SiC MOSFET life prediction method and device based on WOA-LSTM, and storage medium

Abstract

The invention discloses a WOA-LSTM-based SiC MOSFET life prediction method and device, and a storage medium, and relates to the technical field of reliability prediction of power electronic equipment. The method comprises the following steps: selecting drain-source electrode voltage as an aging characteristic parameter of the SiC MOSFET, and acquiring voltage data in real time in an aging test process by using a sensor; the collected voltage data are preprocessed, abnormal values are eliminated, missing values are supplemented, and the data are smoothed; the method comprises the following steps: optimizing parameters of a long short-term memory network LSTM through a whale optimization algorithm WOA, and constructing a WOA-LSTM prediction model; and initializing a WOA-LSTM model, inputting voltage data for training, and establishing a mapping relation between the service life of the SiC MOSFET and the voltage to realize prediction of the residual service life of the SiC MOSFET. The SiC MOSFET service life prediction model has the advantages of being high in adaptability, low in calculation complexity, high in prediction precision and the like, can be widely applied to the fields of the semiconductor industry, new energy automobiles, industrial automation and the like, and provides powerful support for health management and maintenance of equipment.

Description

Technical Field

[0001] The present application relates to the technical field of reliability prediction of power electronic devices, and particularly relates to a method, device and storage medium for predicting the life of SiC MOSFET based on WOA-LSTM. Background Art

[0002] With the rapid development of power electronic technology, as a core component in power electronic devices, the reliability of SiC MOSFET has an important impact on the overall performance of the system. However, since the aging process of SiC MOSFET is affected by various factors, such as electrical, thermal, mechanical stress, etc., traditional life prediction methods often have difficulty in accurately predicting its remaining service life. Therefore, developing a method for predicting the life of SiC MOSFET based on WOA-LSTM is of great significance for improving the reliability of power electronic devices and reducing maintenance costs. At present, some data-driven life prediction methods have been proposed, such as prediction methods based on machine learning algorithms such as neural networks and support vector machines. However, these methods still need to be improved in terms of prediction accuracy, generalization ability, etc. At the same time, due to the complex and variable aging process of SiC MOSFET, traditional prediction methods often have difficulty in meeting the life prediction requirements under different operating conditions.

[0003] It can be seen that when the traditional data-driven model predicts the life of SiC MOSFET, there are often problems such as strong dependence on data quality and easy to fall into local optimal solutions, resulting in low prediction accuracy. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, device and storage medium for predicting the life of SiC MOSFET based on WOA-LSTM for the above technical problems.

[0005] The present specification adopts the following technical solutions:

[0006] The present specification provides a method for predicting the life of SiC MOSFET based on WOA-LSTM, including:

[0007] Select the drain-source voltage as the aging characteristic parameter of SiC MOSFET, and use a sensor to obtain voltage data in real time during the aging test;

[0008] Preprocess the collected voltage data to eliminate outliers, supplement missing values, and smooth the data;

[0009] Optimize the parameters of the long short-term memory network LSTM through the whale optimization algorithm WOA to construct a WOA-LSTM prediction model;

[0010] Initialize the WOA-LSTM model and input voltage data for training, establish the mapping relationship between the SiC MOSFET lifetime and voltage, and realize the prediction of the remaining lifetime of SiC MOSFETs.

[0011] Preferably, the sensor is used to obtain voltage data in real time during the aging test, which specifically includes: based on the accelerated aging test of SiC MOSFETs, according to the working principle and failure mechanism of SiC MOSFETs, select the key voltage parameters closely related to their lifetime, and collect them through voltage sensors.

[0012] Preferably, the preprocessing of the collected voltage data specifically includes: cleaning the original voltage data collected, using statistical methods to identify and remove outliers in the data, using filters to remove high-frequency noise, and filling by interpolation method, or deleting the records containing missing values according to specific situations.

[0013] Preferably, the parameters of the long short-term memory network LSTM are optimized by the whale optimization algorithm WOA, which specifically includes:

[0014] Apply the optimal parameter configuration searched by the WOA algorithm to the LSTM model to construct the WOA-LSTM prediction model, and these parameters include the learning rate, the number of hidden units, the number of iterations, etc.

