Transformer temperature distribution monitoring method based on deep learning and related device

Abstract

The embodiment of the invention discloses a transformer temperature distribution monitoring method based on deep learning and a related device. The monitoring method comprises the following steps: acquiring current voltage and current data of a transformer; and performing temperature distribution prediction by using the current voltage and current data and a pre-trained deep learning model to obtain a current prediction result of the transformer at least comprising a current winding short circuit position, a current risk position and current temperature distribution of the transformer, the risk position being used for indicating a position where the transformer has a winding burnout risk. Through the mode, the temperature distribution of the transformer, the winding short-circuit position and the risk position with the winding burnout risk can be predicted by inputting the acquired voltage and current data into the deep learning model, and the monitoring of the temperature distribution of the transformer is realized under the condition that a temperature sensor does not need to be installed; and positioning the short circuit position and the risk position to judge the health state.

Description

Technical Field

[0001] The present invention relates to the field of data monitoring technology, and in particular to a transformer temperature distribution monitoring method and related devices based on deep learning. Background Art

[0002] Transformers are common equipment in power systems, used to transform voltage and current transmission. As the core component of the transformer, the transformer winding is subjected to the force of current and magnetic field, which causes stress and deformation. This leads to short-circuit faults inside the transformer or between windings. A short-circuit fault in a transformer can cause the temperature at some locations to be higher than the maximum allowable temperature, resulting in the risk of insulation breakdown or winding overheating and burning, and may even cause safety accidents such as fire and explosion, threatening the lives of personnel. By detecting abnormal temperature points inside the transformer as early as possible, potential fault risks can be reduced and the stability of the power system can be improved. At present, the monitoring of transformer temperature distribution is mainly carried out by directly measuring the temperature of some locations through temperature sensors. However, for some locations of the internal windings of the transformer, since they are sealed by the iron core and other windings, temperature sensors cannot be installed to directly measure the temperature, which affects the judgment of the overall health status of the transformer.

[0003] Therefore, a reasonable and effective method is needed to obtain detailed transformer temperature distribution information using simple and measurable transformer experimental data, so as to provide early warning of the transformer health status. Summary of the invention

[0004] The main purpose of the present invention is to provide a transformer temperature distribution monitoring method and related devices based on deep learning, which can solve the problem in the prior art that a temperature sensor cannot be installed to directly measure the temperature.

[0005] To achieve the above object, the first aspect of the present invention provides a transformer temperature distribution monitoring method based on deep learning, the monitoring method comprising:

[0006] Acquiring current voltage and current data of the transformer;

[0007] The temperature distribution is predicted using the current voltage and current data and a pre-trained deep learning model to obtain a current prediction result of the transformer, wherein the current prediction result includes at least the current winding short-circuit position, the current risk position and the current temperature distribution of the transformer, wherein the risk position is used to indicate the position where the transformer is at risk of winding burnout, and the deep learning model is trained using a pre-collected training sample set, wherein the training sample set includes at least the first risk position, the first voltage and current data and the first temperature distribution of each winding short-circuit position of the transformer.

[0008] In a feasible implementation, the method further includes:

[0009] Constructing a finite element model of the transformer;

[0010] Performing an initial simulation based on the finite element model to obtain initial characteristic parameters of the finite element model, wherein the initial characteristic parameters at least include a maximum temperature parameter;

[0011] Using each preset winding short-circuit position as an independent variable, simulating the winding short-circuit working condition on the finite element model to obtain first voltage and current data and first temperature distribution at each winding short-circuit position;

[0012] The first risk position under each winding short-circuit position is obtained by comparing the maximum temperature parameter and the first temperature distribution.

[0013] In a feasible implementation, the comparing the maximum temperature parameter and the first temperature distribution to obtain the first risk position at each winding short-circuit position includes:

[0014] Compare each temperature data in the first temperature distribution with the temperature threshold corresponding to the maximum temperature parameter to obtain a comparison result;

[0015] If the comparison result is that the temperature data is greater than the temperature threshold, it is determined that the transformer position corresponding to the temperature data has a risk of burning and is marked as the first risk position.

