An Improved Convolutional Neural Network for Three-Phase Inverter Fault Diagnosis

• Published in: IEEE transactions on instrumentation and measurement 2022-01, Vol.71, p.1-15
• Main Authors: Zhang, Shiqi, Wang, Rongjie, Si, Yupeng, Wang, Libao
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Circuit faults; Convolution; Convolutional neural network (CNN); Convolutional neural networks; Deep learning; end-to-end; Fault diagnosis; Feature extraction; Inverters; Machine learning; Neural networks; Power transistors; three-phase voltage-source inverter
• ISSN: 0018-9456; 1557-9662
• DOI: 10.1109/TIM.2021.3129198

This article proposes an end-to-end method based on an improved convolutional neural network model for inverter fault diagnosis. First, transient time-domain sequence data under different faults are analyzed, and raw signals are taken as fault representations without manually selecting feature extraction methods. Second, the model can automatically learn and extract features in the input domain using stacked convolution layers with the wide first-layer convolution kernel and a global max pooling layer; thus, it eliminated the influence of expert experience. Finally, the fault diagnosis results of the three-phase voltage-source inverter are automatically obtained in the softmax layer. The proposed fault diagnosis method has superior recognition performance with mixed noise data and variable load data. Contrastive experiments show that the improved fault diagnosis model is effective than traditional machine learning and other deep learning methods.