[0015] Preferably, the initialization of the WOA-LSTM model specifically includes:

[0016] Initialize the parameters of the LSTM, including the number, weights, and biases between neurons, the number of layers of the LSTM model, and the selection of the internal optimizer;

[0017] Initialize the WOA algorithm parameters, including the size of the whale population, the positions of the whale population, and the number of iterations of the algorithm.

[0018] Preferably, the training with input voltage parameters specifically includes:

[0019] Divide the preprocessed voltage data into a training set and a validation set, use the training set data to train the constructed WOA-LSTM prediction model, and continuously adjust the parameters of the WOA algorithm according to the performance indicators on the validation set to improve the optimization process.

[0020] Preferably, the realization of the prediction of the remaining lifetime of SiC MOSFETs specifically includes:

[0021] In each iteration, the WOA algorithm is used to optimize the parameters of the LSTM network. In each iteration, the WOA algorithm calculates the fitness value according to the position of each whale in the current population (i.e., the parameter combination of the LSTM model), and updates the position of the whale according to the fitness value to find a better parameter combination of the LSTM model. Repeat the above steps until the preset number of iterations is reached or the convergence condition is met, and obtain the result of the remaining life of the SiC MOSFET.

[0022] This specification provides a computer-readable storage medium storing a computer program, which when executed by a processor implements the above-mentioned method for predicting the life of a SiC MOSFET based on WOA-LSTM.

[0023] This specification provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the above-mentioned method for predicting the life of a SiC MOSFET based on WOA-LSTM.

[0024] In a method for predicting the life of a SiC MOSFET based on WOA-LSTM provided in this specification, compared with the prior art, the beneficial effects are as follows:

[0025] The present invention combines the advantages of the WOA algorithm and the LSTM network, optimizes the parameters of the LSTM network through the WOA algorithm, and constructs a WOA-LSTM prediction model, which can effectively search for the optimal solution or a parameter combination close to the optimal solution in a complex parameter space, find a better solution in a short time, thereby improving the efficiency of model training and prediction. At the same time, it can be widely applied to fields such as the semiconductor industry, new energy vehicles, and industrial automation, providing strong support for the health management and maintenance of equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings described herein are used to provide a further understanding of the present application and form a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings:

[0027] Figure 1 It is a schematic flow chart of a method for predicting the life of a SiC MOSFET provided in this specification;

[0028] Figure 2 It is a simple circuit platform design for the DC power cycle test in this embodiment;

[0029] Figure 3 It is the drain-source voltage of the SiC MOSFET collected corresponding to a constant current of 15 A and a temperature of 150 °C in this embodiment;

[0030] Figure 4 is the drain-source voltage of the SiC MOSFET after data processing in this embodiment;

[0031] Figure 5 is the LSTM network topology structure in this embodiment;

[0032] Figure 6 is the SiC MOSFET life prediction result graph based on the traditional LSTM model in this embodiment;

[0033] Figure 7 is the SiC MOSFET life prediction result graph based on the WOA-LSTM model in this embodiment. Detailed implementation manners

[0034] To make the objectives, technical solutions, and advantages of this specification clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of them. Based on the embodiments in the specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this application.

[0035] SiC MOSFET life prediction based on traditional data-driven models usually performs model training and verification on specific datasets, which results in limited generalization ability of the models under other datasets or operating conditions. When the operating environment or conditions of the SiC MOSFET change, these models may not be able to provide accurate prediction results.

[0036] Therefore, this specification provides a SiC MOSFET life prediction method based on WOA-LSTM, which can effectively search for the optimal solution or a parameter combination close to the optimal solution in a complex parameter space, find a better solution in a short time, thereby improving the efficiency of model training and prediction, and solving the problems of strong dependence on data quality in SiC MOSFET life prediction under traditional data-driven models and the traditional data-driven models being prone to falling into local optimal solutions, resulting in low prediction accuracy.