[0016] In a feasible implementation, constructing the finite element model of the transformer includes:

[0017] The finite element geometric model of the transformer is divided into an iron core, a winding and an oil tank;

[0018] Setting materials for the core, winding and oil tank according to actual transformer parameters of the transformer to obtain a finite element geometric model after setting;

[0019] Corresponding boundary conditions are set for the iron core and winding in the set finite element geometric model to obtain the finite element model of the transformer.

[0020] In a feasible implementation, performing an initial simulation based on the finite element model to obtain initial characteristic parameters of the finite element model includes:

[0021] Excitation is applied to the finite element model to perform initial simulation of transient and steady-state simulation, second current and voltage data of the transformer are obtained, and maximum temperature parameters of the transformer during operation are calculated during the transient and steady-state simulation.

[0022] In a feasible implementation, the finite element model is simulated under the short-circuit condition by taking each preset winding short-circuit position as an independent variable to obtain the first voltage and current data and the first temperature distribution at each winding short-circuit position, including:

[0023] The winding short-circuit positions are traversed in sequence, and for the traversed target winding short-circuit position, the short-circuit condition of the transformer is set to the target winding short-circuit position to perform a simulation of the short-circuit condition, the first current and voltage data at the target winding short-circuit position are obtained, and the first temperature distribution of the transformer during operation under the short-circuit condition at the target winding short-circuit position is calculated.

[0024] To achieve the above object, the second aspect of the present invention provides a monitoring device for transformer temperature distribution based on deep learning, the device comprising:

[0025] Data acquisition module: used to obtain the current voltage and current data of the transformer;

[0026] Temperature prediction module: used to use the current voltage and current data and a pre-trained deep learning model to predict the temperature distribution, and obtain the current prediction result of the transformer, the current prediction result at least includes the current winding short-circuit position, the current risk position and the current temperature distribution of the transformer, the risk position is used to indicate the position where the transformer has a risk of winding burnout, the deep learning model is trained using a pre-collected training sample set, and the training sample set includes at least the first risk position, the first voltage and current data and the first temperature distribution under each winding short-circuit position of the transformer.

[0027] In a feasible implementation, the device further includes:

[0028] Model building module: used to build a finite element model of the transformer;

[0029] A parameter determination module: used for performing an initial simulation based on the finite element model to obtain initial characteristic parameters of the finite element model, wherein the initial characteristic parameters at least include a maximum temperature parameter;

[0030] A winding short-circuit simulation module is used to simulate the short-circuit working condition of the finite element model by taking each preset winding short-circuit position as an independent variable, and obtain the first voltage and current data and the first temperature distribution at each winding short-circuit position;

[0031] Risk location module: used to compare the maximum temperature parameter and the first temperature distribution to obtain the first risk position under each winding short-circuit position.

[0032] To achieve the above-mentioned purpose, the third aspect of the present invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the steps shown in the first aspect and any feasible implementation method.

[0033] To achieve the above-mentioned purpose, the fourth aspect of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps shown in the first aspect and any feasible implementation method.

[0034] The embodiments of the present invention have the following beneficial effects:

[0035] The present invention provides a monitoring method for transformer temperature distribution based on deep learning, the monitoring method comprising: obtaining the current voltage and current data of the transformer; using the current voltage and current data and a pre-trained deep learning model to predict the temperature distribution, and obtaining the current prediction result of the transformer, the current prediction result at least includes the current winding short-circuit position of the transformer, the current risk position and the current temperature distribution, the risk position is used to indicate the position where the transformer has a risk of winding burning, the deep learning model is trained using a pre-collected training sample set, and the training sample set at least includes the first risk position, the first voltage and current data and the first temperature distribution under each winding short-circuit position of the transformer. In the above manner, the collected voltage and current data can be input into the deep learning model to predict the temperature distribution of the transformer, the winding short-circuit position and the risk position where the winding burns out, and the transformer temperature distribution can be monitored without installing a temperature sensor, and the short-circuit position and the risk position can be located to make a judgment on the health status. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] in:

[0038] Figure 1 Flow chart of a method for monitoring transformer temperature distribution based on deep learning in an embodiment of the present invention;

[0039] Figure 2 Another flow chart of a method for monitoring transformer temperature distribution based on deep learning in an embodiment of the present invention;

[0040] Figure 3It is a structural block diagram of a transformer temperature distribution monitoring device based on deep learning in an embodiment of the present invention;

