An IGBT residual life prediction method based on variational bayes and mixed wiener process

Abstract

The application discloses an IGBT residual life prediction method based on a variational Bayes and a mixed Wiener process, and belongs to the technical field of IGBT residual life prediction. The method comprises the following steps: S1, defining a mixed Wiener process and establishing a degradation model to describe the degradation trajectory of an IGBT; S2, performing offline parameter estimation based on a variational Bayes algorithm by using prior samples; S3, performing optimal model selection in the degradation model according to an autocorrelation determination method; S4, selecting a prior sample most similar to a test sample at a current moment; S5, online updating the mean value and variance of a weight vector of the test sample; S6, obtaining a probability density function of the residual life of the mixed Wiener process in the sense of a first passage time, and estimating the residual life value of the IGBT at each moment. The IGBT residual life prediction method based on the variational Bayes and the mixed Wiener process can automatically determine a degradation mode, improve the fitting precision of the degradation trajectory of the IGBT, reduce the requirement for professionalism, and improve the universality of the model.

Description

Technical Field

[0001] The present invention relates to the technical field of IGBT remaining life prediction, and in particular to an IGBT remaining life prediction method based on variational Bayesian and hybrid Wiener process. Background Art

[0002] With the continuous development of modern society, higher safety and reliability requirements are being placed on infrastructure equipment. Accurately predicting the remaining life of insulated-gate bipolar transistor (IGBT) chips, core components that determine high-speed rail starting and braking speeds, operating speed adjustments, and energy efficiency, is a critical task. This can improve system reliability, reduce failure risks, and minimize economic costs. The degradation process of IGBTs can lead to complex, multi-stage degradation scenarios due to internal mechanisms or changes in external operating conditions. Existing studies have typically selected one of several typical models as the degradation model, which can lead to inaccurate descriptions of the IGBT degradation trajectory. Therefore, a method is needed that automatically determines the form of the degradation model without manual specification, can simultaneously select one or more drift terms, and fuse them into a degradation model that can describe complex degradation trajectories. Furthermore, for ease of use and practicality, the proposed model should maintain a high degree of simplicity and interpretability, and require online parameter updates to reflect individual variability and reduce the need for historical samples. Therefore, a method for predicting the remaining life of IGBTs that meets these requirements is urgently needed. Summary of the Invention

[0003] The purpose of the present invention is to provide an IGBT remaining life prediction method based on variational Bayesian and hybrid Wiener process, which can automatically determine the degradation mode and describe complex degradation trajectories, improve the fitting accuracy of the IGBT degradation trajectory, reduce the requirements for professionalism, and improve the versatility of the model.

[0004] To achieve the above object, the present invention provides an IGBT remaining life prediction method based on variational Bayesian and hybrid Wiener process, comprising the following steps:

[0005] S1. Define the hybrid Wiener process and establish a degradation model to describe the degradation trajectory of IGBT;

[0006] S2, using prior samples to perform offline parameter estimation based on the variational Bayes algorithm;

[0007] S3. selecting an optimal model among the degradation models according to an automatic correlation determination method;

[0008] S4, select the prior sample that is most similar to the test sample at the current moment;

[0009] S5. Update the mean and variance of the weight vector of the test sample online;

[0010] S6. Calculate the probability density function of the remaining life of the mixed Wiener process in terms of the first arrival time, and estimate the remaining life value of the IGBT at each moment.

[0011] Preferably, S2 specifically includes the following steps:

[0012] S2.1. According to the nth prior sample t k time and t k-1 The degradation model at time Δx is used to calculate the difference in degradation amount. nk Expressions of

[0013] S2.2. Find Δx nk Composed vector Likelihood function of ;

[0014] S2.3. Normalize all data from the same sensor to the same scale so that the maximum value is 1;

[0015] S2.4. Give the distribution of prior parameters and conjugate prior distribution;

[0016] S2.5. Update the variational solution of each unknown parameter in turn according to the variational Bayesian algorithm;

[0017] S2.6. Calculate the variational lower bound ELBO;

[0018] S2.7. Iterate the parameter update until the difference between the variational lower bound values ​​of two iterations is less than the preset threshold or the number of iterations is greater than 1000. Stop the iteration and obtain the final parameter estimate.