[0037] In a method for predicting the lifespan of SiC MOSFETs based on WOA-LSTM proposed in this specification, a WOA-LSTM prediction model is constructed to predict the lifespan of SiC MOSFETs. This model is an optimization and prediction method that combines the Whale Optimization Algorithm (WOA) and Long Short-Term Memory networks (LSTM). The Whale Optimization Algorithm is a new type of heuristic optimization algorithm. It simulates the social behavior of humpback whales and introduces a bubble net for hunting. As social mammals, humpback whales will surround and hunt prey through mutual cooperation during hunting. Whales have two behaviors in group hunting: surrounding and driving. Whales in the group move towards other whales to surround the prey and swim in a circle while spraying bubbles to form a bubble net to drive the prey. This unique hunting method is called the bubble net foraging method. The WOA algorithm is based on this hunting behavior and searches for the optimal solution by simulating the search behavior of whales, with the ability of global search and local search. LSTM ensures the preservation of long-term and short-term memories by introducing gating mechanisms such as forget gates, input gates, and output gates, and linearly transmitting information along the time axis, similar to a continuously flowing information conveyor belt. Among them, the forget gate is responsible for controlling the forgetting of information from the cell state, the input gate determines the new information to be added to the cell state, and the output gate controls the information to be output as the hidden state to the subsequent layer or for the final prediction.

[0038] Normally, the traditional LSTM network is commonly used as a method for predicting the lifespan of IGBTs. However, in large-scale datasets or complex models, the training and inference processes of this method may be slow, requiring more computing resources. High complexity may also cause the model to be more prone to overfitting problems during training, being highly dependent on data quality, and the training process may fall into local optimal solutions, resulting in inaccurate prediction results.

[0039] Compared with traditional data-driven prediction models such as LSTM, the WOA-LSTM model provided in this specification combines the advantages of the Whale Optimization Algorithm (WOA) and Long Short-Term Memory networks (LSTM). By using WOA to optimize the key parameters of the LSTM network, the prediction accuracy and generalization ability of the LSTM model are improved. WOA simulates the foraging behavior of the whale group, finds the optimal parameter combination through iterative optimization, and then these optimized parameters are used to construct the LSTM network, enabling the LSTM to more effectively process time series data, capture long-term dependencies in the data, and thus achieve more accurate predictions.

[0040] The following will, in conjunction with the accompanying drawings, elaborate on the technical solutions provided by each embodiment of this application in detail.

[0041] Figure 1 This is a schematic diagram of the process of a SiC MOSFET life prediction method based on WOA-LSTM in this specification, which specifically includes the following steps:

[0042] S101: Select the drain-source voltage as the aging characteristic parameter of the SiC MOSFET, and use a sensor to obtain voltage data in real time during the aging test; specifically including:

[0043] Based on the accelerated aging test of the SiC MOSFET, according to the working principle and failure mechanism of the SiC MOSFET, select the key voltage parameters closely related to its life, and collect them through a voltage sensor.

[0044] S102: Preprocess the collected voltage data to eliminate outliers, supplement missing values, and smooth the data, specifically including:

[0045] Clean the original voltage data collected, use statistical methods to identify and remove outliers in the data, use a filter to remove high-frequency noise, and fill it through interpolation, or select to delete the records containing missing values according to the specific situation.

[0046] S103: Optimize the parameters of the long short-term memory network LSTM through the whale optimization algorithm WOA to construct a WOA-LSTM prediction model, specifically including:

[0047] Apply the optimal parameter configuration searched by the WOA algorithm to the LSTM model to construct a WOA-LSTM prediction model. These parameters include the learning rate, the number of hidden units, the number of iterations, etc.

[0048] S104: Initialize the WOA-LSTM model and input voltage data for training, establish the mapping relationship between the SiC MOSFET life and voltage, and realize the prediction of the remaining life of the SiC MOSFET, specifically including:

[0049] Initialize the parameters of the LSTM, including the number of neurons, weights, biases, the number of layers of the LSTM model, and the selection of the internal optimizer;

[0050] Initialize the parameters of the WOA algorithm, including the size of the whale population, the positions of the whale population, and the number of iterations of the algorithm.

[0051] Input voltage parameters for training, including dividing the preprocessed voltage data into a training set and a validation set, using the training set data to train the constructed WOA-LSTM prediction model, and continuously adjusting the parameters of the WOA algorithm according to the performance indicators on the validation set to improve the optimization process.

[0052] In each iteration, the WOA algorithm is used to optimize the parameters of the LSTM network. In each iteration, the WOA algorithm calculates the fitness value according to the position of each whale in the current population (i.e., the parameter combination of the LSTM model), and updates the position of the whale according to the fitness value to find a better parameter combination of the LSTM model. Repeat the above steps until the preset number of iterations is reached or the convergence condition is met, and obtain the result of the remaining life of the SiC MOSFET.