[0041] Figure 4 4 is a structural block diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0043] See also Figure 1 , Figure 1 The flowchart of a transformer temperature distribution monitoring method based on deep learning in an embodiment of the present invention is shown in FIG. 1 . The method can be applied to both a terminal and a server. The terminal can be a desktop terminal or a mobile terminal. The mobile terminal can be at least one of a mobile phone, a tablet computer, and a laptop computer. The server can be implemented by an independent server or a server cluster composed of multiple servers. This embodiment is described by applying to a terminal as an example. Figure 1 The methods shown include:

[0044] 101. Obtain current voltage and current data of the transformer;

[0045] 102. Use the current voltage and current data and a pre-trained deep learning model to predict the temperature distribution and obtain a current prediction result of the transformer, wherein the current prediction result includes at least the current winding short-circuit position, the current risk position and the current temperature distribution of the transformer, wherein the risk position is used to indicate the position where the transformer is at risk of winding burnout, and the deep learning model is trained using a pre-collected training sample set, wherein the training sample set includes at least the first risk position, the first voltage and current data and the first temperature distribution at each winding short-circuit position of the transformer.

[0046] It should be noted that the artificial intelligence database is a model obtained through training and deep learning of a large amount of data, and has strong information processing and judgment capabilities. Therefore, the present application provides a transformer temperature distribution monitoring method based on deep learning. During the actual operation of the transformer, the transformer temperature distribution is predicted by the easily obtained and easy to collect port current and voltage waveform parameters of the transformer. Specifically, the initial deep learning model is trained by a pre-collected training sample set. Since the training sample set includes at least the first risk position, the first voltage and current data and the first temperature distribution under each winding short-circuit position of the transformer, that is, the position where the transformer has a risk of winding burnout under each winding short-circuit position, the port voltage and current data and the temperature distribution, the deep learning model trained in this way can learn the port current and voltage waveform data, temperature distribution and risk position of the transformer under the short-circuit condition of the short-circuit position, thereby realizing the monitoring of temperature distribution.

[0047] Among them, the training sample set can be obtained through simulation analysis, and the corresponding data performance can be obtained by simulating different operating conditions, so as to construct a database of training sample sets for the deep learning model to learn the relationship between different feature data, so as to predict the performance of other data through a certain data that can be actually collected, such as predicting temperature distribution through voltage and current data, predicting short circuit location, etc.

[0048] Transformer temperature distribution monitoring is realized based on deep learning. It is easy to obtain the port current and voltage waveform parameters of the transformer in actual operation. Based on deep learning technology, the obtained port current and voltage waveforms are compared point by point in time sequence with the current and voltage waveforms in the database to determine the possible short-circuit position of the transformer and the temperature distribution of the transformer at this time, and obtain the position where there is a risk of winding overheating and burning.

[0049] The present invention provides a monitoring method for transformer temperature distribution based on deep learning, the monitoring method comprising: obtaining the current voltage and current data of the transformer; using the current voltage and current data and a pre-trained deep learning model to predict the temperature distribution, and obtaining the current prediction result of the transformer, the current prediction result at least includes the current winding short-circuit position of the transformer, the current risk position and the current temperature distribution, the risk position is used to indicate the position where the transformer has a risk of winding burning, the deep learning model is trained using a pre-collected training sample set, and the training sample set at least includes the first risk position, the first voltage and current data and the first temperature distribution under each winding short-circuit position of the transformer. In the above manner, the collected voltage and current data can be input into the deep learning model to predict the temperature distribution of the transformer, the winding short-circuit position and the risk position where the winding burns out, and the transformer temperature distribution can be monitored without installing a temperature sensor, and the short-circuit position and the risk position can be located to make a judgment on the health status.

[0050] See also Figure 2 , Figure 2 Another flow chart of a method for monitoring transformer temperature distribution based on deep learning in an embodiment of the present invention is shown in FIG. Figure 2 The method shown comprises the following steps:

[0051] 201. Construct a finite element model of the transformer;

[0052] It can be understood that in order to complete the training of the deep learning model, it is necessary to collect the training sample set in advance. In order to obtain more accurate and reliable training samples, the present application constructs a database through simulation to realize the collection of sample data. First, in order to realize the simulation of the transformer, it is necessary to construct a simulation model of the transformer. The simulation model can be a finite element model. A finite element model that conforms to reality is made according to the actual transformer data of the transformer.

