Method and system for estimating residual service life of transformer

Abstract

The invention discloses a method and a system for estimating the residual service life of a transformer. The method comprises the following steps: acquiring first data of the transformer; according to the transformer first data, transformer health state features are extracted, the health state features are calculated, and a transformer health index is obtained; and inputting the first data and the transformer health index into a first prediction model for prediction to obtain a transformer residual service life result. According to the method, accurate prediction of the residual service life of the transformer is realized, the full life cycle data of the transformer is considered, the prediction accuracy and efficiency are improved by optimizing the prediction model parameters, the health condition of equipment can be reflected in time, potential faults are effectively prevented, and the service life of the transformer is prolonged. Therefore, the safety and reliability of the power system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment health management, and in particular to a method and system for estimating the remaining useful life of a transformer. Background Art

[0002] With the continuous growth of global energy demand and the continuous upgrading of power systems, the stability and safety of power equipment have become key factors in ensuring power supply. Especially in the context of the rapid development of smart grids and renewable energy, the health of power equipment, especially transformers, is directly related to the reliability and safety of the entire power system. In order to meet the growing demand for electricity while ensuring the stability and safety of power supply, it is particularly important to implement health monitoring and life prediction of power equipment. By monitoring equipment data in real time, power companies can promptly discover and solve potential problems, thereby avoiding power outages caused by equipment failures and further improving the overall safety and reliability of the power system. Therefore, combined with modern information technology, health monitoring and life prediction of power equipment have become an important means to ensure the stable operation of the power system.

[0003] Although the current power equipment health management has made certain progress, it still faces many challenges. At present, most power equipment health management methods mainly rely on statistical analysis of historical fault data to predict the remaining life of the transformer. However, this method is often limited to a single data source and lacks comprehensive analysis and consideration of the data of the entire life cycle of the equipment. In addition, the process of data collection and processing is usually time-consuming, making it difficult to achieve real-time monitoring and rapid response. This leads to the inability to respond in time when the equipment fails, which affects the stability and safety of the power system. Therefore, the existing prediction methods are not only inefficient, but also have certain limitations in accuracy. In order to overcome these challenges, the power industry urgently needs a more accurate and efficient method to estimate the remaining service life of the transformer, so as to achieve comprehensive monitoring and management of the health status of power equipment. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a method for estimating the remaining service life of a transformer to solve the problem of how to accurately and efficiently estimate the remaining service life of the transformer.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for estimating the remaining useful life of a transformer, comprising:

[0008] Obtaining first transformer data;

[0009] Extracting transformer health status characteristics according to the transformer first data, calculating the health status characteristics, and obtaining a transformer health index;

[0010] The first data and the transformer health index are input into a first prediction model for prediction to obtain a result of the remaining service life of the transformer.

[0011] As a preferred solution of the method for estimating the remaining useful life of a transformer according to the present invention, the health status characteristics are calculated to obtain the health index of the transformer, including:

[0012] Converting the health status feature to obtain a health value, and comparing the health value with a first threshold to obtain a plurality of health scores;

[0013] The health score is combined with the preset weight values ​​of each health status feature to perform calculations to obtain the transformer health index.

[0014] As a preferred solution of the method for estimating the remaining useful life of a transformer according to the present invention, wherein: inputting the first data and the transformer health index into a first prediction model for prediction comprises:

[0015] Set the original parameters of the input layer, hidden layer and output layer in the first prediction model;

[0016] The first data and the transformer health index are input into a first prediction model for training to optimize the parameters of each layer of the first prediction model.

[0017] As a preferred solution of the method for estimating the remaining useful life of a transformer according to the present invention, the optimization of the parameters of each layer of the first prediction model includes:

[0018] Inputting the first data into the first prediction model to obtain a predicted remaining useful life;

[0019] Calculating the loss function of the first prediction model to obtain an error value between the predicted remaining useful life and the actual useful life;

[0020] The gradient of the first prediction model parameter is calculated, and according to the gradient, the model parameter is iteratively updated through an optimization algorithm until a maximum number of iterations is reached or an error value calculated by the loss function converges to a second threshold range.