[0019] Preferably, S3 specifically includes the following steps:

[0020] S3.1. Based on the current parameter estimates obtained in S2.7, complete model selection according to the automatic correlation determination method;

[0021] S3.2. Iterate the parameter estimation of S2 and the model selection of S3.1 until only one model term remains.

[0022] S3.3. Select the term vector corresponding to the largest variational lower bound value as the optimal model.

[0023] Preferably, S4 specifically includes the following steps:

[0024] S4.1. Calculate the Euclidean distance and DTW distance between the degradation sequence of the test sample and all prior samples from the initial moment to the current moment respectively;

[0025] S4.2. Calculate the score of each prior sample at the current moment;

[0026] S4.3. Select the prior sample corresponding to the smallest score as the most similar sample to the test sample at the current moment.

[0027] Preferably, S5 specifically includes the following steps:

[0028] S5.1. Based on the prior parameter distribution of the most similar training sample and the sequential Bayesian algorithm, calculate the posterior distribution of the weight vector at the current moment;

[0029] S5.2. Simplify the posterior distribution of the weight vector and update the mean and variance of the weight vector of the test sample online.

[0030] Therefore, the present invention adopts the above-mentioned IGBT remaining life prediction method based on variational Bayesian and hybrid Wiener process, which can automatically determine the degradation mode and describe complex degradation trajectories, improve the fitting accuracy of IGBT degradation trajectories, reduce the requirements for professionalism, and improve the versatility of the model.

[0031] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 is a diagram of an IGBT remaining life prediction method based on variational Bayesian and hybrid Wiener process of the present invention;

[0033] Figure 2 It is a degradation path combination diagram of an IGBT remaining life prediction method based on variational Bayesian and hybrid Wiener process of the present invention;

[0034] Figure 3 This is a probability density function diagram of the remaining life of an IGBT remaining life prediction method based on variational Bayesian and mixed Wiener process of the present invention;

[0035] Figure 4 It is a remaining life estimation diagram of an IGBT remaining life prediction method based on variational Bayesian and hybrid Wiener process of the present invention;

[0036] Figure 5 This is a comparison diagram of the absolute error of the remaining life of an IGBT remaining life prediction method based on variational Bayesian and hybrid Wiener process of the present invention. DETAILED DESCRIPTION

[0037] The technical solution of the present invention is further described below with reference to the accompanying drawings and embodiments.

[0038] Unless otherwise defined, technical or scientific terms used in the present invention shall have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs.

[0039] Example 1

[0040] like Figure 1 As shown, the present invention provides an IGBT remaining life prediction method based on variational Bayesian and hybrid Wiener process, comprising the following steps:

[0041] S1. Define the hybrid Wiener process and establish a degradation model to describe the degradation trajectory of IGBT;

[0042] A degradation model that can automatically determine the form and quantity of drift terms is established, called a mixed Wiener process, which is expressed as:

[0043]

[0044] in,

[0045]

[0046] Moreover, X(t) is the degradation value at time t, x0 is the initial degradation amount, F(t) is the nonlinear drift term after the weighting of P functions, θ is the weight vector, σ B is the diffusion coefficient, B(t) is the standard Brownian motion, and f(·) represents an arbitrary function. For simplicity, x0 is assumed to be 0. When x0 is non-zero, this assumption can be simply implemented by subtracting the initial degradation amount x0 from the degradation value X(t).

[0047] S2. Use prior samples to perform offline parameter estimation based on the variational Bayesian algorithm; specifically, the following steps are included:

[0048] Assume that there are n prior IGBT samples available for training. These prior samples have known full life cycle degradation data (collector-emitter saturation voltage is used as the degradation quantity here) and are of the same type as the test samples.

