equipment in the present invention, the KAN neural network surrogate model is used to replace the traditional MLP (Multilayer Perceptron) architecture neural network, and the learnable B-spline function (Basis Function) in the KAN neural network surrogate model is used to replace the weight parameters. These B-spline functions can learn the laws between data, and have higher flexibility and adaptability for multi-physical field learning compared with the fixed activation function of the BP (Back Propagation) neural network. Description of the Drawings

[0017] Figure 1 It is the mesh generation diagram of the 220kV transformer winding in the embodiment of the present invention; Figure 2 It is the eigenvalue and contribution rate of the snapshot matrix of the temperature field of the 220kV transformer winding in the embodiment of the present invention; Figure 3 It is the eigenvalue and contribution rate of the snapshot matrix of the flow velocity field of the 220kV transformer winding in the embodiment of the present invention; Figure 4 It is the contour map of the temperature field of the 220kV transformer winding calculated by the finite element simulation method in the embodiment of the present invention; Figure 5 It is the contour map of the temperature field of the 220kV transformer winding obtained by the rapid calculation method for the thermal-fluid coupling field of power equipment in the present invention in the embodiment of the present invention; Figure 6 It is the contour map of the velocity field of the 220kV transformer winding calculated by the finite element simulation method in the embodiment of the present invention; Figure 7 It is the contour map of the velocity field of the 220kV transformer winding obtained by the rapid calculation method for the thermal-fluid coupling field of power equipment in the present invention in the embodiment of the present invention; Figure 8 It is the comparison diagram of the reduced-order model errors of the test set of the temperature field of the 220kV transformer winding obtained by using the BP neural network and the rapid calculation method for the thermal-fluid coupling field of power equipment in the present invention in the embodiment of the present invention; Figure 9This is a comparison chart of the reduced-order model errors of the 220 kV transformer winding velocity field test set obtained by using the BP neural network and the fast calculation method of the thermal-fluid coupling field of the power equipment in the embodiments of the present invention.

[0018] In the figure, 1 - oil duct inlet, 2 - first oil duct outlet, 3 - second oil duct outlet, 4 - medium-voltage winding, 5 - high-voltage winding, 6 - baffle, 7 - transformer oil. Detailed implementation manners

[0019] To enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0020] The fast calculation method of the thermal-fluid coupling field of the power equipment of the present invention includes the following steps: Step 1, establish a simulation model of the thermal-fluid coupling field of the power equipment; Step 2, use the finite element or finite volume numerical calculation method for the simulation model of the thermal-fluid coupling field of the power equipment established in Step 1 to calculate and obtain the simulation results of the thermal-fluid coupling field of the power equipment corresponding to multiple different working conditions; wherein, the simulation results of the thermal-fluid coupling field of the power equipment are temperature or flow velocity; the data of the multiple different working conditions are obtained by the Latin hypercube sampling method; Step 3, construct a sample set through the simulation results of the thermal-fluid coupling field of the power equipment obtained in Step 2, and the sample set is a sample matrix; Step 4, perform POD decomposition (i.e., proper orthogonal decomposition) on the sample set to obtain the characteristic coefficients and orthogonal basis vectors of the sample set corresponding to different working conditions; Step 5, construct a KAN neural network surrogate model with the working conditions as the input and the characteristic coefficients as the output. Through the KAN neural network surrogate model, the mapping relationship between the working conditions and the characteristic coefficients can be obtained; train the constructed KAN neural network surrogate model to obtain a trained KAN neural network surrogate model; Step 6, input the unknown working conditions into the trained KAN neural network surrogate model in Step 5 to obtain the characteristic coefficients corresponding to the unknown working conditions, Step 7, use the characteristic coefficients corresponding to the unknown working conditions obtained in Step 6 and the orthogonal basis vectors obtained in Step 4 to calculate the thermal-fluid coupling field of the power equipment corresponding to the unknown working conditions. The specific calculation process is as follows: Multiply the characteristic coefficients corresponding to the unknown working conditions obtained in Step 6 by the orthogonal basis vectors obtained in Step 4, and then add the result of the multiplication to the average value of the sample set constructed in Step 3, that is, the thermal-fluid coupling field of the power equipment corresponding to the unknown working conditions is obtained.

