Transformer thermal field information determination method, device and equipment and storage medium

Abstract

The application relates to a transformer thermal field information determination method, device and equipment and a storage medium, and belongs to the technical field of power equipment. The method comprises the following steps: in response to a transformer thermal field determination request, obtaining a target operation condition of a transformer. The target operation condition is input into a target thermal field determination model to obtain target thermal field information of the transformer under the target operation condition; wherein the target thermal field determination model is obtained by training a neural network model based on the physical structure of the transformer and training samples. According to the application, the target operation condition is only needed to be input into the target thermal field determination model, and the target thermal field information of the transformer under the target operation condition can be obtained. Based on the target thermal field determination model, the thermal field information of the transformer under any operation condition can be obtained, and the thermal field information response speed is relatively fast.

Description

Technical Field

[0001] This application relates to the field of power equipment technology, and in particular to a method, apparatus, device and storage medium for determining thermal field information of a transformer. Background Technology

[0002] Transformers are important equipment in power systems that are responsible for the transmission and conversion of electrical energy. Monitoring their operating status is a necessary guarantee for ensuring the safe and stable operation of the power grid.

[0003] Among all types of transformer faults, the destruction of insulation materials is the main cause of transformer failure, especially in oil-immersed transformers, where the destruction of the oil-paper insulation material is the most common cause of transformer failure.

[0004] Temperature is another important factor affecting the performance of transformer insulation materials. However, due to the complex internal structure of transformers and the large temperature differences within them, there is currently no effective method for determining the internal thermal field of transformers. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, equipment, and storage medium for determining the thermal field information of a transformer, which can accurately determine the thermal field information of the transformer, in response to the above-mentioned technical problems.

[0006] Firstly, this application provides a method for determining the thermal field information of a transformer. The method includes:

[0007] In response to a request to determine the thermal field of the transformer, the target operating conditions of the transformer are obtained.

[0008] The target operating condition is input into the target thermal field determination model to obtain the target thermal field information of the transformer under the target operating condition. The target thermal field determination model is obtained by training a neural network model based on the physical structure of the transformer and training samples. The training samples include the first sample operating condition and the first sample thermal field information corresponding to the first sample operating condition, as well as the second sample operating condition.

[0009] In one embodiment, the neural network model is trained based on the physical structure of the transformer and training samples, including:

[0010] Based on the physical structure of the transformer, the first sample operating condition, and the first sample thermal field information corresponding to the first sample operating condition, a target thermal field simulation model of the transformer is constructed.

[0011] The thermal field information of the transformer under the second sample operating condition was determined by using the target thermal field simulation model.

[0012] Based on the first sample operating condition and the corresponding first sample thermal field information, as well as the second sample operating condition and the corresponding second sample thermal field information, the neural network model is trained to obtain the target thermal field determination model.

[0013] In one embodiment, a target thermal field simulation model of the transformer is constructed based on the transformer's physical structure, a first sample operating condition, and the corresponding first sample thermal field information, including:

[0014] Based on the physical structure of the transformer, construct a physical model of the transformer;

[0015] Based on the physical model, the first sample operating condition, and the first sample thermal field information corresponding to the first sample operating condition, a target thermal field simulation model of the transformer is constructed.

[0016] In one embodiment, a target thermal field simulation model of the transformer is constructed based on the physical model, the first sample operating condition, and the first sample thermal field information corresponding to the first sample operating condition, including:

[0017] The physical model is imported into the finite element analysis software to obtain the finite element model of the transformer;

[0018] Configure constraints for the finite element model; the constraints include heat dissipation conditions and convective heat transfer coefficients.

[0019] The finite element model with configured constraints is meshed to obtain the initial thermal field simulation model of the transformer;

[0020] The initial thermal field simulation model is trained using the first sample operating condition and the corresponding first sample thermal field information to obtain the target thermal field simulation model.

[0021] In one embodiment, the second sample thermal field information of the transformer under the second sample operating condition is determined using a target thermal field simulation model, including:

[0022] The heat loss of the transformer is determined based on the current and / or voltage parameters in the second sample operating conditions.

[0023] Based on heat loss, a heat source is applied to the windings and core in the target thermal field simulation model to obtain the second sample thermal field information of the transformer under the second sample operating condition.

[0024] In one embodiment, a neural network model is trained based on a first sample operating condition and the corresponding first sample thermal field information, and a second sample operating condition and the corresponding second sample thermal field information, to obtain a target thermal field determination model, including:

[0025] Based on the second sample operating conditions and the corresponding second sample thermal field information, the neural network model is trained to obtain the candidate thermal field determination model.

[0026] The first sample operating condition is input into the candidate thermal field determination model to obtain the predicted thermal field information of the transformer under the first sample operating condition;

[0027] If the temperature difference between the predicted thermal field information and the first sample thermal field information is less than the difference threshold, then the candidate thermal field determination model will be used as the target thermal field determination model.

[0028] Secondly, this application also provides a device for determining the thermal field information of a transformer. The device includes:

[0029] The acquisition module is used to acquire the target operating conditions of the transformer in response to a request to determine the thermal field of the transformer.