[0049] S2.1. According to the nth prior sample t k time and t k-1 The degradation model at time Δx is used to calculate the difference in degradation amount. nk Expressions of

[0050]

[0051] Where ΔX n (t k )=X n (t k )-X n (tk-1 ) and Δt k =t k -t k-1 (n∈{1,2,...,N}), N represents the number of prior samples, k∈{2,3,...,K n}, t k Indicates the current time, K n Represents the total number of state monitoring data of the nth prior sample.

[0052] S2.2. Find Δx nk Composed vector Likelihood function of ;

[0053] For the convenience of expression, let ΔF nk =F n (t k )-F n (t k-1 ), Δx nk represents ΔX n (t k ), Obviously, ΔX n It obeys the multivariate normal distribution, and its likelihood function is:

[0054]

[0055] in, represents a normal distribution about x, with mean and variance ΔF respectively nk and

[0056] S2.3. Normalize all data from the same sensor to the same scale so that the maximum value is 1;

[0057] Let Δf nk =f n (t k )-f n (t k-1 ), then ΔF nk =Δf nk θ n ; Then, all data from the same sensor are normalized to the same scale so that the maximum value is 1, that is: Δf p (k) = Δf p (k) / Zoom(p), where Δf p (k) = f p (k)-f p (k-1) and Zoom(p)=max{Δf p (1),Δf p (2),...,Δf p (KN )}; In addition, due to the incomplete degradation data of the test samples in the online stage, the Zoom(p) of the preprocessed corresponding most similar prior sample is selected as its normalization scale.

[0058] S2.4. Give the distribution of prior parameters and conjugate prior distribution;

[0059] variance The conjugate prior distribution of is the inverse Gamma distribution. For the convenience of calculation, we use ξ n express The reciprocal of ; and the commonly used joint conjugate prior assumptions for normal distribution and Gamma distribution are:

[0060]

[0061] Among them, G(ξ n |α0,β0) represents the Gamma distribution about x, whose shape parameter and scale parameter are α0 and β0 respectively. is the corresponding hyperparameter,

[0062] Then, in order to simplify the computational complexity, the Gamma distribution is introduced as Prior:

[0063]

[0064] Among them, δ0 and γ0 are hyperparameters.

[0065] S2.5. Update the variational solution of each unknown parameter in turn according to the variational Bayesian algorithm;

[0066] According to the variational Bayesian method, the variational solutions of the unknown parameters at the mth iteration are:

[0067] 1)q m (θ n ,ξ n ) and its joint conjugate prior have the same form:

[0068]

[0069] where {θ nm ,V nm ,α nm ,β nm The value of} is obtained by the following calculation:

[0070]

[0071] 2) is the product of a set of independent Gamma distributions:

[0072]

[0073] in δ nm and γ nmp The value of is calculated by the following formula:

[0074]

[0075] {θ nm ,V nm ,α nm ,β nm Unknown terms in expressions is a diagonal matrix, we have:

[0076]

[0077] During the update of unknown parameters, the variables The initial values ​​of

[0078] S2.6. Calculate the variational lower bound ELBO;

[0079]

[0080] S2.7. Iterate the parameter update until the difference between the variational lower bound values ​​of two iterations is less than the preset threshold or the number of iterations is greater than 1000. Stop the iteration and obtain the final parameter estimate.

[0081] S3. Selecting the optimal model in the degradation model according to the automatic correlation determination method; specifically comprising the following steps:

[0082] S3.1. Based on the current parameter estimates obtained in S2.7, complete model selection according to the automatic correlation determination method;

[0083] Based on the automatic correlation determination method, the minimum The corresponding terms are regarded as irrelevant terms, that is, θ nm ≈0 is not considered as an item in the optimal degradation model. for:

[0084] exp{min(lnS n )+[max(lnS n )-min(lnS n )] / b};

[0085] Among them, S n ={S n1 ,S n2 ,...,S nP}、S nprepresents the auto-correlation determination value, b is a tuning parameter, and b=10 is selected.