[0053] In a feasible implementation, step 201 includes: dividing the finite element geometric model of the transformer into an iron core, a winding and an oil tank; setting materials for the iron core, the winding and the oil tank according to actual transformer parameters of the transformer to obtain a set finite element geometric model; setting corresponding boundary conditions for the iron core and the winding in the set finite element geometric model to obtain a finite element model of the transformer.

[0054] Exemplarily, a model can be built in COMSOL finite element simulation software based on actual transformer parameters. Specifically, the transformer finite element geometric model is divided into three parts: core, winding and oil tank. Then, the material of each geometric part is set according to the actual transformer, and then the corresponding boundary conditions are set for the core and winding to obtain the finite element model of the transformer.

[0055] 202. Perform an initial simulation based on the finite element model to obtain initial characteristic parameters of the finite element model, where the initial characteristic parameters at least include a maximum temperature parameter;

[0056] Furthermore, in order to obtain the initial characteristic parameters of the finite element model, an initial simulation is performed. By applying excitation to the finite element model, transient and steady-state simulations are realized to obtain the voltage and current data and temperature distribution at this time. In order to identify the risk location later, the maximum temperature parameter is also calculated at this time. The maximum temperature parameter is used to reflect the maximum temperature that the transformer can withstand to avoid overheating.

[0057] In a feasible implementation, step 202 includes: applying excitation to the finite element model to perform initial simulation of transient and steady-state simulations, obtaining second current and voltage data of the transformer, and calculating maximum temperature parameters of the transformer during operation during the transient and steady-state simulations.

[0058] Exemplarily, the model characteristic parameters obtained by simulation can specifically be: applying excitation to the transformer finite element model, conducting transient and steady-state simulation studies, obtaining port current and voltage waveform data, and calculating the maximum temperature parameters of the transformer during operation based on the calculation function of the simulation software.

[0059] 203. Using each preset winding short-circuit position as an independent variable, simulating the winding short-circuit working condition on the finite element model to obtain first voltage and current data and a first temperature distribution at each winding short-circuit position;

[0060] Furthermore, in order to obtain data performance under different short-circuit conditions, the above-mentioned finite element model is simulated under different conditions. Specifically, each winding short-circuit position is set in advance, and each preset winding short-circuit position is used as an independent variable. The finite element model is simulated under the winding short-circuit condition to obtain the first voltage and current data and the first temperature distribution under each winding short-circuit position.

[0061] In a feasible implementation, step 203 includes: traversing the winding short-circuit positions in sequence, and for the traversed target winding short-circuit positions, setting the short-circuit condition of the transformer to the target winding short-circuit position to simulate the short-circuit condition, obtaining the first current and voltage data at the target winding short-circuit position, and calculating the first temperature distribution of the transformer when operating under the short-circuit condition of the target winding short-circuit position.

[0062] Exemplarily, write a .m file that implements parametric modeling and traversal simulation: export the initial simulation file obtained based on the initial simulation step in COMSOL as a .m file adapted to MATLAB, and then use MATLAB to rewrite the initial .m file, taking the winding short-circuit position as an independent variable, and realize the automatic change of the winding short-circuit position through the code writing of the loop statement. The functions implemented by each loop process are: setting the transformer winding short-circuit position, obtaining the port current and voltage waveform data, and calculating the temperature distribution of the transformer under this working condition, and finally storing the port current, voltage and temperature distribution parameters in the specified file table.

[0063] 204. Obtain a first risk position at each winding short-circuit position by comparing the maximum temperature parameter with the first temperature distribution;

[0064] After obtaining the temperature distribution under the short-circuit condition, the risk position can be further identified. When the temperature exceeds the maximum temperature, it is considered that there is a risk of burning, and the risk position can be located by comparing the maximum temperature parameter with the first temperature distribution.

[0065] In one feasible implementation, step 204 includes:

[0066] Each temperature data in the first temperature distribution is compared with the temperature threshold corresponding to the maximum temperature parameter to obtain a comparison result; if the comparison result is that the temperature data is greater than the temperature threshold, it is determined that the transformer position corresponding to the temperature data has a burning risk and is marked as the first risk position.

[0067] 80% of the maximum temperature parameter is used as the temperature threshold corresponding to the maximum temperature, and the transformer position with a temperature greater than the temperature threshold is located by comparison, thereby marking the risk position.

