Method and device for determining temperature field of transformer winding

Abstract

The invention relates to the technical field of power equipment simulation analysis, and particularly provides a transformer winding temperature field determination method and device, and the method comprises the steps: obtaining the perception data of a transformer; taking the sensing data of the transformer as input of a pre-trained neural network model to obtain a transformer winding temperature field output by the pre-trained neural network model; wherein the sensing data comprises load current, environment temperature, temperature of the oil flow inlet and flow velocity of the oil flow inlet. According to the technical scheme provided by the invention, rapid calculation of the transformer winding temperature field considering real-time sensing data access can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment simulation analysis, and in particular to a method and device for determining a transformer winding temperature field. Background Art

[0002] The application of artificial intelligence and digital twin technology in intelligent auxiliary decision-making and regulation of power grids has attracted much attention, and has put forward the demand for panoramic state perception and dynamic and flexible adjustment of power equipment. At present, the exploration of digitalization of power equipment has been carried out, and the state representation of high-fidelity digital twins has been achieved through multi-physical field simulation of equipment.

[0003] However, due to problems such as insulation and sealing of power equipment, the internal state of the equipment can only be obtained through indirect sensing methods such as external temperature, vibration, and current, and there is no one-to-one correspondence between the internal state of the equipment and the sensed quantity. Through multi-physical field simulation analysis, adjusting the parameters of the simulation model using measured data is an effective means to improve the accuracy of the model, but the physical field simulation numerical calculation usually takes several hours to complete a transient analysis, which cannot support real-time analysis of the internal state of the equipment. Therefore, it is necessary to study the fast calculation method of the internal physical field of the equipment, provide a data interface between the sensor data and the numerical simulation, and realize the real-time perception and prediction of the internal state of the equipment. Summary of the invention

[0004] In order to overcome the above defects, the present invention proposes a method and device for determining the temperature field of a transformer winding.

[0005] In a first aspect, a method for determining a transformer winding temperature field is provided, the method comprising:

[0006] Get the transformer's perception data;

[0007] Using the sensed data of the transformer as an input of a pre-trained neural network model to obtain a transformer winding temperature field output by the pre-trained neural network model;

[0008] The sensing data includes: load current, ambient temperature, temperature of the oil inlet, and flow rate of the oil inlet.

[0009] Preferably, the training process of the pre-trained neural network model includes:

[0010] Obtain transformer perception data and temperature field data in different scenarios;

[0011] Use the transformer perception data and temperature field data in different scenarios to build training sample data;

[0012] The initial neural network model is trained using the training sample data to obtain the pre-trained neural network model.

[0013] Furthermore, the acquisition of the transformer sensing data and temperature field data at the sampling time includes:

[0014] Construct an electromagnetic heat-flow coupling simulation model for transformer windings;

[0015] The Latin hypercube sampling method is used to sample the transformer's perception data set to obtain multiple groups of perception data, where each group of perception data is regarded as a scene;

[0016] Each group of sensing data is used as a sampling point for finite element calculation to perform finite element calculation on the electromagnetic heat flow coupling simulation model of the transformer winding, so as to obtain the transformer winding temperature field data under different scenarios.

[0017] Furthermore, the transformer winding temperature field data satisfies the following constraints:

[0018]

[0019] In the above formula, r is the medium density, c is the volume specific heat capacity, T is the transformer winding temperature field, τ is the temperature gradient, r is the r-axis coordinate of the transformer in the cylindrical coordinate system, λ is the heat transfer coefficient, z is the z-axis coordinate of the transformer in the cylindrical coordinate system, and q v It is the amount of heat dissipated by a unit volume of heat transfer medium per unit time.

[0020] Furthermore, in the process of sampling the transformer's perception data using the Latin hypercube sampling method, the j-th dimension component of the i-th sample point is as follows:

[0021]

[0022] In the above formula, is the j-th dimension component of the i-th sample point, is a random permutation of integers 1 to n, is a uniform random distribution in the range of [0,1], n is the total number of preset sampling points in each dimension, and d is the perception data dimension of the transformer.