[0021] As a preferred solution of the method for estimating the remaining useful life of a transformer according to the present invention, the first prediction model includes:

[0022] The input data of the input layer is calculated by linear change to obtain the input data of the hidden layer, and the input data of the hidden layer is calculated by a nonlinear activation function to obtain the output data of the hidden layer;

[0023] The output data of the hidden layer is first subjected to linear change calculation and then subjected to nonlinear activation function calculation until the output data of the last hidden layer is obtained;

[0024] The output data of the last hidden layer is used as the input data of the output layer, and is calculated according to the nonlinear activation function to obtain the predicted remaining service life.

[0025] As a preferred solution of the method for estimating the remaining useful life of a transformer according to the present invention, the method further comprises:

[0026] Evaluating the first prediction model to obtain a remaining life error value;

[0027] When the remaining life error value exceeds a third threshold, the preset transformer life estimation model is retrained until the remaining life error value does not exceed the third threshold.

[0028] As a preferred solution of the method for estimating the remaining useful life of a transformer according to the present invention, the first data of the transformer includes:

[0029] The transformer first data includes transformer historical operation data, historical operation environment parameters, real-time operation data and real-time operation environment parameters;

[0030] After acquiring the first data, a preprocessing operation is performed on the first data, and the preprocessing operation includes data cleaning, denoising and standardization.

[0031] In a second aspect, the present invention provides a system for estimating the remaining useful life of a transformer, comprising:

[0032] A data acquisition module, used for acquiring first transformer data;

[0033] A calculation module, used for extracting the health status characteristics of the transformer according to the first data of the transformer, calculating the health status characteristics, and obtaining the health index of the transformer;

[0034] The prediction module is used to input the first data and the transformer health index into a first prediction model for prediction to obtain the remaining service life result of the transformer.

[0035] In a third aspect, the present invention provides a computing device, comprising:

[0036] Memory and processor;

[0037] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the transformer remaining service life estimation method are implemented.

[0038] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for estimating the remaining useful life of a transformer.

[0039] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention obtains the historical operating data, historical operating environment parameters, real-time operating data and real-time operating environment parameters of the transformer comprehensively, extracts the health status characteristics after preprocessing, and then calculates the transformer health index, which is then input together with the transformer data into the first prediction model that has been optimized and trained, thereby achieving an accurate prediction of the remaining service life of the transformer. The present invention not only takes into account the full life cycle data of the transformer, but also improves the accuracy and efficiency of the prediction by optimizing the prediction model parameters, can timely reflect the health status of the equipment, and effectively prevent potential failures, thereby significantly improving the safety and reliability of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. 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 creative labor. Among them:

[0041] Figure 1 The present invention is a schematic diagram of the overall process of a method for estimating the remaining useful life of a transformer according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0043] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0044] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0045] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0046] At the same time, in the description of the present invention, it should be noted that the orientations or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the orientations or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the system or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0047] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0048] Example 1

[0049] Reference Figure 1 , as an embodiment of the present invention, provides a method for estimating the remaining useful life of a transformer, comprising:

[0050] S100: Acquire first transformer data;

[0051] S102: extracting transformer health status characteristics according to the first transformer data, calculating the health status characteristics, and obtaining the transformer health index;

[0052] S104: inputting the first data and the transformer health index into a first prediction model for prediction to obtain a result of the remaining service life of the transformer;

[0053] It should be noted that the present invention first obtains the first data of the transformer, and extracts key health status features based on these data, and then calculates the health index of the transformer; the health index, as an important basis for evaluating the status of the transformer, is input into the constructed first prediction model together with the first data, so as to accurately predict the remaining service life of the transformer; the present invention not only improves the accuracy of transformer status assessment, but also realizes preventive maintenance of the transformer and optimizes its service life management.

[0054] In the embodiment of the present application, the first transformer data is obtained in the above step S100, and the first transformer data includes historical operation data of the transformer, historical operation environment parameters, real-time operation data and real-time operation environment parameters;

[0055] In an optional embodiment, the transformer historical operation data and real-time operation data may include data such as the transformer's current, voltage, temperature, load rate, oil chromatography analysis results, etc.; current and voltage sensors can monitor the transformer's operating status, temperature sensors can detect the transformer oil temperature and winding temperature, and the load rate can be determined by calculating the ratio of the transformer's actual load to the rated capacity.

[0056] After the first data is acquired, a preprocessing operation is performed on the first data, and the preprocessing operation includes data cleaning, denoising and standardization.

