Multi-view feature fusion fault diagnosis method based on an improved temporal convolutional network

This paper addresses the problem of fault identification in rotating machinery by analysing vibration data using a neural network approach. Temporal convolutional networks (TCNs) have attracted a lot of focus in the domain of fault identification; however, TCN convolution kernels are small and susceptible to high-frequency noise interference. Furthermore, the default weight coefficient of the internal residual connection is 1. When there are few residual blocks, the residual block characteristic extraction ability is suppressed and only the vibration signal collected at a single location is utilised for fault diagnosis as it contains incomprehensive fault information. To tackle the above issues, this paper proposes a multi-view feature fusion fault diagnosis algorithm with an adaptive residual coefficient assignment TCN with wide first-layer kernels (WD-ARCATCN). Firstly, a WD-ARCATCN feature extraction network is designed to extract deep state features from different views and the first layer of the TCN is set as a wide-kernel (WD) convolutional layer to suppress high-frequency noise. An adaptive residual coefficient assignment (ARCA) unit is designed in the residual connection to increase the characteristic learning capability of the residual blocks and the residual blocks with ARCA units are stacked to further extract multi-view deep fault features. In this paper, acceleration signals collected at different positions are used as the multi-view feature source for the first time and the fault information contained is more comprehensive. Then, based on a self-attention mechanism, the multi-view feature fusion method is improved and the view weights are adaptively assigned to effectively fuse different view characteristics and enhance the identification of the fault characteristics. Finally, the mapping between the multi-view fusion features and the labels is achieved using a softmax classifier. The algorithm has been tested using experimental data from the bearing vibration database at Case Western Reserve University (CWRU) and it performed much better compared to other diagnostic algorithms.