[0021] In the above solution of the present invention, when the simulation result of the thermal-fluid coupling field of the power equipment is temperature, taking the operating conditions as the input and the characteristic coefficients as the output, when constructing the KAN neural network surrogate model, the number of neurons in the output layer of the KAN neural network surrogate model is the same as the dimension of the characteristic coefficients corresponding to the temperature; When the simulation result of the thermal-fluid coupling field of the power equipment is flow velocity, taking the operating conditions as the input and the characteristic coefficients as the output, when constructing the KAN neural network surrogate model, the number of neurons in the output layer of the KAN neural network surrogate model is the same as the dimension of the characteristic coefficients corresponding to the flow velocity.

[0022] In the above solution of the present invention, the power equipment may be a transformer winding, a transformer bushing, GIS or GIL; When the power equipment is a transformer winding, the operating conditions include the temperature at the oil duct inlet, the flow velocity at the oil duct inlet, and the heat source density of the winding; When the power equipment is a transformer bushing, GIS or GIL, the operating conditions include the current of the central current-carrying conductor and the ambient temperature.

[0023] Embodiment 1 In this embodiment, the above method is used to quickly calculate the thermal-fluid coupling field of a 220 kV transformer winding, including the following steps: Step 1): Use CAD software to establish a thermal two-dimensional finite element analysis model of a 220 kV transformer, and mesh the thermal two-dimensional finite element analysis model. The thermal two-dimensional finite element analysis model mesh has a total of 289,415 nodes and 246,955 elements, as Figure 1 shown; set the thermal performance parameters of the materials required for the calculation for the thermal two-dimensional finite element analysis model, where the thermal performance parameters include the thermal conductivity and the convective heat transfer coefficient.

[0024] Step 2): Set the constraint conditions required for the calculation. Since the 220 kV transformer winding is an oil natural circulation structure, the oil flow inside the winding completely depends on the natural convection generated by the combined action of fluid thermal expansion and contraction and gravity. In the thermal two-dimensional finite element analysis model of the 220 kV transformer winding, set the flow velocity boundary and the pressure boundary at the oil duct inlet 1 and the oil duct outlets (including the first oil duct outlet 2 and the second oil duct outlet 3) respectively, and set the fluid outer boundary except the oil duct inlet 1, the first oil duct outlet 2 and the second oil duct outlet 3 to be adiabatic, to obtain a thermal-fluid coupling field simulation model of the 220 kV transformer winding for calculation.

[0025] Step 3): Adopt the Latin hypercube sampling method to select the four most significant factors affecting the winding temperature, namely the oil temperature at the oil duct inlet 1 of the 220 kV transformer winding, the oil flow velocity at the oil duct inlet 1, the heat source density of the high-voltage winding 5, and the heat source density of the medium-voltage winding 4, to form a sample space. Generate 100 sets of training data and 30 sets of test data.

[0026] Step 4): Use the simulation software Fluent to perform simulation calculations on the above 100 groups of training data to obtain 100 groups of temperature field result data and flow velocity field result data of the 220 kV transformer winding. Form a temperature snapshot matrix and a flow velocity field snapshot matrix based on the temperature field result data and the flow velocity field result data respectively. Perform POD decomposition on the temperature snapshot matrix and the flow velocity field snapshot matrix respectively to obtain the corresponding eigenvalues and contribution rates, as Figure 2 and Figure 3 shown.

[0027] Step 5): Input the 100 groups of working conditions obtained by simulation into the KAN neural network surrogate model. The output of the KAN neural network surrogate model is the characteristic coefficients corresponding to different groups of working conditions. Through training and learning, based on the KAN neural network surrogate model, establish a mapping relationship between different construction working conditions and characteristic coefficients. The training times of the KAN neural network surrogate model are all 10,000 epochs (i.e., 10,000 times), and set the batch size (i.e., batch size) to 32 and the Adam optimizer. After training, obtain the trained KAN neural network surrogate model.