[0030] The determination module is used to input the target operating condition into the target thermal field determination model to obtain the target thermal field information of the transformer under the target operating condition. The target thermal field determination model is obtained by training a neural network model based on the physical structure of the transformer and training samples. The training samples include the first sample operating condition and the first sample thermal field information corresponding to the first sample operating condition, as well as the second sample operating condition.

[0031] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0032] In response to a request to determine the thermal field of the transformer, the target operating conditions of the transformer are obtained.

[0033] The target operating condition is input into the target thermal field determination model to obtain the target thermal field information of the transformer under the target operating condition. The target thermal field determination model is obtained by training a neural network model based on the physical structure of the transformer and training samples. The training samples include the first sample operating condition and the first sample thermal field information corresponding to the first sample operating condition, as well as the second sample operating condition.

[0034] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0035] In response to a request to determine the thermal field of the transformer, the target operating conditions of the transformer are obtained.

[0036] The target operating condition is input into the target thermal field determination model to obtain the target thermal field information of the transformer under the target operating condition. The target thermal field determination model is obtained by training a neural network model based on the physical structure of the transformer and training samples. The training samples include the first sample operating condition and the first sample thermal field information corresponding to the first sample operating condition, as well as the second sample operating condition.

[0037] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0038] In response to a request to determine the thermal field of the transformer, the target operating conditions of the transformer are obtained.

[0039] The target operating condition is input into the target thermal field determination model to obtain the target thermal field information of the transformer under the target operating condition. The target thermal field determination model is obtained by training a neural network model based on the physical structure of the transformer and training samples. The training samples include the first sample operating condition and the first sample thermal field information corresponding to the first sample operating condition, as well as the second sample operating condition.

[0040] The aforementioned method, apparatus, equipment, and storage medium for determining the thermal field information of a transformer, in response to a request for thermal field determination of the transformer, acquires the target operating condition of the transformer; inputs the target operating condition into a target thermal field determination model to obtain the target thermal field information of the transformer under the target operating condition; wherein, the target thermal field determination model is obtained by training a neural network model based on the physical structure of the transformer and training samples; the training samples include a first sample operating condition and the corresponding first sample thermal field information, as well as a second sample operating condition. This application can train a neural network model to obtain the target thermal field determination model based on the first sample operating condition and the corresponding first sample thermal field information, as well as the second sample operating condition. Only the target operating condition needs to be input into the target thermal field determination model to obtain the target thermal field information of the transformer under the target operating condition. Based on the target thermal field determination model, not only can the thermal field information of the transformer under any operating condition be obtained, but it also has a fast thermal field information response speed. Based on the thermal field information, the temperature information at any location inside the transformer can be clearly identified, which can be used to realize temperature early warning of the transformer, reduce the failure rate of the transformer, and extend the service life of the transformer. Attached Figure Description

[0041] Figure 1 This is a diagram illustrating the application environment of the method for determining the thermal field information of a transformer provided in this embodiment.

[0042] Figure 2 This is a flowchart illustrating the first method for determining the thermal field information of a transformer provided in this embodiment;

[0043] Figure 3 This is a schematic diagram of the first method for constructing a target thermal field determination model provided in this embodiment;

[0044] Figure 4 This is a schematic diagram of the process for obtaining the thermal field information of the second sample provided in this embodiment;

[0045] Figure 5 This is a schematic diagram of the second method for constructing a target thermal field determination model provided in this embodiment;

[0046] Figure 6 This is a flowchart illustrating the second method for determining the thermal field information of a transformer provided in this embodiment;

[0047] Figure 7 This embodiment provides a structural block diagram of a transformer thermal field information determination device.

[0048] Figure 8 This is an internal structural diagram of the computer device provided in this embodiment. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0050] In one embodiment, a computer device is provided, which may be a server, a computer, or an industrial control computer, and its internal structure diagram may be as follows. Figure 1 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores data for acquiring abnormal data. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a method for determining the thermal field information of a transformer.

[0051] In one embodiment, a method for determining the thermal field information of a transformer is provided, such as... Figure 2 As shown, it includes the following steps:

[0052] S201, in response to the request to determine the thermal field of the transformer, obtains the target operating conditions of the transformer.

[0053] Here, thermal field refers to the distribution of heat energy and temperature. A thermal field determination request is a request to obtain the thermal field information (i.e., temperature distribution information) of the transformer. The target operating condition refers to the operating condition corresponding to the thermal field information to be queried. The operating condition may include at least one of the following: current, voltage, and environmental parameters; it may also include the operating condition under no-load conditions.

[0054] An optional implementation of this embodiment is as follows: In response to a request to determine the thermal field of the transformer, a target operating condition acquisition request is sent to relevant equipment, so that the relevant equipment can provide feedback on the target operating condition, thereby acquiring the target operating condition of the transformer. The relevant equipment may be devices that receive and store parameters corresponding to the target operating condition.

[0055] Another optional implementation of this embodiment is as follows: In response to a request to determine the thermal field of the transformer, the target operating condition of the transformer is obtained directly or indirectly from the feedback of the detection device. The detection device can be a sensor, such as a current sensor, a voltage sensor, an environmental sensing sensor (e.g., a temperature sensor), etc.

[0056] S202, the target operating condition is input into the target thermal field determination model to obtain the target thermal field information of the transformer under the target operating condition. The target thermal field determination model is obtained by training a neural network model based on the transformer's physical structure and training samples. The training samples include a first sample operating condition and the corresponding first sample thermal field information, as well as a second sample operating condition.

