Open-Circuit Fault Diagnosis of Three-Phase PWM Rectifier Using Beetle Antennae Search Algorithm Optimized Deep Belief Network

Abstract

Effective open-circuit fault diagnosis for a two-level three-phase pulse-width modulating (PWM) rectifier can reduce the failure rate and prevent unscheduled shutdown. Nevertheless, traditional signal-based feature extraction methods show poor distinguishability for insufficient fault features. Shallow learning diagnosis models are prone to fall into local extremum, slow convergence speed, and overfitting. In this paper, a novel fault diagnosis strategy based on modified ensemble empirical mode decomposition (MEEMD) and the beetle antennae search (BAS) algorithm optimized deep belief network (DBN) is proposed to cope with these problems. Initially, MEEMD is applied to extract useful fault features from each intrinsic mode function (IMF) component. Meanwhile, to remove features with redundancy and interference, fault features are selected by calculating the importance of each feature based on the extremely randomized trees (ERT) algorithm, and the dimension of fault feature vectors is reduced by principal component analysis. Additionally, the DBN stacked with two layers of a restricted Boltzmann machine (RBM) is selected as the classifier, and the BAS algorithm is used as the optimizer to determine the optimal number of units in the hidden layers of the DBN. The proposed method combined with feature extraction, feature selection, optimization, and fault classification algorithms significantly improves the diagnosis accuracy.

Machine Learning and Fuzzy Logic in Electronics: Applying Intelligence in Practice

“…Du et al propose a method for feature extraction and selection for the optimization and classification of faults at a two-level three-phase pulse-width modulating rectifier [49]. Such a fault diagnosis approach based on open-circuit measurement can prevent unwished shutdown and can decrease the number of failures.…”

Machine Learning-Based Condition Monitoring for PV Systems: State of the Art and Future Prospects

“…The detection of this type of fault can be performed either via data-driven methods, such as illustrated by the works of Wang et al [33] and Du et al [34] (i.e., ML modeling), or through the use of physical simulation models and analysis of I-V/P-V curves, as indicated in the work of Pei et al [31]. However, detection with ML modeling can be undertaken by means of both supervised learning (approximation) when labels are known or unsupervised learning (clustering) when data is unlabeled.…”

A Neural Network Classifier with Multi-Valued Neurons for Analog Circuit Fault Diagnosis

“…In recent years, support vector machines (SVM) have often been successfully used in place of neural networks for the fault diagnosis of analog circuits [24][25][26] by exploiting the great classifier capability of this kind of machine learning approach. Another recent category of machine learning approaches includes deep-learning NN [27].…”