[0028] Step 6): Under the working conditions (i.e., the temperature at the inlet of oil duct 1 T in = 323.1 K, the flow velocity at the inlet of oil duct 1 v = 0.127 m / s, the power of the high-voltage winding 5 Q h = 155,120 W / m 3 , the power of the medium-voltage winding 4 Q m = 91,191 W / m 3 ), use the trained KAN neural network surrogate model in Step 5) to predict the temperature field distribution and flow velocity field distribution of the 220 kV transformer winding respectively.

[0029] It can be seen from Figures 4 to 7 that the predicted temperature results (fast calculation) near the 220 kV transformer winding using the KAN neural network surrogate model of the present invention and the temperature results of the finite element simulation calculation are both between 314 K and 335 K, and the flow velocity field results are both between 0 m / s and 0.165 m / s. The physical field distributions are basically the same, and the errors are mainly concentrated near the outlet 2 of the first oil duct of the winding. From Figure 8 and Figure 9It can be seen that the average relative error of the temperature field predicted by the BP neural network is mostly between 0.5% and 1.1%, and the maximum absolute error is mostly between 0.1 K and 1.2 K. While for the temperature field predicted by the KAN neural network surrogate model of the present invention, the average relative error is mostly between 0.48% and 0.9%, and the maximum absolute error is mostly between 0.1 K and 0.4 K. The average relative error of the flow velocity field predicted by the BP neural network is mostly between 2% and 7.5%, and the maximum absolute error is mostly between 0.0002 m / s and 0.00125 m / s. While for the temperature field predicted by the KAN neural network surrogate model of the present invention, the average relative error is mostly between 2% and 7%, and the maximum absolute error is mostly between 0.0001 m / s and 0.0004 m / s. It can be seen that the prediction errors of the temperature field and flow velocity field of the KAN neural network surrogate model of the present invention are overall smaller than those of the BP neural network, verifying the rationality and accuracy of the fast calculation method for the thermal-fluid coupling field of power equipment based on the KAN neural network surrogate model of the present invention.

[0030] In addition, the embodiment of the present invention also provides a system for implementing the above-mentioned fast calculation method for the thermal-fluid coupling field of power equipment, and the system includes: Data acquisition module: used to acquire unknown working conditions; First calculation module: used to process the unknown working conditions by using the trained KAN neural network surrogate model to obtain the characteristic coefficients corresponding to the unknown working conditions; Second calculation module: used to calculate the thermal-fluid coupling field of the power equipment corresponding to the unknown working conditions by using the calculated orthogonal basis vectors and the characteristic coefficients corresponding to the unknown working conditions; wherein, the calculation process of the orthogonal basis vectors includes: establishing a simulation model for the thermal-fluid coupling field of the power equipment; using the simulation model for the thermal-fluid coupling field of the power equipment to calculate the simulation results of the thermal-fluid coupling field of the power equipment corresponding to different working conditions; constructing a sample set through the simulation results of the thermal-fluid coupling field of the power equipment; performing proper orthogonal decomposition on the sample set to obtain the characteristic coefficients and orthogonal basis vectors of the sample set corresponding to different working conditions.

[0031] The embodiment of the present invention also provides a corresponding electronic device and a computer-readable storage medium for implementing the solution provided by the embodiment of the present invention.

[0032] Wherein, the device includes a memory and a processor, the memory is used to store instructions or codes, and the processor is used to execute the instructions or codes so that the device executes the fast calculation method for the thermal-fluid coupling field of power equipment according to any embodiment of the present application.

[0033] The computer program is stored on the storage medium, wherein the computer program, when executed by the processor, implements the fast calculation method for the thermal-fluid coupling field of power equipment according to any embodiment of the present application.

[0034] Obviously, the described embodiments are only partial embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0035] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that it is still possible to modify the specific implementation manners of the present invention or make equivalent replacements. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A rapid calculation method for the thermal-fluid coupling field of power equipment, characterized in that, It includes the following processes: Obtain unknown operating conditions; Use the trained KAN neural network surrogate model to process the unknown operating conditions to obtain the characteristic coefficients corresponding to the unknown operating conditions; Use the calculated orthogonal basis vectors and the characteristic coefficients corresponding to the unknown operating conditions to calculate the heat-fluid coupling field of the power equipment corresponding to the unknown operating conditions; wherein, the calculation process of the orthogonal basis vectors includes: establishing a heat-fluid coupling field simulation model of the power equipment; using the heat-fluid coupling field simulation model of the power equipment to calculate the heat-fluid coupling field simulation results corresponding to different operating conditions; constructing a sample set through the heat-fluid coupling field simulation results; performing proper orthogonal decomposition on the sample set to obtain the characteristic coefficients of the sample set corresponding to different operating conditions and the orthogonal basis vectors.