[0057] The target thermal field information refers to the temperature distribution information inside the transformer corresponding to the target operating condition. The target thermal field determination model is a neural network model trained based on the transformer's physical structure and training samples. Training samples are the sample set used to train the neural network model, mainly including the first sample operating condition and its corresponding first sample thermal field information, as well as the second sample operating condition. The first and second sample operating conditions refer to the set of operating condition samples used as input parameters when training the neural network model. It should be noted that the first sample operating condition has corresponding first sample thermal field information. The first sample thermal field information refers to the sample set of real thermal field information corresponding to the first sample operating condition, mainly used for verification and convergence during the neural network model training process. The second sample operating condition does not have corresponding real sample thermal field information. The neural network model uses, but is not limited to, a CNN neural network model.

[0058] One optional implementation method of this embodiment is to directly input the target operating condition into the target thermal field determination model to obtain the target thermal field information of the transformer under the target operating condition.

[0059] Another optional implementation of this embodiment is as follows: preprocess the target operating condition, and input the preprocessed target operating condition into the target thermal field determination model, which then outputs the target thermal field information of the transformer under the target operating condition. The preprocessing method includes at least one of cleaning, correction, and normalization processing.

[0060] The aforementioned method for determining the thermal field information of a transformer, in response to a request to determine the thermal field of the transformer, acquires the target operating condition of the transformer; inputs the target operating condition into a target thermal field determination model to obtain the target thermal field information of the transformer under the target operating condition; wherein, the target thermal field determination model is obtained by training a neural network model based on the physical structure of the transformer and training samples; the training samples include a first sample operating condition and the corresponding first sample thermal field information, as well as a second sample operating condition. This application can train a neural network model to obtain the target thermal field determination model based on the first sample operating condition and the corresponding first sample thermal field information, as well as the second sample operating condition. Only the target operating condition needs to be input into the target thermal field determination model to obtain the target thermal field information of the transformer under the target operating condition. Based on the target thermal field determination model, not only can the thermal field information of the transformer under any operating condition be obtained, but it also has a fast thermal field information response speed. Based on the thermal field information, the temperature information at any location inside the transformer can be clearly identified, which can be used to realize temperature early warning of the transformer, reduce the failure rate of the transformer, and extend the service life of the transformer. For example, based on the thermal field information inside the transformer, the temperature information at any location inside the transformer can be known. When the temperature exceeds the set temperature threshold, which will damage the performance of the insulation material, a temperature warning can be issued, which can effectively reduce the failure rate of the transformer and extend its service life.

[0061] In one embodiment, to improve the accuracy of the constructed target thermal field determination model, such as... Figure 3 As shown, in S202, an optional implementation method for training the neural network model based on the physical structure of the transformer and training samples includes:

[0062] S301. Based on the physical structure of the transformer, the first sample operating condition, and the first sample thermal field information corresponding to the first sample operating condition, construct the target thermal field simulation model of the transformer.

[0063] The physical structure of a transformer refers to its structural components, mainly including the core, windings, end plates and pressure plates, and tank. The target thermal field simulation model refers to a simulation model that can be used to simulate the thermal field of a transformer.

[0064] Optionally, in this embodiment, a physical model of the transformer is constructed based on its physical structure. A target thermal field simulation model of the transformer is then constructed based on the physical model, the first sample operating condition, and the corresponding first sample thermal field information.

[0065] Optionally, in this embodiment, an alternative implementation method for constructing the physical model of the transformer based on its physical structure is as follows: The physical model of the transformer is constructed using model building software, based on its physical structure. The model building software may be, but is not limited to, Solidworks software.

[0066] Optionally, in this embodiment, an optional implementation method for constructing the target thermal field simulation model of the transformer based on the physical model, the first sample operating condition, and the corresponding first sample thermal field information is as follows: The physical model is imported into finite element analysis software to obtain the finite element model of the transformer. Constraints are configured for the finite element model; these constraints include heat dissipation conditions and convective heat transfer coefficients. The finite element model with configured constraints is meshed to obtain the initial thermal field simulation model of the transformer. The initial thermal field simulation model is trained using the first sample operating condition and the corresponding first sample thermal field information to obtain the target thermal field simulation model. The finite element analysis software can be, but is not limited to, ANSYS, COMSOL, etc.

[0067] When meshing a finite element model with configured constraints, the meshing method can be tetrahedral meshing or other forms of meshing methods.

[0068] In this embodiment, the initial thermal field simulation model is trained using the first sample operating condition and the corresponding first sample thermal field information to obtain the target thermal field simulation model. An optional implementation method is as follows:

[0069] The first sample operating condition is input into the initial thermal field simulation model. The initial thermal field simulation model predicts the thermal field information of the predicted sample, and the temperature difference between the predicted sample thermal field information and the first sample thermal field information is determined. If the temperature difference is less than a temperature threshold, the initial thermal field simulation model is used as the target thermal field simulation model. If the temperature difference is not less than the temperature threshold, the constraints (heat dissipation conditions and / or convective heat transfer coefficient) are adjusted, and the initial thermal field simulation model is updated until the temperature difference between the predicted sample thermal field information and the first sample thermal field information is less than the temperature threshold, thus completing the iterative training process of the initial thermal field simulation model. When determining the temperature difference between the predicted sample thermal field information and the first sample thermal field information, the local temperature difference at the same location on the transformer (e.g., the temperature difference between the core end information in the predicted sample thermal field information and the core end information in the first sample thermal field information) can be used as the temperature difference between the predicted sample thermal field information and the first sample thermal field information.