[0053] It should be noted that the SiC MOSFET accelerated aging test is mainly a test method that simulates the power cycle conditions of the SiC MOSFET in actual operation to accelerate its aging process. In this experiment, power is continuously applied to the SiC MOSFET to make it periodically switch between the on and off states, thereby using the thermal stress generated inside the device to impact the SiC MOSFET and accelerate its aging failure. The power cycle aging experiment can effectively evaluate the reliability and life of the SiC MOSFET under long-term use, and provide a basis for the design and optimization of products. The simple circuit platform design of its power cycle test is as Figure 2 shown.

[0054] Embodiment

[0055] The SiC MOSFET life prediction method proposed in this embodiment adds the WOA optimization algorithm to the traditional SiC MOSFET life prediction method. On this premise, the above scheme uses the position of each whale to calculate the fitness, and finds the optimal solution by updating the position of the whale according to the fitness value to address the problem of strong data quality dependence and easy to fall into local optimal solutions in the SiC MOSFET life prediction under the traditional data-driven model; during the prediction process, the WOA-LSTM algorithm will continuously update the parameters of the LSTM network to adapt to the changes in the input data and improve the prediction accuracy.

[0056] The flowchart of the SiC MOSFET life prediction method based on the WOA-LSTM model is as Figure 1 shown. This embodiment specifically includes the following steps:

[0057] Step 1: Select the drain-source voltage as the aging characteristic parameter of the SiC MOSFET, and use a sensor to obtain voltage data in real time during the aging test.

[0058] The aging test process of the SiC MOSFET in this embodiment specifically includes:

[0059] Power the aging board or test board through the device, apply a periodically varying load current to the SiC MOSFET to simulate the junction temperature variation in actual use. During the test, repeatedly heat and cool the device by controlling the turn-on and turn-off of the current, thereby accelerating its aging process, and monitor the change of the drain-source voltage in real time to evaluate the package reliability and aging characteristics of the device.

[0060] In addition, the key parameter of the SiC MOSFET collected is the drain-source voltage of the SiC MOSFET corresponding to a constant current of 15 A and a temperature of 150 °C, as Figure 3 shown.

[0061] Step 2: Preprocess the collected voltage data to eliminate outliers, supplement missing values, and smooth the data, specifically including:

[0062] Eliminate the collected voltage outliers. This step aims to identify and remove those values that significantly deviate from the normal data range. These outliers may be caused by measurement errors, equipment failures, or external interferences, etc. A reasonable threshold range can be set, and data points outside this range are regarded as outliers and removed, or statistical methods such as boxplot can be used to automatically identify and exclude outliers.

[0063] Supplement the possible missing values in the data. Missing data will affect the accuracy and reliability of subsequent analysis. The methods for dealing with missing values can directly delete the records containing missing values (if the missing ratio is not high) and use interpolation methods (such as linear interpolation, polynomial interpolation, etc.) to estimate the missing values based on adjacent data points.

[0064] Smoothing the data is beneficial to reducing the random noise in the data and making the data change trend clearer. The commonly used mean filtering method is used. The basic principle of mean filtering is to replace each pixel value in the original image with the mean value, that is, for the current pixel point (x, y) to be processed, select a template, which consists of several adjacent pixels of it, calculate the mean value of all pixels in the template, and then assign this mean value to the current pixel point (x, y) as the gray value g(x, y) of the processed image at this point. Its expression is

[0065]

[0066] In the above expression, m is the total number of pixels including the current pixel in the template. The drain-source voltage of the SiC MOSFET after data processing is as Figure 4 shown.

[0067] Step 3: Optimize the parameters of the long short-term memory network LSTM through the whale optimization algorithm WOA to construct a WOA-LSTM prediction model.

[0068] It should be noted that the advantage of combining WOA and LSTM lies in that the global search ability and high efficiency of the Whale Optimization Algorithm (WOA) can make up for the deficiencies of the LSTM network in parameter optimization; while the complex structure and strong learning ability of the LSTM network can make full use of the optimization results of the WOA, further improving the performance of the model.

[0069] The specific steps to optimize the parameters of the LSTM network through the WOA algorithm and construct the WOA-LSTM prediction model are as follows: Apply the optimal parameter configuration searched by the WOA algorithm to the LSTM model to construct the WOA-LSTM prediction model, and these parameters include the learning rate, the number of hidden units, the number of iterations, etc.

