WaveletKernelNet: An Interpretable Deep Neural Network for Industrial Intelligent Diagnosis
This work addresses interpretability in fault diagnosis for industrial maintenance, but it is incremental as it modifies an existing CNN architecture.
The authors tackled the lack of interpretability in CNNs for industrial fault diagnosis by proposing WaveletKernelNet, which replaces the first convolutional layer with a continuous wavelet convolutional layer, resulting in fewer parameters, higher accuracy, and faster convergence than standard CNNs.
Convolutional neural network (CNN), with ability of feature learning and nonlinear mapping, has demonstrated its effectiveness in prognostics and health management (PHM). However, explanation on the physical meaning of a CNN architecture has rarely been studied. In this paper, a novel wavelet driven deep neural network termed as WaveletKernelNet (WKN) is presented, where a continuous wavelet convolutional (CWConv) layer is designed to replace the first convolutional layer of the standard CNN. This enables the first CWConv layer to discover more meaningful filters. Furthermore, only the scale parameter and translation parameter are directly learned from raw data at this CWConv layer. This provides a very effective way to obtain a customized filter bank, specifically tuned for extracting defect-related impact component embedded in the vibration signal. In addition, three experimental verification using data from laboratory environment are carried out to verify effectiveness of the proposed method for mechanical fault diagnosis. The results show the importance of the designed CWConv layer and the output of CWConv layer is interpretable. Besides, it is found that WKN has fewer parameters, higher fault classification accuracy and faster convergence speed than standard CNN.