[0070] S302, through the target thermal field simulation model, determines the second sample thermal field information of the transformer under the second sample operating condition.

[0071] The second sample thermal field information refers to the sample thermal field information predicted by the target thermal field simulation model based on the second sample operating conditions.

[0072] Optionally, in this embodiment, the operating conditions of the second sample are input into the target thermal field simulation model, and the target thermal field simulation model outputs the thermal field information of the second sample.

[0073] S303, based on the first sample operating condition and the first sample thermal field information corresponding to the first sample operating condition, and the second sample operating condition and the second sample thermal field information corresponding to the second sample operating condition, the neural network model is trained to obtain the target thermal field determination model.

[0074] Optionally, in this embodiment, the neural network model is trained based on the first sample operating condition and the first sample thermal field information corresponding to the first sample operating condition, as well as the second sample operating condition and the second sample thermal field information corresponding to the second sample operating condition. The relevant parameters of the neural network model are adjusted until the output accuracy of the trained neural network model meets the requirements, thereby obtaining the target thermal field determination model.

[0075] In this embodiment, a target thermal field simulation model of the transformer is constructed based on the transformer's physical structure, the first sample operating condition, and the corresponding first sample thermal field information. The target thermal field simulation model is used to determine the second sample thermal field information of the transformer under the second sample operating condition. Based on the first sample operating condition and the corresponding first sample thermal field information, as well as the second sample operating condition and the corresponding second sample thermal field information, a neural network model is trained to obtain the target thermal field determination model. In this embodiment, the training sample set can be expanded based on the target thermal field simulation model and the second sample operating condition. The neural network model is trained based on the first sample operating condition, the corresponding first sample thermal field information, the second sample operating condition, and the expanded second sample thermal field information to obtain the target thermal field determination model. The more sample operating conditions and sample thermal field information available, the more accurate the target thermal field determination model's output.

[0076] In one embodiment, to more accurately determine the thermal field information of the second sample, such as Figure 4 As shown, through the target thermal field simulation model, the optional implementation methods for the second sample thermal field information of the transformer under the second sample operating condition are determined, including:

[0077] S401, determine the heat loss of the transformer based on the current parameters and / or voltage parameters in the second sample operating condition.

[0078] Among them, heat loss refers to the heat loss inside the transformer.

[0079] One optional implementation of this embodiment is as follows: Based on the current parameters and voltage parameters in the second sample operating condition, the magnetic field information of the transformer under the second sample operating condition is determined, and the heat loss of the transformer can be determined based on the magnetic field information.

[0080] An optional implementation of this embodiment is as follows: the heat loss of the transformer is determined based on the current parameters and / or voltage parameters under the second sample operating condition, the resistance value of the transformer, and the operating events under the second sample operating condition.

[0081] S402, based on heat loss, applies a heat source to the windings and core in the target thermal field simulation model to obtain the second sample thermal field information of the transformer under the second sample operating condition.

[0082] Optionally, in this embodiment, based on the heating characteristics of the winding and the core, a heat source is applied to the winding and the core in the target thermal field simulation model according to the heat loss, so as to obtain the second sample thermal field information of the transformer under the second sample operating condition.

[0083] In this embodiment, the heat loss of the transformer is determined based on the current and / or voltage parameters in the second sample operating condition. Based on the heat loss, a heat source is applied to the windings and core in the target thermal field simulation model to obtain the second sample thermal field information of the transformer under the second sample operating condition. This allows the obtained second sample thermal field information to be closer to the actual thermal field information under the second sample operating condition.

[0084] In one embodiment, to further improve the accuracy of the target thermal field determination model, such as... Figure 5 As shown, based on the first sample operating condition and the corresponding first sample thermal field information, and the second sample operating condition and the corresponding second sample thermal field information, a neural network model is trained to obtain a target thermal field determination model. One optional implementation includes:

[0085] S501, based on the second sample operating conditions and the corresponding second sample thermal field information, train the neural network model to obtain the candidate thermal field determination model.

[0086] S502, input the first sample operating condition into the candidate thermal field determination model to obtain the predicted thermal field information of the transformer under the first sample operating condition.

[0087] S503, if the temperature difference between the predicted thermal field information and the first sample thermal field information is less than the difference threshold, then the candidate thermal field determination model is used as the target thermal field determination model.

[0088] Optionally, this embodiment can employ a random sampling method to select a first local region temperature from the predicted thermal field information and a second local region temperature from the first sample thermal field information. The temperature difference between the first and second local region temperatures is used as the temperature difference between the predicted thermal field information and the first sample thermal field information. If the temperature difference is less than a threshold, the candidate thermal field determination model is used as the target thermal field determination model. The local region location corresponding to the first local region temperature is the same as the local region location corresponding to the second local region temperature.

