Incipient Fault Diagnosis Method for IGBT Drive Circuit Based on Improved SAE

He, Yigang; Li, Chenchen; Shi, Tiancheng; Lin, Tao; Yuan, Wu

doi:10.1109/access.2019.2923017

Cited by 14 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All the variables in X −1,j and X 1,j have the class labels −1 (Majority) and 1 (Minority), respectively. We set five kinds of sizes, (n p , n n ) = (30,30), (15,30), (12,30), (6,30), and (3, 30) to illustrate the performance of different algorithms in different-sized data. b = 1, 2, 2.5, 5, 10 for these five cases and a larger b indicates a more severely imbalanced dataset.…”

Section: Numeric Studies a Simulation Data Studiesmentioning

confidence: 99%

“…In statistics, Relevance Vector Machine (RVM), initially proposed by [24], is an algorithm that uses the Bayesian model to obtain the parsimonious solutions for regression and probabilistic classification. RVM has obtained successful applications in text image recognition (e.g., [20,23]), image classification (e.g., [6,28]), time series analysis (e.g., [14]), mechanical fault diagnosis (e.g., [7,12]), and electric demand forecasting (e.g., [21,32]). As a generalized linear model, RVM has an identical functional form to the Support Vector Machine (SVM) but obtains a comparable performance with fewer kernel functions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fully Bayesian Analysis of Relevance Vector Machine Classification With Probit Link Function for Imbalanced Data Problem

et al. 2021

View full text Add to dashboard Cite

The original RVM classification model uses the logistic link function to build the likelihood function making the model hard to be conducted since the posterior of the weight parameter has no closed-form solution. This paper proposes the probit link function approach instead of the logistic one for the likelihood function in the RVM classification model, namely PRVM (RVM with the probit link function). We show that the posterior of the weight parameter in PRVM follows the Multivariate Normal distribution and achieves a closed-form solution. A latent variable is needed in our algorithms to simplify the Bayesian computation greatly, and its conditional posterior follows a truncated Normal distribution. Compared with the original RVM classification model, our proposed one is a Fully Bayesian approach, and it has a more efficient computation process. For the prior structure, we first consider the Normal-Gamma independent prior to propose a Generic Bayesian PRVM algorithm. Furthermore, the Fully Bayesian PRVM algorithm with a hierarchical hyperprior structure is proposed, which improves the classification performance, especially in the imbalanced data problem.

show abstract

Section: Numeric Studies a Simulation Data Studiesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fully Bayesian Analysis of Relevance Vector Machine Classification With Probit Link Function for Imbalanced Data Problem

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In order to compare the fault diagnosis accuracy of different learning networks, three other deep learning networks, such as stack auto-encoder(SAE) network in Ref. [18], [29], deep belief neural (DBN)network in Ref. [30] and recurrent neural network(RNN) in Ref.…”

Section: Comparison With Other Learning Networkmentioning

confidence: 99%

A novel method of combining generalized frequency response function and convolutional neural network for complex system fault diagnosis

2020

View full text Add to dashboard Cite

To solve the problem of low accuracy in traditional fault diagnosis methods, a novel method of combining generalized frequency response function(GFRF) and convolutional neural network(CNN) is proposed. In order to accurately characterize system state information, this paper proposed a variable step size least mean square (VSSLMS) adaptive algorithm to calculate the second-order GFRF spectrum values under normal and fault states; In order to improve the ability of fault feature extraction, a convolution neural network (CNN) with gradient descent learning rate and alternate convolution layer and pooling layer is designed to extract the fault features from GFRF spectrum. In the proposed method, the second-order GFRF spectrum of each state of Permanent Magnet Synchronous Motor (PMSM) is obtained by VSSLMS; Then, the two-dimension GFRF spectrum, which is regarded as the gray value of the image,will be further transformed into image. Finally, the CNN is trained with learning rate by gradient descent way to realize the fault diagnosis of PMSM. Experimental results indicate that the accuracy of proposed method is 98.75%, which verifies the reliability of the proposed method in application of PMSM fault diagnosis.

show abstract

“…The stacked auto-encoder neural network, referred to as SAE in this paper, is a feedback neural network model consisting of a series of multi-layer auto-encoders (AE) [32]. AE is an unsupervised feature learning method, and the softmax classifier is a supervised learning algorithm, the SAE model combines the advantages of unsupervised and supervised together [33], [34].…”

Section: Sae Algorithm For Inverse Problemmentioning

confidence: 99%

A Stacked Autoencoder Neural Network Algorithm for Breast Cancer Diagnosis With Magnetic Detection Electrical Impedance Tomography

Chen

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Magnetic detection electrical impedance tomography (MDEIT) is a novel imaging technique that aims to reconstruct the conductivity distribution with electrical current injection and the external magnetic flux density measurement by magnetic sensors. Aiming at improving the resolution and accuracy of MDEIT and providing an efficient imaging method for breast cancer diagnosis, a new algorithm based on stacked auto-encoder (SAE) neural network is proposed. Both numerical simulation and phantom experiments are done to verify its feasibility. In the numerical simulation, an amount of sample data with different conductivity distribution are calculated. Then a neural network model is established and trained by training these samples. Finally, the conductivity distribution of an imaging target with the anomaly location can be reconstructed by the network model. The reconstruction result of the SAE algorithm is compared with the reconstruction results of the traditional sensitivity matrix (SM) algorithm and the back propagation (BP) neural network algorithm. Under the noise of 30dB, the relative errors of BP algorithm, SM algorithm and SAE algorithm are 137.19%, 24.90% and 15.28% respectively. Result shows by the SAE algorithm, the location of anomalies is reconstructed more accurately, the conductivity value is more closely to the real one and the anti-noise performance is more robust. At last, a breast phantom experiment by self-made platforms is completed to verify the application feasibility of the new algorithm. The relative reconstruction error of conductivity by proposed SAE algorithm can be reduced to 14.56%. The results show that by SAE algorithm, MDEIT can be a promising approach in clinical diagnosis of breast cancer, and it also provide more potential application prospect for the extensive application of MDEIT. INDEX TERMS Breast cancer diagnosis, inverse problem, magnetic detection electrical impedance tomography, stacked auto-encoder.

show abstract

Incipient Fault Diagnosis Method for IGBT Drive Circuit Based on Improved SAE

Cited by 14 publications

References 28 publications

Fully Bayesian Analysis of Relevance Vector Machine Classification With Probit Link Function for Imbalanced Data Problem

Fully Bayesian Analysis of Relevance Vector Machine Classification With Probit Link Function for Imbalanced Data Problem

A novel method of combining generalized frequency response function and convolutional neural network for complex system fault diagnosis

A Stacked Autoencoder Neural Network Algorithm for Breast Cancer Diagnosis With Magnetic Detection Electrical Impedance Tomography

Contact Info

Product

Resources

About