[0057] In the embodiment of the present application, the above step S102 also includes the following sub-steps A1-A2;

[0058] In A1, the health status feature is transformed to obtain a health value, and the health value is compared with a first threshold to obtain a plurality of health scores;

[0059] In A2, the health score is combined with the preset weight values ​​of each health status feature to calculate and obtain the transformer health index;

[0060] In the embodiment of the present application, multiple health scores are compared with preset health thresholds. If the above health score values ​​exceed or are lower than the preset normal range, a corresponding health score is obtained; then the health score of each health status feature is multiplied by the corresponding weight ratio and summed up to obtain the health index of the transformer;

[0061] In an embodiment of the present application, the above-mentioned transformer health index is an evaluation index of the current health status of the transformer. It is calculated by an intelligent algorithm based on the transformer operation data and other relevant information, and is used to measure the health level of the transformer. The level of the health index reflects the degree to which the current state of the transformer is different from the ideal state, which helps to evaluate whether the equipment is in good working condition, whether there is a potential failure risk, and whether maintenance or replacement is required.

[0062] In the embodiment of the present application, the steps of obtaining the above transformer health index are: first, collecting transformer operation data from multiple angles, including but not limited to current, voltage, temperature, oil chromatography analysis results, partial discharge, load conditions, etc.;

[0063] In an optional embodiment, the oil chromatography analysis may be the content of dissolved gases, such as hydrogen, methane, acetylene, etc.;

[0064] In an embodiment of the present application, these data are preprocessed, including but not limited to data cleaning, such as removing noise and processing missing values; data conversion, such as converting non-numeric data into numerical data; feature engineering, such as extracting features that have a greater impact on health status.

[0065] In the embodiment of the present application, the content of dissolved gases in the transformer oil can be known through oil chromatography analysis, and the presence of these gases and changes in their content can reflect insulation aging or potential failures inside the transformer.

[0066] In the embodiment of the present application, based on these pre-processed data, a health index model is established to calculate the health index of the transformer;

[0067] In an optional embodiment, the above health index model may be a rule-based method or a machine learning-based method;

[0068] In an optional embodiment, the rule-based approach can set a series of rules to evaluate the health status according to industry standards or expert experience;

[0069] In an optional embodiment, the machine learning-based method may use algorithms such as random forest, support vector machine, XGBoost, etc., to train the model through a large amount of historical data, thereby deriving a health index that can reflect the current health status.

[0070] In the embodiment of the present application, appropriate weights are assigned to different features, because different features have different degrees of influence on the health status of the transformer; for example, high temperature may accelerate the aging of insulating materials, so the temperature feature may be assigned a higher weight in the health index calculation. Through such a comprehensive analysis, the transformer health index can be obtained;

[0071] It should be noted that the higher the health index, the better the health of the transformer, and vice versa, it means there may be health problems. By regularly calculating the health index, operation and maintenance personnel can timely understand the health status of the transformer and take appropriate maintenance measures accordingly, thereby extending the service life of the equipment and ensuring the stable operation of the power system.

[0072] In the embodiment of the present application, the above step S104 also includes the following sub-steps B1-B4;

[0073] In B1, the original parameters of the input layer, hidden layer and output layer in the first prediction model are set; the first data and the transformer health index are input into the first prediction model for training, and the parameters of each layer of the first prediction model are optimized;

[0074] In the embodiment of the present application, the input data of the input layer is calculated by linear change to obtain the input data of the hidden layer, and the input data of the hidden layer is calculated by a nonlinear activation function to obtain the output data of the hidden layer;

[0075] In the embodiment of the present application, the output data of the hidden layer is first subjected to linear change calculation and then subjected to nonlinear activation function calculation until the output data of the last hidden layer is obtained;

[0076] Specifically, the input data of the first hidden layer is expressed as:

[0077] Z (1) =W (1) x+b (1)

[0078] Where Z (1) is the input value of the first hidden layer, W (1) is the weight matrix of the first hidden layer, which indicates the connection strength between the input layer and the hidden layer. x is the input data of the input layer, and b (1) It is a bias vector used to adjust the activation value of the hidden layer. The superscript represents the data of the hidden layer. Each hidden layer has a different weight matrix and bias vector.