[0070] It should be noted that LSTM is a special recurrent neural network dedicated to processing and predicting sequence data with long-term dependencies. The LSTM model consists of a series of LSTM modules, and each LSTM module contains three key gating structures: the forget gate, the input gate, and the output gate. As Figure 5 shown, these gating structures determine whether to pass, discard, or update information through the learned weights and activation functions.

[0071] The forget gate uses the Sigmoid activation function to transform the memory cell at the previous moment and the input at the current moment t into a value between 0 and 1. 0 means discarding all information, and 1 means retaining all information. This value determines how much information is retained. The forget gate f t The calculation formula is:

[0072] f t = σ(W f [h t-1 , x t + b f ) (2)

[0073] In the formula, σ is the Sigmoid function; W f is the weight matrix of the forget gate; h t-1 is the output neuron; x t is the input neuron at the current moment; b f is the bias term of the forget gate.

[0074] The input gate has two parts: The first part is the Sigmoid layer, which determines the state of updating the memory cell; the second part is the tanh layer, which creates a new candidate memory cell state. The input gate I t The calculation formula is:

[0075] I t = σ(W I [h t-1 , x t+b I ) (3)

[0076]

[0077] Wherein, W I is the input gate weight matrix; b I , b c are the bias terms of the input gate and the cell state respectively; C t is the alternative update information; tanh is the activation function; W c is the memory cell weight matrix; C t is the memory cell state.

[0078] The output gate determines the output value of the unit state. First, use the Sigmoid layer to determine which part is output, then process it through tanh and multiply it by the output of the Sigmoid function. The output gate O t The calculation formula is:

[0079] O t =σ(W o [h t-1 , x t +b o ) (6)

[0080] h t =O t tanhC t (7)

[0081] Wherein, W o is the output gate weight matrix; b o is the output gate bias term.

[0082] It should be noted that WOA simulates the strategies of whales in hunting and predation behaviors, and has global search ability, good stability and convergence accuracy. The algorithm mainly includes three parts: surrounding prey, bubble-net predation, and searching for prey.

[0083] In the stage of surrounding prey, the size of the whale population is set to N, and the position of the i-th whale in space is d represents the dimension of the search space. The optimal position of the prey in the group, that is, the corresponding global optimal solution, and other whales will gradually approach and surround this position, and update the position using equations (8) and (9):

[0084] D = |CX * (t)-X(t)| (8)

[0085] X(t + 1) = X * (t)-AD (9)

[0086] Wherein, t is the current iteration number; X* (t) is the current prey position; X(t) is the current individual position; D is the distance between the whale and the prey; A and C are position coefficients, defined as follows:

[0087] A = 2αr1 - α (10)

[0088] C = 2r2 (11)

[0089] Where r1 and r2 are random values in [0, 1]; α is the convergence factor, which can be defined by the following expression:

[0090] α = 2 - 2t / T (12)

[0091] Where T is the maximum number of iterations.

[0092] In the bubble net hunting stage, by calculating the distance between the position (X, Y) and the position (X * , Y * ), using the spiral position update method, the position distance between the whale and the prey is updated, simulating the way the whale attacks the prey in a spiral, and its expression is as follows:

[0093]

[0094] Where D t is the distance between the whale and the prey; b is a constant that limits the spiral; l is a random number between [-1, 1]; during the continuous optimization process, in order to simulate the whale approaching the prey along the path surrounded by the spiral, the update probability p is usually set to 0.5.

[0095] In the prey search stage, in order to improve the global search ability of the algorithm and avoid falling into local optima, that is, when A ≥ 1, the algorithm randomly searches for the position of the prey, and the expression for this stage is as follows:

[0096]

[0097] Where is the position of a randomly selected whale in the whale population.

[0098] Finally, by initializing the WOA-LSTM model and inputting voltage data for training, the mapping relationship between the SiC MOSFET life and voltage is established, and the prediction of the remaining life of the SiC MOSFET is realized.

[0099] It should be noted that the parameters of the LSTM are initialized, including the number of neurons, weights, biases, the number of layers of the LSTM model, and the choice of the internal optimizer; the parameters of the WOA algorithm are initialized, including the size of the whale population, the positions of the whale population, and the number of iterations of the algorithm.