[0086] S3.2. Iterate the parameter estimation of S2 and the model selection of S3.1 until only one model term remains.

[0087] S3.3. Select the term vector corresponding to the largest variational lower bound value as the optimal model.

[0088] S4. Select the prior sample that is most similar to the test sample at the current moment; specifically, the following steps are included:

[0089] S4.1. Calculate the Euclidean distance and DTW distance between the degradation sequence of the test sample and all prior samples from the initial moment to the current moment respectively;

[0090] 1) Euclidean distance ED nk :

[0091]

[0092] where x nk Indicates the nth prior sample at time t k The degradation amount, k now =min(k,K n ).

[0093] 2) DTW distance DTW nk :

[0094] DTW distance uses dynamic programming to align two degradation sequence value curves and calculates the similarity between two curves of different lengths. DTW distance focuses more on the trend and shape of the time series, which is something that Euclidean distance cannot solve. For the test sample degradation value sequence and the degradation value sequence of the nth prior sample x a and x nb The DTW distance between them is:

[0095] DTW(x a ,x nb )=(x a -x nb ) 2 ;

[0096] in,

[0097] The curved path can be obtained by the distance matrix M DTW The elements in the matrix are M DTW The shortest path in is:

[0098] D a,b =DTW(x a ,x nb )+min{D a-1,b-1 ,D a-1,b .D a,b-1};

[0099] Among them, D a,b Denotes the cumulative distance, in particular, D 1,1 =DTW(x1,x n1 ) holds true. In this way, the similarity based on DTW distance can be obtained by calculate.

[0100] S4.2. Calculate the score of each prior sample at the current moment;

[0101]

[0102] S4.3. Select the prior sample corresponding to the smallest score as the most similar sample to the test sample at the current moment.

[0103] S5. Online update of the mean and variance of the weight vector of the test sample; specifically, the following steps:

[0104] S5.1. Based on the prior parameter distribution of the most similar training sample and the sequential Bayesian algorithm, calculate the posterior distribution of the weight vector at the current moment;

[0105]

[0106] Where, represents the time t k The degenerate state x k (k>1).

[0107] S5.2. Simplify the posterior distribution of the weight vector and update the mean and variance of the weight vector of the test sample online;

[0108] θ follows a normal distribution with a mean of Ω k and variance H k It can be updated by:

[0109]

[0110] in, Ω k and H k The initial values ​​are Ω1=θ nm and

[0111] S6. Calculate the probability density function of the remaining life of the mixed Wiener process in terms of the first arrival time, and estimate the remaining life value of the IGBT at each moment.

[0112] Based on the proposed hybrid Wiener process degradation model, the probability density function expression of the remaining life of the IGBT is:

[0113]

[0114] Where ω represents the given failure threshold, L k express The corresponding remaining life, F′(t) is the first-order derivative of F(t) with respect to t.

[0115] Based on the above formula, the probability density function of the remaining life of the IGBT at each moment can be calculated, and its maximum value is the estimated value of the remaining life.