[0023] Furthermore, in the process of training the initial neural network model using the training sample data, the validity of the pre-trained neural network model is judged using the root mean square error, wherein the root mean square error is as follows:

[0024]

[0025] In the above formula, RMSE is the root mean square error, s is the number of test samples in the training sample, is the transformer winding temperature field predicted by the pre-trained neural network model for the i-th test sample, is the transformer winding temperature field in the i-th test sample, max T FEM is the maximum transformer winding temperature, min T FEM is the minimum temperature of the transformer winding.

[0026] Furthermore, in the process of training the initial neural network model using the training sample data, the maximum error is used to judge the validity of the pre-trained neural network model, wherein the maximum error is as follows:

[0027]

[0028] In the above formula, L ∞ is the maximum error, T ROM is the transformer winding temperature field predicted by the pre-trained neural network model, T FEM is the transformer winding temperature field in the test sample, max T FEM is the maximum transformer winding temperature, min T FEM is the minimum temperature of the transformer winding.

[0029] In a second aspect, a device for determining a transformer winding temperature field is provided, the device for determining a transformer winding temperature field comprising:

[0030] An acquisition module is used to obtain the perception data of the transformer;

[0031] An analysis module, used to use the sensing data of the transformer as an input of a pre-trained neural network model to obtain a transformer winding temperature field output by the pre-trained neural network model;

[0032] The sensing data includes: load current, ambient temperature, temperature of the oil inlet, and flow rate of the oil inlet.

[0033] Preferably, the training process of the pre-trained neural network model includes:

[0034] Obtain transformer perception data and temperature field data in different scenarios;

[0035] Use the transformer perception data and temperature field data in different scenarios to build training sample data;

[0036] The initial neural network model is trained using the training sample data to obtain the pre-trained neural network model.

[0037] Furthermore, the acquisition of the transformer sensing data and temperature field data at the sampling time includes:

[0038] Construct an electromagnetic heat-flow coupling simulation model for transformer windings;

[0039] A Latin hypercube sampling device is used to sample the transformer's perception data set to obtain multiple groups of perception data, where each group of perception data is regarded as a scene;

[0040] Each group of sensing data is used as a sampling point for finite element calculation to perform finite element calculation on the electromagnetic heat flow coupling simulation model of the transformer winding, so as to obtain the transformer winding temperature field data under different scenarios.

[0041] Furthermore, the transformer winding temperature field data satisfies the following constraints:

[0042]

[0043] In the above formula, r is the medium density, c is the volume specific heat capacity, T is the transformer winding temperature field, τ is the temperature gradient, r is the r-axis coordinate of the transformer in the cylindrical coordinate system, λ is the heat transfer coefficient, z is the z-axis coordinate of the transformer in the cylindrical coordinate system, and q v It is the amount of heat dissipated by a unit volume of heat transfer medium per unit time.

[0044] Furthermore, in the process of sampling the transformer's perception data using the Latin hypercube sampling device, the j-th dimension component of the i-th sample point is as follows:

[0045]

[0046] In the above formula, is the j-th dimension component of the i-th sample point, is a random permutation of integers 1 to n, is a uniform random distribution in the range of [0,1], n is the total number of preset sampling points in each dimension, and d is the perception data dimension of the transformer.

[0047] Furthermore, in the process of training the initial neural network model using the training sample data, the validity of the pre-trained neural network model is judged using the root mean square error, wherein the root mean square error is as follows:

[0048]

[0049] In the above formula, RMSE is the root mean square error, s is the number of test samples in the training sample, is the transformer winding temperature field predicted by the pre-trained neural network model for the i-th test sample, is the transformer winding temperature field in the i-th test sample, max T FEM is the maximum transformer winding temperature, min TFEM is the minimum temperature of the transformer winding.

[0050] Furthermore, in the process of training the initial neural network model using the training sample data, the maximum error is used to judge the validity of the pre-trained neural network model, wherein the maximum error is as follows:

[0051]

[0052] In the above formula, L ∞ is the maximum error, T ROM is the transformer winding temperature field predicted by the pre-trained neural network model, T FEM is the transformer winding temperature field in the test sample, max T FEM is the maximum transformer winding temperature, min T FEM is the minimum temperature of the transformer winding.