[0089] Optionally, in this embodiment, if the temperature difference between the predicted thermal field information and the first sample thermal field information is not less than the difference threshold, the relevant parameters of the candidate thermal field determination model are adjusted, and the execution step S502 is returned based on the adjusted candidate thermal field determination model until the temperature difference between the predicted thermal field information and the first sample thermal field information is less than the difference threshold.

[0090] In this embodiment, since the accuracy of the second sample thermal field information is obtained based on the simulation of the target thermal field simulation model and is not the actual thermal field information, the accuracy will be slightly worse than the actual situation. Therefore, this application uses the second sample operating conditions and the second sample thermal field information corresponding to the second sample operating conditions to train the neural network model to obtain the candidate thermal field determination model, and uses the first sample operating conditions and the first sample thermal field information to verify and iterate the candidate thermal field determination model, so that the thermal field information output by the obtained target thermal field determination model is more accurate.

[0091] In one embodiment, such as Figure 6 As shown, one possible implementation of the method for determining the thermal field information of a transformer is as follows:

[0092] S601, based on the physical structure of the transformer, construct a physical model of the transformer.

[0093] S602, import the physical model into the finite element analysis software to obtain the finite element model of the transformer.

[0094] S603 configures the constraints for the finite element model. These constraints include heat dissipation conditions and convective heat transfer coefficients.

[0095] S604 performs mesh generation on the finite element model after configuring constraints to obtain the initial thermal field simulation model of the transformer.

[0096] S605 uses the first sample operating condition and the corresponding first sample thermal field information to train the initial thermal field simulation model and obtain the target thermal field simulation model.

[0097] S606, determine the heat loss of the transformer based on the current parameters and / or voltage parameters in the second sample operating condition.

[0098] S607, based on heat loss, applies a heat source to the windings and core in the target thermal field simulation model to obtain the second sample thermal field information of the transformer under the second sample operating condition.

[0099] S608, based on the second sample operating conditions and the corresponding second sample thermal field information, train the neural network model to obtain the candidate thermal field determination model.

[0100] S609, input the first sample operating condition into the candidate thermal field determination model to obtain the predicted thermal field information of the transformer under the first sample operating condition.

[0101] S6010 If the temperature difference between the predicted thermal field information and the first sample thermal field information is less than the difference threshold, then the candidate thermal field determination model is used as the target thermal field determination model.

[0102] S6011, in response to a request to determine the thermal field of the transformer, obtains the target operating conditions of the transformer.

[0103] S6012 inputs the target operating condition into the target thermal field determination model to obtain the target thermal field information of the transformer under the target operating condition.

[0104] In this embodiment, in response to a request to determine the thermal field of the transformer, the target operating condition of the transformer is obtained. The target operating condition is input into the target thermal field determination model to obtain the target thermal field information of the transformer under the target operating condition. The target thermal field determination model is obtained by training a neural network model based on the transformer's physical structure and training samples. The training samples include a first sample operating condition and the corresponding first sample thermal field information, as well as a second sample operating condition. This application can train a neural network model to obtain the target thermal field determination model based on the first sample operating condition, the corresponding first sample thermal field information, and the second sample operating condition. By simply inputting the target operating condition into the target thermal field determination model, the target thermal field information of the transformer under the target operating condition can be obtained. Based on the target thermal field determination model, not only can the thermal field information of the transformer under any operating condition be obtained, but it also has a fast thermal field information response speed. Based on the thermal field information, the temperature information at any location inside the transformer can be clearly identified, which can be used to realize temperature early warning of the transformer, reduce the transformer failure rate, and extend the service life of the transformer. For example, based on the thermal field information inside the transformer, the temperature information at any location inside the transformer can be known. When the temperature exceeds the set temperature threshold, which will damage the performance of the insulation material, a temperature warning can be issued, which can effectively reduce the failure rate of the transformer and extend its service life.

[0105] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0106] Based on the same inventive concept, this application also provides a transformer thermal field information determination device for implementing the above-described method for determining transformer thermal field information. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more transformer thermal field information determination device embodiments provided below can be found in the limitations of the transformer thermal field information determination method described above, and will not be repeated here.

[0107] In one embodiment, such as Figure 7 As shown, a device 1 for determining the thermal field information of a transformer is provided, comprising: an acquisition module 10 and a determination module 20, wherein:

[0108] The acquisition module 10 is used to acquire the target operating conditions of the transformer in response to a request to determine the thermal field of the transformer.

[0109] The determination module 20 is used to input the target operating condition into the target thermal field determination model to obtain the target thermal field information of the transformer under the target operating condition. The target thermal field determination model is obtained by training a neural network model based on the physical structure of the transformer and training samples. The training samples include the first sample operating condition and the first sample thermal field information corresponding to the first sample operating condition, as well as the second sample operating condition.

[0110] In one embodiment, for the upper Figure 7 The determining module 20 is also specifically used for:

[0111] Based on the physical structure of the transformer, the first sample operating condition, and the first sample thermal field information corresponding to the first sample operating condition, a target thermal field simulation model of the transformer is constructed.

[0112] The thermal field information of the transformer under the second sample operating condition was determined by using the target thermal field simulation model.

[0113] Based on the first sample operating condition and the corresponding first sample thermal field information, as well as the second sample operating condition and the corresponding second sample thermal field information, the neural network model is trained to obtain the target thermal field determination model.