[0079] In the embodiment of the present application, the output data of the last hidden layer is used as the input data of the output layer, and the predicted remaining service life is obtained by calculating according to the nonlinear activation function;

[0080] The input data of the hidden layer is calculated through the nonlinear ReLU activation function to obtain the output data of the first hidden layer. Specifically, it is obtained by the following formula:

[0081] A (1) =ReLU(z (1) )

[0082] Among them, A(1) The output data of the first hidden layer, which means that for the input data, the output of the ReLU function is a larger value between 0 and 1. If the input data is greater than 0, the output is 1; if the input data is less than or equal to 0, the output is 0;

[0083] According to the above two formulas, the output data of the hidden layer is first calculated by linear change and then by nonlinear ReLU activation function until the output data Z of the last hidden layer is obtained. (2) and A (2) , the output data of the last hidden layer is used as the input data of the output layer, and is calculated according to the nonlinear Sigmoid activation function. Thereby, the predicted output data is obtained; specifically, it is obtained according to the following formula:

[0084] Z (3) =W (3) A (2) +b (3)

[0085] Y=Sigmoid(Z (3) )

[0086] Among them, Z (3) is the input value of the output layer, W (3) is the weight matrix of the output layer, which represents the connection strength between the output layer and the second hidden layer. (2) is the input data of the second hidden layer, b (3) is the bias vector, and Y is the output value of the output layer.

[0087] In an optional embodiment, the first prediction model may be a multi-layer perceptron, a convolutional neural network, a recurrent neural network, a long short-term memory network, a gated recurrent unit, etc.;

[0088] Exemplarily, multi-layer perception is used as the first prediction model;

[0089] Specifically, the input layer is responsible for receiving data from multiple sensors, including the current, voltage, temperature, load rate, oil chromatography analysis results of the transformer, and the outdoor temperature, humidity, and environmental pollution degree of the operating environment parameters, a total of eight key parameters, that is, the first preset number of nodes of the input layer is 8;

[0090] These parameters are normalized and converted into a format that is easy for the neural network to process. Both hidden layers use 64 neurons and the ReLU activation function.

[0091] The ReLU activation function is widely used in deep learning models because of its simplicity and ability to effectively alleviate the gradient vanishing problem. It makes the neuron output a positive value of the input value, or zero, which helps the model learn nonlinear features.

[0092] The output layer uses the Sigmoid activation function to output the remaining service life of the transformer.

[0093] In B2, the first data is input into a first prediction model to obtain a predicted remaining useful life;

[0094] Calculating the loss function of the first prediction model to obtain an error value between the predicted remaining useful life and the actual useful life;

[0095] In an optional embodiment, the loss function may be a mean square error, a cross entropy loss, or the like as a loss function;

[0096] In the embodiment of the present application, the error value between the predicted remaining useful life and the actual result is obtained by using the mean square error MSE as the loss function, which is specifically expressed as:

[0097]

[0098] Among them, Y i It is real data. is the predicted data, and m is the number of samples.

[0099] In an embodiment of the present application, the gradient of the first prediction model parameter is calculated, and based on the gradient, the model parameter is iteratively updated through an optimization algorithm until the maximum number of iterations is reached or the error value calculated by the loss function converges to within a second threshold range.

[0100] In B3, the first prediction model is evaluated to obtain a remaining life error value; when the remaining life error value exceeds a third threshold, the preset transformer life estimation model is retrained until the remaining life error value does not exceed the third threshold;

[0101] It should be noted that the present invention obtains transformer operating data and operating environment parameters, obtains a transformer health index based on the transformer operating data, and inputs the transformer health index into a preset transformer life estimation model in combination with the operating environment parameters to obtain the remaining service life of the transformer; by collecting transformer operating data and environmental parameters, then calculating the health index, and inputting it into the life prediction model to obtain the predicted remaining life, precise health management is achieved, and the accuracy and efficiency of the remaining life prediction of transformer equipment are improved.

[0102] The above is a schematic scheme of a method for estimating the remaining useful life of a transformer in this embodiment. It should be noted that the technical scheme of the system for estimating the remaining useful life of the transformer and the technical scheme of the method for estimating the remaining useful life of the transformer described above are of the same concept, and the details of the technical scheme of the system for estimating the remaining useful life of the transformer in this embodiment that are not described in detail can all be referred to the description of the technical scheme of the method for estimating the remaining useful life of the transformer described above.