[0053] In a third aspect, a computer device is provided, comprising: one or more processors;

[0054] The processor is configured to execute one or more programs;

[0055] When the one or more programs are executed by the one or more processors, the transformer winding temperature field determination method is implemented.

[0056] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed, the method for determining the temperature field of the transformer winding is implemented.

[0057] The above one or more technical solutions of the present invention have at least one or more of the following beneficial effects:

[0058] The present invention provides a method and device for determining the temperature field of a transformer winding, comprising: obtaining the sensory data of the transformer; using the sensory data of the transformer as the input of a pre-trained neural network model to obtain the transformer winding temperature field output by the pre-trained neural network model; wherein the sensory data includes: load current, ambient temperature, temperature of the oil inlet, and flow rate of the oil inlet. The technical solution provided by the present invention can realize the real-time and rapid solution of the transformer winding temperature under different working conditions, and explores a new technical method for predictive maintenance of power equipment such as transformers. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 1 is a schematic flow chart of the main steps of a method for determining a transformer winding temperature field according to an embodiment of the present invention;

[0060] Figure 2It is a schematic diagram of an electromagnetic heat flow coupling simulation model of a transformer winding according to an embodiment of the present invention. DETAILED DESCRIPTION

[0061] The specific implementation modes of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0062] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] As disclosed in the background technology, the application of artificial intelligence and digital twin technology in intelligent auxiliary decision-making and regulation of power grids has attracted much attention, and has put forward the demand for panoramic state perception and dynamic and flexible adjustment of power equipment. At present, the exploration of digitalization of power equipment has been carried out, and the state representation of high-fidelity digital twins has been achieved through multi-physical field simulation of equipment.

[0064] However, due to problems such as insulation and sealing of power equipment, the internal state of the equipment can only be obtained through indirect sensing methods such as external temperature, vibration, and current, and there is no one-to-one correspondence between the internal state of the equipment and the sensed quantity. Through multi-physical field simulation analysis, adjusting the parameters of the simulation model using measured data is an effective means to improve the accuracy of the model, but the physical field simulation numerical calculation usually takes several hours to complete a transient analysis, which cannot support real-time analysis of the internal state of the equipment. Therefore, it is necessary to study the fast calculation method of the internal physical field of the equipment, provide a data interface between the sensor data and the numerical simulation, and realize the real-time perception and prediction of the internal state of the equipment.

[0065] In order to improve the above-mentioned problems, the present invention provides a method and device for determining the temperature field of a transformer winding, including: obtaining the sensory data of the transformer; using the sensory data of the transformer as the input of a pre-trained neural network model to obtain the transformer winding temperature field output by the pre-trained neural network model; wherein the sensory data includes: load current, ambient temperature, temperature of the oil inlet, and flow rate of the oil inlet. The technical solution provided by the present invention can realize the real-time and rapid solution of the transformer winding temperature under different working conditions, and explores new technical methods for the predictive maintenance of power equipment such as transformers. The above-mentioned solution is elaborated in detail below.

[0066] Example 1

[0067] See attached Figure 1 , Figure 1FIG. 1 is a flow chart showing the main steps of a method for determining a transformer winding temperature field according to an embodiment of the present invention. Figure 1 As shown, the method for determining the transformer winding temperature field in the embodiment of the present invention mainly includes the following steps:

[0068] Step S101: obtaining the sensing data of the transformer;

[0069] Step S102: using the sensing data of the transformer as an input of a pre-trained neural network model to obtain a transformer winding temperature field output by the pre-trained neural network model;

[0070] The sensing data includes: load current, ambient temperature, temperature of the oil inlet, and flow rate of the oil inlet.

[0071] In this embodiment, the training process of the pre-trained neural network model includes:

[0072] Obtain transformer perception data and temperature field data in different scenarios;

[0073] Use the transformer perception data and temperature field data in different scenarios to build training sample data;

[0074] The initial neural network model is trained using the training sample data to obtain the pre-trained neural network model.