[0114] In one embodiment, for the upper Figure 7 The determining module 20 is also specifically used for:

[0115] Based on the physical structure of the transformer, construct a physical model of the transformer;

[0116] Based on the physical model, the first sample operating condition, and the first sample thermal field information corresponding to the first sample operating condition, a target thermal field simulation model of the transformer is constructed.

[0117] In one embodiment, for the upper Figure 7 The determining module 20 is also specifically used for:

[0118] The physical model is imported into the finite element analysis software to obtain the finite element model of the transformer;

[0119] Configure constraints for the finite element model; the constraints include heat dissipation conditions and convective heat transfer coefficients.

[0120] The finite element model with configured constraints is meshed to obtain the initial thermal field simulation model of the transformer;

[0121] The initial thermal field simulation model is trained using the first sample operating condition and the corresponding first sample thermal field information to obtain the target thermal field simulation model.

[0122] In one embodiment, for the upper Figure 7 The determining module 20 is also specifically used for:

[0123] The heat loss of the transformer is determined based on the current and / or voltage parameters in the second sample operating conditions.

[0124] Based on heat loss, a heat source is applied to the windings and core in the target thermal field simulation model to obtain the second sample thermal field information of the transformer under the second sample operating condition.

[0125] In one embodiment, for the upper Figure 7 The determining module 20 is also specifically used for:

[0126] Based on the second sample operating conditions and the corresponding second sample thermal field information, the neural network model is trained to obtain the candidate thermal field determination model.

[0127] The first sample operating condition is input into the candidate thermal field determination model to obtain the predicted thermal field information of the transformer under the first sample operating condition;

[0128] If the temperature difference between the predicted thermal field information and the first sample thermal field information is less than the difference threshold, then the candidate thermal field determination model will be used as the target thermal field determination model.

[0129] The various modules in the aforementioned transformer thermal field information confirmation device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the operations corresponding to each module.

[0130] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores transformer-related data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for determining the thermal field information of a transformer.

[0131] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0132] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0133] In response to a request to determine the thermal field of the transformer, the target operating conditions of the transformer are obtained.

[0134] The target operating condition is input into the target thermal field determination model to obtain the target thermal field information of the transformer under the target operating condition. The target thermal field determination model is obtained by training a neural network model based on the physical structure of the transformer and training samples. The training samples include the first sample operating condition and the first sample thermal field information corresponding to the first sample operating condition, as well as the second sample operating condition.

[0135] In one embodiment, when the processor executes the computer program, it further performs the following steps: training a neural network model based on the physical structure of the transformer and training samples, including:

[0136] Based on the physical structure of the transformer, the first sample operating condition, and the first sample thermal field information corresponding to the first sample operating condition, a target thermal field simulation model of the transformer is constructed.

[0137] The thermal field information of the transformer under the second sample operating condition was determined by using the target thermal field simulation model.

[0138] Based on the first sample operating condition and the corresponding first sample thermal field information, as well as the second sample operating condition and the corresponding second sample thermal field information, the neural network model is trained to obtain the target thermal field determination model.

[0139] In one embodiment, when the processor executes the computer program, it further performs the following steps: constructing a target thermal field simulation model of the transformer based on the transformer's physical structure, a first sample operating condition, and the first sample thermal field information corresponding to the first sample operating condition, including:

[0140] Based on the physical structure of the transformer, construct a physical model of the transformer;

[0141] Based on the physical model, the first sample operating condition, and the first sample thermal field information corresponding to the first sample operating condition, a target thermal field simulation model of the transformer is constructed.

[0142] In one embodiment, when the processor executes the computer program, it further performs the following steps: constructing a target thermal field simulation model of the transformer based on the physical model, the first sample operating condition, and the first sample thermal field information corresponding to the first sample operating condition, including:

[0143] The physical model is imported into the finite element analysis software to obtain the finite element model of the transformer;

[0144] Configure constraints for the finite element model; the constraints include heat dissipation conditions and convective heat transfer coefficients.

[0145] The finite element model with configured constraints is meshed to obtain the initial thermal field simulation model of the transformer;

[0146] The initial thermal field simulation model is trained using the first sample operating condition and the corresponding first sample thermal field information to obtain the target thermal field simulation model.

[0147] In one embodiment, when the processor executes the computer program, it further performs the following steps: determining the second sample thermal field information of the transformer under the second sample operating condition using a target thermal field simulation model, including:

[0148] The heat loss of the transformer is determined based on the current and / or voltage parameters in the second sample operating conditions.

[0149] Based on heat loss, a heat source is applied to the windings and core in the target thermal field simulation model to obtain the second sample thermal field information of the transformer under the second sample operating condition.

[0150] In one embodiment, when the processor executes the computer program, it further performs the following steps: training a neural network model based on a first sample operating condition and the first sample thermal field information corresponding to the first sample operating condition, and a second sample operating condition and the second sample thermal field information corresponding to the second sample operating condition, to obtain a target thermal field determination model, including:

[0151] Based on the second sample operating conditions and the corresponding second sample thermal field information, the neural network model is trained to obtain the candidate thermal field determination model.

[0152] The first sample operating condition is input into the candidate thermal field determination model to obtain the predicted thermal field information of the transformer under the first sample operating condition;

[0153] If the temperature difference between the predicted thermal field information and the first sample thermal field information is less than the difference threshold, then the candidate thermal field determination model will be used as the target thermal field determination model.