[0103] The transformer remaining service life estimation system in this embodiment includes:

[0104] A data acquisition module, used for acquiring first transformer data;

[0105] A calculation module, used for extracting the health status characteristics of the transformer according to the first data of the transformer, calculating the health status characteristics, and obtaining the health index of the transformer;

[0106] The prediction module is used to input the first data and the transformer health index into the first prediction model for prediction to obtain the remaining service life result of the transformer.

[0107] This embodiment further provides a calculation device, which is applicable to the case of estimating the remaining service life of a transformer, and includes:

[0108] A memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the method for estimating the remaining useful life of a transformer as proposed in the above embodiment.

[0109] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for estimating the remaining useful life of a transformer as proposed in the above embodiment is implemented.

[0110] The storage medium proposed in this embodiment and the method for estimating the remaining useful life of a transformer proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0111] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ReadOnly, Memory, ROM), random access memory (RandomAccess Memory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods of various embodiments of the present invention.

Claims

1. A method for estimating the remaining useful life of a transformer, characterized in that: include: Obtaining first transformer data; Extracting transformer health status characteristics according to the transformer first data, calculating the health status characteristics, and obtaining a transformer health index; The first data and the transformer health index are input into a first prediction model for prediction to obtain a result of the remaining service life of the transformer.

2. The method for estimating the remaining useful life of a transformer according to claim 1, characterized in that: Calculating the health status characteristics to obtain the transformer health index includes: Converting the health status feature to obtain a health value, and comparing the health value with a first threshold to obtain a plurality of health scores; The health score is combined with the preset weight values ​​of each health status feature to perform calculations to obtain the transformer health index.

3. The method for estimating the remaining useful life of a transformer according to claim 1 or 2, characterized in that: Inputting the first data and the transformer health index into a first prediction model for prediction includes: Set the original parameters of the input layer, hidden layer and output layer in the first prediction model; The first data and the transformer health index are input into a first prediction model for training to optimize the parameters of each layer of the first prediction model.

4. The method for estimating the remaining useful life of a transformer according to claim 3, characterized in that: Optimizing the parameters of each layer of the first prediction model includes: Inputting the first data into the first prediction model to obtain a predicted remaining useful life; Calculating the loss function of the first prediction model to obtain an error value between the predicted remaining useful life and the actual useful life; The gradient of the first prediction model parameter is calculated, and according to the gradient, the model parameter is iteratively updated through an optimization algorithm until a maximum number of iterations is reached or an error value calculated by the loss function converges to a second threshold range.

5. The method for estimating the remaining useful life of a transformer according to claim 4, characterized in that: The first prediction model includes, The input data of the input layer is calculated by linear change to obtain the input data of the hidden layer, and the input data of the hidden layer is calculated by a nonlinear activation function to obtain the output data of the hidden layer; The output data of the hidden layer is first subjected to linear change calculation and then subjected to nonlinear activation function calculation until the output data of the last hidden layer is obtained; The output data of the last hidden layer is used as the input data of the output layer, and is calculated according to the nonlinear activation function to obtain the predicted remaining service life.

6. The method for estimating the remaining useful life of a transformer according to claim 5, characterized in that: Also includes, Evaluating the first prediction model to obtain a remaining life error value; When the remaining life error value exceeds a third threshold, the preset transformer life estimation model is retrained until the remaining life error value does not exceed the third threshold.

7. The method for estimating the remaining useful life of a transformer according to claim 1, wherein: The first data of the transformer includes, The transformer first data includes transformer historical operation data, historical operation environment parameters, real-time operation data and real-time operation environment parameters; After acquiring the first data, a preprocessing operation is performed on the first data, and the preprocessing operation includes data cleaning, denoising and standardization.

8. A system for estimating the remaining useful life of a transformer, characterized in that: include, A data acquisition module, used for acquiring first transformer data; A calculation module, used for extracting the health status characteristics of the transformer according to the first data of the transformer, calculating the health status characteristics, and obtaining the health index of the transformer; The prediction module is used to input the first data and the transformer health index into a first prediction model for prediction to obtain the remaining service life result of the transformer.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the transformer remaining service life estimation method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for estimating the remaining useful life of a transformer as claimed in any one of claims 1 to 7.

Images