[0075] In one embodiment, the step of obtaining the transformer sensing data and temperature field data at the sampling time includes:

[0076] Construct an electromagnetic thermal flow coupling simulation model of the transformer winding, such as Figure 2 As shown;

[0077] The Latin hypercube sampling method is used to sample the transformer's perception data set to obtain multiple groups of perception data, where each group of perception data is regarded as a scene;

[0078] Each group of sensing data is used as a sampling point for finite element calculation to perform finite element calculation on the electromagnetic heat flow coupling simulation model of the transformer winding, so as to obtain the transformer winding temperature field data under different scenarios.

[0079] In one embodiment, the transformer winding temperature field data satisfies the following constraints:

[0080]

[0081] In the above formula, r is the medium density, c is the volume specific heat capacity, T is the transformer winding temperature field, τ is the temperature gradient, r is the r-axis coordinate of the transformer in the cylindrical coordinate system, λ is the heat transfer coefficient, z is the z-axis coordinate of the transformer in the cylindrical coordinate system, and q vIt is the amount of heat dissipated by a unit volume of heat transfer medium per unit time.

[0082] In one embodiment, in the process of sampling the sensory data of the transformer using the Latin hypercube sampling method, the j-th dimension component of the i-th sample point is as follows:

[0083]

[0084] In the above formula, is the j-th dimension component of the i-th sample point, is a random permutation of integers 1 to n, is a uniform random distribution in the range of [0,1], n is the total number of preset sampling points in each dimension, and d is the perception data dimension of the transformer.

[0085] In one embodiment, in the process of training the initial neural network model using the training sample data, the validity of the pre-trained neural network model is judged using the root mean square error, wherein the root mean square error is as follows:

[0086]

[0087] In the above formula, RMSE is the root mean square error, s is the number of test samples in the training sample, is the transformer winding temperature field predicted by the pre-trained neural network model for the i-th test sample, is the transformer winding temperature field in the i-th test sample, max T FEM is the maximum transformer winding temperature, min T FEM is the minimum temperature of the transformer winding.

[0088] In one embodiment, in the process of training the initial neural network model using the training sample data, the validity of the pre-trained neural network model is judged using the maximum error, wherein the maximum error is as follows:

[0089]

[0090] In the above formula, L ∞ is the maximum error, T ROM is the transformer winding temperature field predicted by the pre-trained neural network model, T FEM is the transformer winding temperature field in the test sample, max T FEM is the maximum transformer winding temperature, min T FEM is the minimum temperature of the transformer winding.

[0091] Example 2

[0092] Based on the same inventive concept, the present invention also provides a transformer winding temperature field determination device, the transformer winding temperature field determination device comprising:

[0093] An acquisition module is used to obtain the perception data of the transformer;

[0094] An analysis module, used to use the sensing data of the transformer as an input of a pre-trained neural network model to obtain a transformer winding temperature field output by the pre-trained neural network model;

[0095] The sensing data includes: load current, ambient temperature, temperature of the oil inlet, and flow rate of the oil inlet.

[0096] Preferably, the training process of the pre-trained neural network model includes:

[0097] Obtain transformer perception data and temperature field data in different scenarios;

[0098] Use the transformer perception data and temperature field data in different scenarios to build training sample data;

[0099] The initial neural network model is trained using the training sample data to obtain the pre-trained neural network model.

[0100] Furthermore, the acquisition of the transformer sensing data and temperature field data at the sampling time includes:

[0101] Construct an electromagnetic heat-flow coupling simulation model for transformer windings;

[0102] A Latin hypercube sampling device is used to sample the transformer's perception data set to obtain multiple groups of perception data, where each group of perception data is regarded as a scene;

[0103] Each group of sensing data is used as a sampling point for finite element calculation to perform finite element calculation on the electromagnetic heat flow coupling simulation model of the transformer winding, so as to obtain the transformer winding temperature field data under different scenarios.

[0104] Furthermore, the transformer winding temperature field data satisfies the following constraints:

[0105]

[0106] In the above formula, r is the medium density, c is the volume specific heat capacity, T is the transformer winding temperature field, τ is the temperature gradient, r is the r-axis coordinate of the transformer in the cylindrical coordinate system, λ is the heat transfer coefficient, z is the z-axis coordinate of the transformer in the cylindrical coordinate system, and q v It is the amount of heat dissipated by a unit volume of heat transfer medium per unit time.