[0116] In order to verify the performance of the IGBT remaining life prediction method, NASA's IGBT accelerated aging dataset is selected for illustration, and the prediction results are compared with other advanced methods. Figure 2 The degradation trajectory of the IGBT sample in the dataset is given in a. The degradation amount is selected as the collector-emitter saturation voltage, and the failure threshold is set to be 5.5V higher than the initial value. The test sample is DEVICE4, and the training samples are DEVICE2 / DEVICE3. Figure 2 b in the figure represents the degradation trajectory of the test sample and the estimated degradation trajectory fitted by the hybrid Wiener degradation model and parameter estimation method proposed in the present invention, which shows that the degradation model of the present invention can better fit the real degradation trajectory. Figure 3 The probability density function of the remaining life is given by Figure 4 The estimated average value of the remaining life of the IGBT is given. Figure 5 A comparison chart shows the absolute errors between the true and estimated remaining life values ​​for this method and the multi-stage nonlinear Wiener process method. Furthermore, the root mean square error (RMS) and mean absolute error (MAE) were used to quantify the prediction performance of this method. The RMS errors for this method and the multi-stage nonlinear Wiener process method were 14.38 and 19.75, respectively, and the MAEs were 8.67 and 17.40, respectively, demonstrating that the proposed method exhibits superior performance.

[0117] Therefore, the present invention adopts the above-mentioned IGBT remaining life prediction method based on variational Bayesian and hybrid Wiener process, which can automatically determine the degradation mode and describe complex degradation trajectories, improve the fitting accuracy of IGBT degradation trajectories, reduce the requirements for professionalism, and improve the versatility of the model.

[0118] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit the same. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solutions of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for predicting the remaining life of an IGBT based on variational Bayesian and mixed Wiener processes, characterized by: The following steps are involved: S1. Define the hybrid Wiener process and establish a degradation model to describe the degradation trajectory of IGBT; A degradation model that can automatically determine the form and quantity of drift terms is established, called a mixed Wiener process, which is expressed as: ； in, ； and, for The degradation value at the moment, is the initial degradation amount, for The nonlinear drift term after weighting the function, is the weight vector, is the diffusion coefficient, is the standard Brownian motion, Represents functions of any form; S2, using prior samples to perform offline parameter estimation based on the variational Bayes algorithm; The specific steps include: S2.

1. According to Prior samples Moment and The degradation model at the moment calculates the difference in degradation amount Expressions of S2.2, seek Composed vector Likelihood function of ; S2.

3. Normalize all data from the same sensor to the same scale so that the maximum value is 1; S2.

4. Give the distribution of prior parameters and conjugate prior distribution; S2.

5. Update the variational solution of each unknown parameter in turn according to the variational Bayesian algorithm; S2.

6. Calculate the variational lower bound ELBO; S2.

7. Iterate the parameter update until the difference between the variational lower bounds of two iterations is less than a preset threshold or the number of iterations is greater than 1000. Then stop the iteration and obtain the final parameter estimate. S3. selecting an optimal model among the degradation models according to an automatic correlation determination method; The specific steps include: S3.

1. Based on the current parameter estimates obtained in S2.7, complete model selection according to the automatic correlation determination method; S3.

2. Iterate the parameter estimation of S2 and the model selection of S3.1 until only one model term remains. S3.

3. Select the term vector corresponding to the largest variational lower bound as the optimal model; S4, select the prior sample that is most similar to the test sample at the current moment; S5. Update the mean and variance of the weight vector of the test sample online; S6. Calculate the probability density function of the remaining life of the mixed Wiener process in terms of the first arrival time, and estimate the remaining life value of the IGBT at each moment.

2. The IGBT remaining life prediction method based on variational Bayesian and hybrid Wiener process according to claim 1, characterized in that: S4 specifically includes the following steps: S4.

1. Calculate the Euclidean distance and DTW distance between the degradation sequence of the test sample and all prior samples from the initial moment to the current moment respectively; S4.

2. Calculate the score of each prior sample at the current moment; S4.

3. Select the prior sample corresponding to the smallest score as the most similar sample to the test sample at the current moment.

3. The IGBT remaining life prediction method based on variational Bayesian and hybrid Wiener process according to claim 1, characterized in that: S5 specifically includes the following steps: S5.

1. Based on the prior parameter distribution of the most similar training sample and the sequential Bayesian algorithm, calculate the posterior distribution of the weight vector at the current moment; S5.

2. Simplify the posterior distribution of the weight vector and update the mean and variance of the weight vector of the test sample online.

Images