[0068] Exemplarily, a temperature monitoring database adapted to the transformer is constructed. The .m file obtained in the above steps is imported into the COMSOL software, and the traversal simulation results of all winding short-circuit positions are simulated. The traversed data includes each short-circuit position and its corresponding port current and voltage waveform data and temperature distribution. If the temperature parameter of a certain position is greater than 80% of the maximum allowable temperature of the position, it is considered that there is a risk of winding overheating and burning at the position, and it is marked in the corresponding data, and a temperature monitoring database adapted to the transformer is constructed, and a database of training sample data sets is obtained in turn.

[0069] Then, the short circuit location, risk location, and temperature distribution can be used as the real labels of the voltage and current data, and the voltage and current data can be input into the initial deep model for prediction to obtain the first prediction result. The loss value between the first prediction result and the real label of the input voltage and current data is used to determine whether the model converges. When the model converges, the model training is considered to be completed, and the real label can be predicted based on the input current and voltage data. Then, the trained deep learning model is used to predict the actual voltage and current.

[0070] 205. Obtain current voltage and current data of the transformer;

[0071] 206. Use the current voltage and current data and a pre-trained deep learning model to predict the temperature distribution, and obtain the current prediction result of the transformer, wherein the current prediction result at least includes the current winding short-circuit position, the current risk position and the current temperature distribution of the transformer, wherein the risk position is used to indicate the position where the transformer has a risk of winding burnout, and the deep learning model is trained using a pre-collected training sample set, wherein the training sample set at least includes the first risk position, the first voltage and current data and the first temperature distribution at each winding short-circuit position of the transformer.

[0072] It should be noted that steps 205 and 206 are Figure 1 The contents of steps 101 and 102 are similar, and are not described here to avoid repetition. For details, please refer to Figure 1 The contents of steps 101 and 102 are shown.

[0073] The present invention proposes a transformer temperature distribution monitoring method based on deep learning. The method combines COMSOL finite element simulation software with MATLAB to perform parametric modeling of the transformer, traverses different short-circuit positions of the transformer, simulates and analyzes the temperature field distribution of various working conditions, and finally uses the traversed simulation results to build a database. The port data and database parameters measured online are analyzed through deep learning, thereby realizing the monitoring of the transformer temperature distribution. The method specifically includes the following processing steps S1 to S5:

[0074] S1: Build a model in COMSOL finite element simulation software based on actual transformer parameters: divide the transformer finite element geometric model into three parts: core, winding and oil tank. Then set the materials of each geometric part according to the actual transformer, and then set the corresponding boundary conditions for the core and winding to obtain the finite element model of the transformer.

[0075] S2: Simulate to obtain the model characteristic parameters: apply excitation to the transformer finite element model, conduct transient and steady-state simulation research, and obtain the port current and voltage waveform data. Based on the calculation function of the software, calculate the maximum temperature parameters of the transformer during operation.

[0076] S3: Write the .m file for parameterized modeling and traversal simulation: In COMSOL, export the initial simulation file obtained based on step S2 as a .m file adapted to MATLAB, and then use MATLAB to rewrite the initial .m file, taking the winding short-circuit position as an independent variable, and realize the automatic change of the winding short-circuit position through the code writing of the loop statement. The functions implemented in each loop process are: setting the transformer winding short-circuit position, obtaining the port current and voltage waveform data, and calculating the temperature distribution of the transformer under this working condition, and finally storing the port current, voltage and temperature distribution parameters in the specified file table.

[0077] S4: Construct a temperature monitoring database suitable for the transformer. Import the .m file obtained in the above steps into the COMSOL software, and simulate the traversal simulation results of all winding short-circuit positions. The traversed data includes each short-circuit position and its corresponding port current and voltage waveform data and temperature distribution. If the temperature parameter of a certain position is greater than 80% of the maximum allowable temperature of the position, it is considered that there is a risk of winding overheating and burning at this position, and it is marked in the corresponding data to construct a temperature monitoring database suitable for the transformer.

[0078] S5: Transformer temperature distribution monitoring based on deep learning. The actual transformer in operation can easily obtain the port current and voltage waveform parameters of the transformer. Based on deep learning technology, the obtained port current and voltage waveforms are compared with the current and voltage waveforms in the database point by point in time sequence to determine the possible short-circuit position of the transformer and the temperature distribution of the transformer at this time, and obtain the position where there is a risk of winding overheating and burning.