[0107] Furthermore, in the process of sampling the transformer's perception data using the Latin hypercube sampling device, the j-th dimension component of the i-th sample point is as follows:

[0108]

[0109] In the above formula, is the j-th dimension component of the i-th sample point, is a random permutation of integers 1 to n, is a uniform random distribution in the range of [0,1], n is the total number of preset sampling points in each dimension, and d is the perception data dimension of the transformer.

[0110] Furthermore, in the process of training the initial neural network model using the training sample data, the validity of the pre-trained neural network model is judged using the root mean square error, wherein the root mean square error is as follows:

[0111]

[0112] In the above formula, RMSE is the root mean square error, s is the number of test samples in the training sample, is the transformer winding temperature field predicted by the pre-trained neural network model for the i-th test sample, is the transformer winding temperature field in the i-th test sample, max T FEM is the maximum transformer winding temperature, min T FEM is the minimum temperature of the transformer winding.

[0113] Furthermore, in the process of training the initial neural network model using the training sample data, the maximum error is used to judge the validity of the pre-trained neural network model, wherein the maximum error is as follows:

[0114]

[0115] In the above formula, L ∞ is the maximum error, T ROM is the transformer winding temperature field predicted by the pre-trained neural network model, T FEM is the transformer winding temperature field in the test sample, max T FEM is the maximum transformer winding temperature, min T FEM is the minimum temperature of the transformer winding.

[0116] Example 3

[0117] Based on the same inventive concept, the present invention also provides a computer device, which includes a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function, so as to implement the steps of a method for determining the temperature field of a transformer winding in the above embodiment.

[0118] Example 4

[0119] Based on the same inventive concept, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It can be understood that the computer-readable storage medium here can include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the steps of a method for determining a transformer winding temperature field in the above embodiment.

[0120] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0121] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0122] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0123] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0124] 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 it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for determining a transformer winding temperature field, characterized in that: The method comprises: Get the transformer's perception data; Using the sensed data of the transformer as an input of a pre-trained neural network model to obtain a transformer winding temperature field output by the pre-trained neural network model; The sensing data includes: load current, ambient temperature, temperature of the oil inlet, and flow rate of the oil inlet.

2. The method according to claim 1, characterized in that The training process of the pre-trained neural network model includes: Obtain transformer perception data and temperature field data in different scenarios; Use the transformer perception data and temperature field data in different scenarios to build training sample data; The initial neural network model is trained using the training sample data to obtain the pre-trained neural network model.

3. The method according to claim 2, characterized in that The step of obtaining the transformer sensing data and temperature field data at the sampling moment includes: Construct an electromagnetic heat-flow coupling simulation model for transformer windings; The Latin hypercube sampling method is used to sample the transformer's perception data set to obtain multiple groups of perception data, where each group of perception data is regarded as a scene; Each group of sensing data is used as a sampling point for finite element calculation to perform finite element calculation on the electromagnetic heat flow coupling simulation model of the transformer winding, so as to obtain the transformer winding temperature field data under different scenarios.

4. The method according to claim 3, characterized in that The transformer winding temperature field data meets the following constraints: In the above formula, r is the medium density, c is the volume specific heat capacity, T is the transformer winding temperature field, τ is the temperature gradient, r is the r-axis coordinate of the transformer in the cylindrical coordinate system, λ is the heat transfer coefficient, z is the z-axis coordinate of the transformer in the cylindrical coordinate system, and q v It is the amount of heat dissipated by a unit volume of heat transfer medium per unit time.

5. The method according to claim 3, characterized in that In the process of sampling the transformer's perception data using the Latin hypercube sampling method, the j-th dimension component of the i-th sample point is as follows: In the above formula, is the j-th dimension component of the i-th sample point, is a random permutation of integers 1 to n, is a uniform random distribution in the range of [0,1], n is the total number of preset sampling points in each dimension, and d is the perception data dimension of the transformer.

6. The method according to claim 3, characterized in that In the process of training the initial neural network model using the training sample data, the effectiveness of the pre-trained neural network model is judged using the root mean square error, wherein the root mean square error is as follows: In the above formula, RMSE is the root mean square error, s is the number of test samples in the training sample, T ROMi is the transformer winding temperature field predicted by the pre-trained neural network model for the i-th test sample, T FEMi is the transformer winding temperature field in the i-th test sample, maxT FEM is the maximum transformer winding temperature, minT FEM is the minimum temperature of the transformer winding.

