Intelligent diagnosis of cascaded H‐bridge multilevel inverter combining sparse representation and deep convolutional neural networks

Abstract

Effective fault diagnosis for cascaded H-bridge multilevel inverter (CHMLI) can reduce failure rate and prevent the unscheduled shutdown. Nevertheless, traditional signal-based feature extraction and feature selection methods show poor distinguishability for insufficient fault features in a one-dimensional space. The shallow learning models are prone to fall into local extremum, slow convergence speed and overfitting. To cope with these problems, a novel image-oriented fault diagnosis strategy based on sparse representation (SR) and deep convolutional neural network (DCNN) is proposed for CHMLI. Initially, Hilbert-Huang transform (HHT) is applied to obtain the HHT spectral images of original monitoring signals, where these images comprehensively represent the features with detailed information of multiple domains on the time-frequency plane. Furthermore, an image fusion method based on the SR algorithm is employed on these spectral images of the same fault category to construct fused feature images, which effectively reflects the complicated relationships between the measured signals and fault features. Ultimately, the DCNN models can not only mine the relationship between the various fault categories and the different fused feature images but also can alleviate the problem of overfitting that is caused by the limited availability of training samples. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Fault Diagnosis of Asymmetric Cascaded Multilevel Inverter using Ensemble Machine Learning

“…Sparse representation with deep convolutional neural networks (DCNNs) is applied to provide an intelligent fault detection method for CMLI. By harnessing the beneficial characteristics of both approaches, the technique aims to improve defect identification efficiency and accuracy [19].…”

FPGA-based fault analysis for 7-level switched ladder multi-level inverter using decision tree algorithm

“…The switching faults are tested for tolerance to affirm the durability of the multi-level inverter [18]. The fault identification is performed with the cascaded H-bridge multilevel inverter (CHMLI) circuit using the deep convolutional neural network through imaging [19]. The 7-level multi-level inverter is diagnosed for faults using the cuckoo search algorithm with radial basis function is advantageous for prediction [20].…”