[0079] The advantage of the present invention is that it uses the easily available transformer port current and voltage waveform parameters to obtain detailed transformer temperature distribution information based on deep learning, thereby providing a health status warning for the transformer, which is of great significance to the safe operation, fault analysis and prevention of the transformer.

[0080] In one possible implementation, Figure 3 is a structural block diagram of a transformer temperature distribution monitoring device based on deep learning in an embodiment of the present invention, such as Figure 3 The device shown comprises:

[0081] Data acquisition module 301: used to obtain current voltage and current data of the transformer;

[0082] Temperature prediction module 302: used to use the current voltage and current data and a pre-trained deep learning model to predict the temperature distribution, and obtain the current prediction result of the transformer, the current prediction result at least includes the current winding short-circuit position, the current risk position and the current temperature distribution of the transformer, the risk position is used to indicate the position where the transformer has a risk of winding burnout, the deep learning model is trained using a pre-collected training sample set, and the training sample set includes at least the first risk position, the first voltage and current data and the first temperature distribution under each winding short-circuit position of the transformer.

[0083] It should be noted that Figure 3 The functions of each module in the device shown are Figure 1 The contents of each step in the method shown are similar, so they are not described here to avoid repetition. For details, please refer to Figure 1 The content of each step in the method shown.

[0084] The present invention provides a monitoring device for transformer temperature distribution based on deep learning, the device includes: a data acquisition module: used to obtain the current voltage and current data of the transformer; a temperature prediction module: used to use the current voltage and current data and a pre-trained deep learning model to predict the temperature distribution, and obtain the current prediction result of the transformer, the current prediction result at least includes the current winding short-circuit position of the transformer, the current risk position and the current temperature distribution, the risk position is used to indicate the position where the transformer has a risk of winding burning, the deep learning model is trained using a pre-collected training sample set, and the training sample set at least includes the first risk position, the first voltage and current data and the first temperature distribution under each winding short-circuit position of the transformer. In the above manner, the collected voltage and current data can be used to input the deep learning model to predict the temperature distribution of the transformer, the winding short-circuit position and the risk position with the risk of winding burning, and the transformer temperature distribution can be monitored without installing a temperature sensor, and the short-circuit position and the risk position can be located to make a judgment on the health status.

[0085] In a feasible implementation, the device further includes:

[0086] Model building module: used to build a finite element model of the transformer;

[0087] A parameter determination module: used for performing an initial simulation based on the finite element model to obtain initial characteristic parameters of the finite element model, wherein the initial characteristic parameters at least include a maximum temperature parameter;

[0088] A winding short-circuit simulation module is used to simulate the short-circuit working condition of the finite element model by taking each preset winding short-circuit position as an independent variable, and obtain the first voltage and current data and the first temperature distribution at each winding short-circuit position;

[0089] Risk location module: used to compare the maximum temperature parameter and the first temperature distribution to obtain the first risk position under each winding short-circuit position.

[0090] It should be noted that the above-mentioned model building module, parameter determination module, winding short circuit simulation module and risk location module have the same functions as Figure 2 The contents of each step in the method shown are similar, so they are not described here to avoid repetition. For details, please refer to Figure 2 The content of each step in the method shown.

[0091] The advantage of the present invention is that it uses the easily available transformer port current and voltage waveform parameters to obtain detailed transformer temperature distribution information based on deep learning, thereby providing a health status warning for the transformer, which is of great significance to the safe operation, fault analysis and prevention of the transformer.

[0092] Figure 4 FIG. 1 shows an internal structure diagram of a computer device in an embodiment. The computer device may be a terminal or a server. Figure 4 As shown, the computer device includes a processor, a memory and a network interface connected via a system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement the above method. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can implement the above method. Those skilled in the art can understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0093] In one embodiment, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps: Figure 1 or Figure 2 The steps of the method are shown.

[0094] In one embodiment, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the processor performs the following steps: Figure 1 or Figure 2 The steps of the method are shown.

[0095] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0096] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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.