7. The method according to claim 3, characterized in that In the process of training the initial neural network model using the training sample data, the validity of the pre-trained neural network model is judged using the maximum error, wherein the maximum error is as follows: In the above formula, L ∞ is the maximum error, T ROM is the transformer winding temperature field predicted by the pre-trained neural network model, T FEM is the transformer winding temperature field in the test sample, maxT FEM is the maximum transformer winding temperature, minT FEM is the minimum temperature of the transformer winding.

8. A device for determining the temperature field of a transformer winding, characterized in that: The device comprises: An acquisition module is used to obtain the perception data of the transformer; An analysis module, used to use the sensing data of the transformer as an input of a pre-trained neural network model to obtain a transformer winding temperature field output by the pre-trained neural network model; The sensing data includes: load current, ambient temperature, temperature of the oil inlet, and flow rate of the oil inlet.

9. The device according to claim 8, characterized in that The training process of the pre-trained neural network model includes: Obtain transformer perception data and temperature field data in different scenarios; Use the transformer perception data and temperature field data in different scenarios to build training sample data; The initial neural network model is trained using the training sample data to obtain the pre-trained neural network model.

10. The device according to claim 9, characterized in that The step of obtaining the transformer sensing data and temperature field data at the sampling moment includes: Construct an electromagnetic heat-flow coupling simulation model for transformer windings; A Latin hypercube sampling device is used to sample the transformer's perception data set to obtain multiple groups of perception data, where each group of perception data is regarded as a scene; Each group of sensing data is used as a sampling point for finite element calculation to perform finite element calculation on the electromagnetic heat flow coupling simulation model of the transformer winding, so as to obtain the transformer winding temperature field data under different scenarios.

11. The device according to claim 10, characterized in that The transformer winding temperature field data meets the following constraints: In the above formula, r is the medium density, c is the volume specific heat capacity, T is the transformer winding temperature field, τ is the temperature gradient, r is the r-axis coordinate of the transformer in the cylindrical coordinate system, λ is the heat transfer coefficient, z is the z-axis coordinate of the transformer in the cylindrical coordinate system, and q v It is the amount of heat dissipated by a unit volume of heat transfer medium per unit time.

12. The device according to claim 10, characterized in that In the process of sampling the transformer's perception data using the Latin hypercube sampling device, the j-th dimension component of the i-th sample point is as follows: In the above formula, is the j-th dimension component of the i-th sample point, is a random permutation of integers 1 to n, is a uniform random distribution in the range of [0,1], n is the total number of preset sampling points in each dimension, and d is the perception data dimension of the transformer.

13. The device according to claim 10, characterized in that In the process of training the initial neural network model using the training sample data, the effectiveness of the pre-trained neural network model is judged using the root mean square error, wherein the root mean square error is as follows: In the above formula, RMSE is the root mean square error, s is the number of test samples in the training sample, is the transformer winding temperature field predicted by the pre-trained neural network model for the i-th test sample, is the transformer winding temperature field in the i-th test sample, maxT FEM is the maximum transformer winding temperature, minT FEM is the minimum temperature of the transformer winding.

14. The device according to claim 10, characterized in that In the process of training the initial neural network model using the training sample data, the validity of the pre-trained neural network model is judged using the maximum error, wherein the maximum error is as follows: In the above formula, L ∞ is the maximum error, T ROM is the transformer winding temperature field predicted by the pre-trained neural network model, T FEM is the transformer winding temperature field in the test sample, maxT FEM is the maximum transformer winding temperature, minT FEM is the minimum temperature of the transformer winding.

15. A computer device, characterized in that: include: one or more processors; The processor is configured to execute one or more programs; When the one or more programs are executed by the one or more processors, the transformer winding temperature field determination method according to any one of claims 1 to 7 is implemented.

16. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed, the method for determining the temperature field of a transformer winding as claimed in any one of claims 1 to 7 is implemented.

Images