2. The rapid calculation method of the thermal-fluid coupling field of the power equipment according to claim 1, wherein The heat-fluid coupling field simulation result of the power equipment is temperature or flow velocity.

3. The rapid calculation method of the thermal-fluid coupling field of the power equipment according to claim 2, characterized in that The input of the KAN neural network surrogate model is the operating condition, and the output is the characteristic coefficient; When the heat-fluid coupling field simulation result of the power equipment is temperature, the number of neurons in the output layer of the KAN neural network surrogate model is the same as the dimension of the characteristic coefficient corresponding to the temperature; When the heat-fluid coupling field simulation result of the power equipment is flow velocity, the number of neurons in the output layer of the KAN neural network surrogate model is the same as the dimension of the characteristic coefficient corresponding to the flow velocity.

4. The rapid calculation method of the thermal-fluid coupling field of the power equipment according to claim 2, characterized in that The step of using the heat-fluid coupling field simulation model of the power equipment to calculate the heat-fluid coupling field simulation results corresponding to different operating conditions includes: Use the finite element numerical calculation method or the finite volume numerical calculation method for the heat-fluid coupling field simulation model of the power equipment to calculate the heat-fluid coupling field simulation results corresponding to different operating conditions.

5. The rapid calculation method for the thermal-fluid coupling field of the power equipment according to claim 1, wherein The step of using the calculated orthogonal basis vectors and the characteristic coefficients corresponding to the unknown operating conditions to calculate the heat-fluid coupling field of the power equipment corresponding to the unknown operating conditions includes: Multiply the characteristic coefficients corresponding to the unknown operating conditions by the orthogonal basis vectors, and then add the average value of the sample set to obtain the heat-fluid coupling field of the power equipment corresponding to the unknown operating conditions.

6. The rapid calculation method for the thermal-fluid coupling field of the power equipment according to claim 1, wherein The power equipment is a transformer winding, a transformer bushing, a gas-insulated switchgear or a gas-insulated transmission line.

7. The rapid calculation method of the heat-fluid coupling field of the power equipment according to claim 6, characterized in that: When the power equipment is a transformer winding, the operating conditions include the temperature at the oil duct inlet, the flow velocity at the oil duct inlet, and the heat source density of the winding; When the power equipment is a transformer bushing, a gas-insulated switchgear or a gas-insulated transmission line, the operating conditions include the current of the central current-carrying conductor and the ambient temperature.

8. A fast calculation system for the thermal-fluid coupling field of power equipment, characterized in that, It includes: Data acquisition module: used to obtain unknown operating conditions; First calculation module: used to use the trained KAN neural network surrogate model to process the unknown operating conditions to obtain the characteristic coefficients corresponding to the unknown operating conditions; Second calculation module: configured to calculate the heat-fluid coupling field of the power equipment corresponding to unknown operating conditions by using the calculated orthogonal basis vectors and the characteristic coefficients corresponding to the unknown operating conditions; wherein, the calculation process of the orthogonal basis vectors includes: establishing a simulation model of the heat-fluid coupling field of the power equipment; using the simulation model of the heat-fluid coupling field of the power equipment to calculate the simulation results of the heat-fluid coupling field of the power equipment corresponding to different operating conditions; constructing a sample set through the simulation results of the heat-fluid coupling field of the power equipment; performing proper orthogonal decomposition on the sample set to obtain the characteristic coefficients of the sample set corresponding to different operating conditions and the orthogonal basis vectors.

9. An electronic device, characterized in that, Comprising: One or more processors; A storage device having stored thereon one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method for quickly calculating the heat-fluid coupling field of the power equipment according to any one of claims 1-7.

10. A storage medium, characterized in that, Having stored thereon a computer program, wherein when the computer program is executed by a processor, the method for quickly calculating the heat-fluid coupling field of the power equipment according to any one of claims 1-7 is implemented.

Images