[0100] It should be noted that the preprocessed voltage data is divided into a training set and a validation set. The constructed WOA-LSTM prediction model is trained using the training set data. According to the performance metrics on the validation set, the parameters of the WOA algorithm are continuously adjusted to improve the optimization process.

[0101] In each iteration, the WOA algorithm is used to optimize the parameters of the LSTM network. In each iteration, the WOA algorithm calculates the fitness value according to the position of each whale in the current population (i.e., the parameter combination of the LSTM model), and updates the position of the whale according to the fitness value to find a better parameter combination of the LSTM model. Repeat the above steps until the preset number of iterations is reached or the convergence condition is met, and obtain the result of the remaining life of the SiC MOSFET. Compare the WOA-LSTM prediction result with the traditional LSTM prediction result, as Figure 6 and Figure 7 shown.

[0102] According to Figure 6 and Figure 7 the prediction results, it can be seen that the WOA-LSTM prediction method in this embodiment effectively improves the prediction accuracy in the life prediction of SiC MOSFET compared with the traditional LSTM prediction method.

[0103] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, 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, it should be considered as the scope recorded in this specification.

Claims

1. A method for predicting the lifespan of SiC MOSFET based on WOA-LSTM, characterized in that, include: The drain-source voltage is selected as the aging characteristic parameter of SiC MOSFET, and the voltage data is obtained in real time by using a sensor during the aging test; Preprocess the collected voltage data to eliminate outliers, supplement missing values, and smooth the data; The parameters of the long short-term memory network LSTM are optimized through the whale optimization algorithm WOA, and the WOA-LSTM prediction model is constructed; Initialize the WOA-LSTM model and input voltage data for training, establish the mapping relationship between SiC MOSFET life and voltage, and realize the prediction of the remaining life of SiC MOSFET.

2. The WOA-LSTM-based SiC MOSFET lifetime prediction method according to claim 1, wherein, The method of using a sensor to obtain voltage data in real time during the aging test specifically includes: Based on the accelerated aging test of SiC MOSFET, according to the working principle and failure mechanism of SiC MOSFET, key voltage parameters closely related to its life are selected and collected through voltage sensors.

3. The method for predicting the lifespan of SiC MOSFET based on WOA-LSTM according to claim 1, wherein, The preprocessing of the collected voltage data specifically includes: The collected raw voltage data is cleaned, and outliers in the data are identified and eliminated using statistical methods. High-frequency noise is removed using filters, and interpolation is used to fill in the data, or records with missing values ​​are deleted according to specific circumstances.

4. The method for predicting the lifespan of SiC MOSFET based on WOA-LSTM according to claim 1, wherein, The Whale Optimization Algorithm (WOA) is used to optimize the parameters of the Long Short-Term Memory (LSTM) network, specifically including: The optimal parameter configuration searched by the WOA algorithm is applied to the LSTM model to build a WOA-LSTM prediction model. These parameters include learning rate, number of hidden units, number of iterations, etc.

5. The WOA-LSTM-based SiC MOSFET lifetime prediction method according to claim 1, wherein The initialization of the WOA-LSTM model specifically includes: Initializing the LSTM parameters, including the number of neurons, weights, biases, the number of layers of the LSTM model, and the selection of an internal optimizer; The initialization WOA algorithm parameters include the size of the whale population, the location of the whale population and the number of iterations of the algorithm.

6. The method for predicting the SiC MOSFET lifetime based on WOA-LSTM according to claim 1, wherein, The input voltage parameters are trained, specifically including: The preprocessed voltage data is divided into a training set and a validation set. The constructed WOA-LSTM prediction model is trained using the training set data. According to the performance indicators on the validation set, the parameters of the WOA algorithm are continuously adjusted to improve the optimization process.

7. The method for predicting the lifespan of SiC MOSFET based on WOA-LSTM according to claim 1, wherein The prediction of the remaining life of SiC MOSFET specifically includes: In each iteration, the WOA algorithm is used to optimize the parameters of the LSTM network. In each iteration, the WOA algorithm calculates the fitness value based on the position of each whale in the current population (i.e., the parameter combination of the LSTM model), and updates the position of the whale based on the fitness value to find a better LSTM model parameter combination. Repeat the above steps until the preset number of iterations is reached or the convergence condition is met, and the result of the remaining life of the SiC MOSFET is obtained.

8. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. A computer device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the method according to any one of claims 1 to 7 above.

Images