[0154] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0155] In response to a request to determine the thermal field of the transformer, the target operating conditions of the transformer are obtained.

[0156] The target operating condition is input into the target thermal field determination model to obtain the target thermal field information of the transformer under the target operating condition. The target thermal field determination model is obtained by training a neural network model based on the physical structure of the transformer and training samples. The training samples include the first sample operating condition and the first sample thermal field information corresponding to the first sample operating condition, as well as the second sample operating condition.

[0157] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: training a neural network model based on the physical structure of the transformer and training samples, including:

[0158] Based on the physical structure of the transformer, the first sample operating condition, and the first sample thermal field information corresponding to the first sample operating condition, a target thermal field simulation model of the transformer is constructed.

[0159] The thermal field information of the transformer under the second sample operating condition was determined by using the target thermal field simulation model.

[0160] Based on the first sample operating condition and the corresponding first sample thermal field information, as well as the second sample operating condition and the corresponding second sample thermal field information, the neural network model is trained to obtain the target thermal field determination model.

[0161] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: constructing a target thermal field simulation model of the transformer based on the transformer's physical structure, a first sample operating condition, and the first sample thermal field information corresponding to the first sample operating condition, including:

[0162] Based on the physical structure of the transformer, construct a physical model of the transformer;

[0163] Based on the physical model, the first sample operating condition, and the first sample thermal field information corresponding to the first sample operating condition, a target thermal field simulation model of the transformer is constructed.

[0164] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: constructing a target thermal field simulation model of the transformer based on the physical model, the first sample operating condition, and the first sample thermal field information corresponding to the first sample operating condition, including:

[0165] The physical model is imported into the finite element analysis software to obtain the finite element model of the transformer;

[0166] Configure constraints for the finite element model; the constraints include heat dissipation conditions and convective heat transfer coefficients.

[0167] The finite element model with configured constraints is meshed to obtain the initial thermal field simulation model of the transformer;

[0168] The initial thermal field simulation model is trained using the first sample operating condition and the corresponding first sample thermal field information to obtain the target thermal field simulation model.

[0169] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the second sample thermal field information of the transformer under the second sample operating condition using a target thermal field simulation model, including:

[0170] The heat loss of the transformer is determined based on the current and / or voltage parameters in the second sample operating conditions.

[0171] Based on heat loss, a heat source is applied to the windings and core in the target thermal field simulation model to obtain the second sample thermal field information of the transformer under the second sample operating condition.

[0172] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: training a neural network model based on a first sample operating condition and the first sample thermal field information corresponding to the first sample operating condition, and a second sample operating condition and the second sample thermal field information corresponding to the second sample operating condition, to obtain a target thermal field determination model, including:

[0173] Based on the second sample operating conditions and the corresponding second sample thermal field information, the neural network model is trained to obtain the candidate thermal field determination model.

[0174] The first sample operating condition is input into the candidate thermal field determination model to obtain the predicted thermal field information of the transformer under the first sample operating condition;

[0175] If the temperature difference between the predicted thermal field information and the first sample thermal field information is less than the difference threshold, then the candidate thermal field determination model will be used as the target thermal field determination model.

[0176] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0177] In response to a request to determine the thermal field of the transformer, the target operating conditions of the transformer are obtained.

[0178] The target operating condition is input into the target thermal field determination model to obtain the target thermal field information of the transformer under the target operating condition. The target thermal field determination model is obtained by training a neural network model based on the physical structure of the transformer and training samples. The training samples include the first sample operating condition and the first sample thermal field information corresponding to the first sample operating condition, as well as the second sample operating condition.

[0179] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: training a neural network model based on the physical structure of the transformer and training samples, including:

[0180] Based on the physical structure of the transformer, the first sample operating condition, and the first sample thermal field information corresponding to the first sample operating condition, a target thermal field simulation model of the transformer is constructed.

[0181] The thermal field information of the transformer under the second sample operating condition was determined by using the target thermal field simulation model.

[0182] Based on the first sample operating condition and the corresponding first sample thermal field information, as well as the second sample operating condition and the corresponding second sample thermal field information, the neural network model is trained to obtain the target thermal field determination model.

[0183] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: constructing a target thermal field simulation model of the transformer based on the transformer's physical structure, a first sample operating condition, and the first sample thermal field information corresponding to the first sample operating condition, including:

[0184] Based on the physical structure of the transformer, construct a physical model of the transformer;

[0185] Based on the physical model, the first sample operating condition, and the first sample thermal field information corresponding to the first sample operating condition, a target thermal field simulation model of the transformer is constructed.

[0186] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: constructing a target thermal field simulation model of the transformer based on the physical model, the first sample operating condition, and the first sample thermal field information corresponding to the first sample operating condition, including:

[0187] The physical model is imported into the finite element analysis software to obtain the finite element model of the transformer;

[0188] Configure constraints for the finite element model; the constraints include heat dissipation conditions and convective heat transfer coefficients.

[0189] The finite element model with configured constraints is meshed to obtain the initial thermal field simulation model of the transformer;

[0190] The initial thermal field simulation model is trained using the first sample operating condition and the corresponding first sample thermal field information to obtain the target thermal field simulation model.

