Reliable Fault Diagnosis of Multiple Induction Motor Defects Using a 2-D Representation of Shannon Wavelets

This paper proposes an approach for a 2-D representation of Shannon wavelets for highly reliable fault diagnosis of multiple induction motor defects. Since the wavelet transform is efficient for analyzing non-stationary and non-deterministic vibration signals, this paper utilizes wavelet coefficients deduced from the Shannon mother wavelet function with varying dilation and translation parameters to create 2-D gray-level images. Using the resulting images and their associated texture characteristics, this paper extracts features by generating global neighborhood structure maps, which are used to extract global image features. The texture features are then used as inputs in one-against-all multi-class support vector machines to identify faults in the induction machine. To evaluate the performance of the proposed approach, it is compared with five conventional state-of-the-art algorithms in terms of classification accuracy. In addition, this paper explores the robustness of the proposed approach in noisy environments by adding white Gaussian noise to the acquired vibration signals. The experimental results indicate that the proposed approach outperforms conventional algorithms in terms of the classification accuracy. Moreover, the proposed approach achieves higher classification accuracy, even in noisy environments.