[0097] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A transformer temperature distribution monitoring method based on deep learning, characterized in that: The monitoring method comprises: Acquiring current voltage and current data of the transformer; The temperature distribution is predicted using the current voltage and current data and a pre-trained deep learning model to obtain a current prediction result of the transformer, wherein the current prediction result includes at least the current winding short-circuit position, the current risk position and the current temperature distribution of the transformer, wherein the risk position is used to indicate the position where the transformer is at risk of winding burnout, and the deep learning model is trained using a pre-collected training sample set, wherein the training sample set includes at least the first risk position, the first voltage and current data and the first temperature distribution of each winding short-circuit position of the transformer.

2. The method according to claim 1, characterized in that: The method further comprises: Constructing a finite element model of the transformer; Performing an initial simulation based on the finite element model to obtain initial characteristic parameters of the finite element model, wherein the initial characteristic parameters at least include a maximum temperature parameter; Using each preset winding short-circuit position as an independent variable, simulating the winding short-circuit working condition on the finite element model to obtain first voltage and current data and first temperature distribution at each winding short-circuit position; The first risk position under each winding short-circuit position is obtained by comparing the maximum temperature parameter and the first temperature distribution.

3. The method according to claim 2, characterized in that: The step of comparing the maximum temperature parameter with the first temperature distribution to obtain a first risk position at each winding short-circuit position includes: Compare each temperature data in the first temperature distribution with the temperature threshold corresponding to the maximum temperature parameter to obtain a comparison result; If the comparison result is that the temperature data is greater than the temperature threshold, it is determined that the transformer position corresponding to the temperature data has a risk of burning and is marked as the first risk position.

4. The method according to claim 2, characterized in that: The step of constructing a finite element model of the transformer comprises: The finite element geometric model of the transformer is divided into an iron core, a winding and an oil tank; Setting materials for the core, winding and oil tank according to actual transformer parameters of the transformer to obtain a finite element geometric model after setting; Corresponding boundary conditions are set for the iron core and winding in the set finite element geometric model to obtain the finite element model of the transformer.

5. The method according to claim 4, characterized in that: The initial simulation is performed based on the finite element model to obtain initial characteristic parameters of the finite element model, including: Excitation is applied to the finite element model to perform initial simulation of transient and steady-state simulation, second current and voltage data of the transformer are obtained, and maximum temperature parameters of the transformer during operation are calculated during the transient and steady-state simulation.

6. The method according to claim 2, characterized in that: The method uses each preset winding short-circuit position as an independent variable, simulates the short-circuit working condition of the finite element model, and obtains the first voltage and current data and the first temperature distribution at each winding short-circuit position, including: The winding short-circuit positions are traversed in sequence, and for the traversed target winding short-circuit position, the short-circuit condition of the transformer is set to the target winding short-circuit position to perform a simulation of the short-circuit condition, the first current and voltage data at the target winding short-circuit position are obtained, and the first temperature distribution of the transformer during operation under the short-circuit condition at the target winding short-circuit position is calculated.

7. A monitoring device for transformer temperature distribution based on deep learning, characterized in that: The device comprises: Data acquisition module: used to obtain the current voltage and current data of the transformer; Temperature prediction module: used to use the current voltage and current data and a pre-trained deep learning model to predict the temperature distribution, and obtain the current prediction result of the transformer, the current prediction result at least includes the current winding short-circuit position, the current risk position and the current temperature distribution of the transformer, the risk position is used to indicate the position where the transformer has a risk of winding burnout, the deep learning model is trained using a pre-collected training sample set, and the training sample set includes at least the first risk position, the first voltage and current data and the first temperature distribution under each winding short-circuit position of the transformer.

8. The device according to claim 7, characterized in that: The device also includes: Model building module: used to build a finite element model of the transformer; A parameter determination module: used for performing an initial simulation based on the finite element model to obtain initial characteristic parameters of the finite element model, wherein the initial characteristic parameters at least include a maximum temperature parameter; A winding short-circuit simulation module is used to simulate the short-circuit working condition of the finite element model by taking each preset winding short-circuit position as an independent variable, and obtain the first voltage and current data and the first temperature distribution at each winding short-circuit position; Risk location module: used to compare the maximum temperature parameter and the first temperature distribution to obtain the first risk position under each winding short-circuit position.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 6.

10. A computer device comprising a memory and a processor, characterized in that: The memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method according to any one of claims 1 to 6.

Images