[0191] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: determining the second sample thermal field information of the transformer under the second sample operating condition using a target thermal field simulation model, including:

[0192] The heat loss of the transformer is determined based on the current and / or voltage parameters in the second sample operating conditions.

[0193] Based on heat loss, a heat source is applied to the windings and core in the target thermal field simulation model to obtain the second sample thermal field information of the transformer under the second sample operating condition.

[0194] In one embodiment, when the computer program is executed by a processor, it further performs the following steps: training a neural network model based on a first sample operating condition and the first sample thermal field information corresponding to the first sample operating condition, and a second sample operating condition and the second sample thermal field information corresponding to the second sample operating condition, to obtain a target thermal field determination model, including:

[0195] Based on the second sample operating conditions and the corresponding second sample thermal field information, the neural network model is trained to obtain the candidate thermal field determination model.

[0196] The first sample operating condition is input into the candidate thermal field determination model to obtain the predicted thermal field information of the transformer under the first sample operating condition;

[0197] If the temperature difference between the predicted thermal field information and the first sample thermal field information is less than the difference threshold, then the candidate thermal field determination model will be used as the target thermal field determination model.

[0198] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0199] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0200] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for determining the thermal field information of a transformer, characterized in that, The method includes: In response to a request to determine the thermal field of the transformer, the target operating condition of the transformer is obtained; The target operating condition is input into the target thermal field determination model to obtain the target thermal field information of the transformer under the target operating condition; wherein, the target thermal field information refers to the temperature distribution information inside the transformer corresponding to the target operating condition; the target thermal field determination model is obtained by training a neural network model based on the physical structure of the transformer and training samples; the training samples include a first sample operating condition and the first sample thermal field information corresponding to the first sample operating condition, and a second sample operating condition; the training of the neural network model based on the physical structure of the transformer and the training samples includes: constructing the target thermal field of the transformer according to the physical structure of the transformer, the first sample operating condition and the first sample thermal field information corresponding to the first sample operating condition. The simulation model is used to determine the heat loss of the transformer based on the current and / or voltage parameters in the second sample operating condition. Based on the heat loss, a heat source is applied to the windings and core in the target thermal field simulation model to obtain the second sample thermal field information of the transformer under the second sample operating condition. The neural network model is trained based on the second sample operating condition and the corresponding second sample thermal field information to obtain a candidate thermal field determination model. The first sample operating condition is input into the candidate thermal field determination model to obtain the predicted thermal field information of the transformer under the first sample operating condition. If the temperature difference between the predicted thermal field information and the first sample thermal field information is less than a difference threshold, the candidate thermal field determination model is used as the target thermal field determination model.

2. The method according to claim 1, characterized in that, The step of constructing a target thermal field simulation model of the transformer based on the transformer's physical structure, the first sample operating condition, and the corresponding first sample thermal field information includes: Based on the physical structure of the transformer, construct a physical model of the transformer; Based on the physical model, the first sample operating conditions, and the first sample thermal field information corresponding to the first sample operating conditions, a target thermal field simulation model of the transformer is constructed.

3. The method according to claim 2, characterized in that, The step of constructing a target thermal field simulation model of the transformer based on the physical model, the first sample operating condition, and the first sample thermal field information corresponding to the first sample operating condition includes: The physical model is imported into the finite element analysis software to obtain the finite element model of the transformer; Configure constraints for the finite element model; wherein the constraints include heat dissipation conditions and convective heat transfer coefficient; The finite element model with configured constraints is meshed to obtain the initial thermal field simulation model of the transformer. The initial thermal field simulation model is trained using the first sample operating condition and the corresponding first sample thermal field information to obtain the target thermal field simulation model.

4. A device for determining the thermal field information of a transformer, characterized in that, The device includes: The acquisition module is used to acquire the target operating conditions of the transformer in response to a request to determine the thermal field of the transformer. A determination module is used to input the target operating condition into a target thermal field determination model to obtain the target thermal field information of the transformer under the target operating condition; wherein, the target thermal field information refers to the temperature distribution information inside the transformer corresponding to the target operating condition; the target thermal field determination model is obtained by training a neural network model based on the physical structure of the transformer and training samples; the training samples include a first sample operating condition and the first sample thermal field information corresponding to the first sample operating condition, and a second sample operating condition; the step of training the neural network model based on the physical structure of the transformer and the training samples includes: constructing the transformer's... The target thermal field simulation model is used to determine the heat loss of the transformer based on the current and / or voltage parameters in the second sample operating condition. Based on the heat loss, a heat source is applied to the windings and core in the target thermal field simulation model to obtain the second sample thermal field information of the transformer under the second sample operating condition. The neural network model is trained based on the second sample operating condition and the corresponding second sample thermal field information to obtain a candidate thermal field determination model. The first sample operating condition is input into the candidate thermal field determination model to obtain the predicted thermal field information of the transformer under the first sample operating condition. If the temperature difference between the predicted thermal field information and the first sample thermal field information is less than a difference threshold, the candidate thermal field determination model is used as the target thermal field determination model.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method for determining the thermal field information of a transformer as described in any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for determining the thermal field information of a transformer as described in any one of claims 1 to 3.

7. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the method for determining the thermal field information of a transformer as described in any one of claims 1 to 3.

Images