Multiblock temporal convolution network-based temporal-correlated feature learning for fault diagnosis of multivariate processes

• DOI: 10.1016/j.jtice.2021.04.062
• Publication Date: 2021-05-21T19:11:05Z
• Authors: Yumin He; Hongbo Shi; Shuai Tan; Bing Song; Jiazhen Zhu
• Keywords: 0209 industrial biotechnology; 0202 electrical engineering, electronic engineering, information engineering; 02 engineering and technology

Abstract A new temporal-correlated feature learning method, multiblock temporal convolutional network (MBTCN), is proposed for supervised fault diagnosis of multivariate processes in this paper. The MBTCN used a new idea, "local extraction and global integration," to consider the cross-correlation and the temporal-correlation in the multivariate processes' data. First, MBTCN divides the overall variables into several sub-blocks based on process mechanisms and uses one-dimensional convolutional neural network (1D-CNN) architectures to extract temporal-correlated features in each sub-block, with the 1D-CNN network sliding over time steps. Thus, the adjacent samples and the close-related variables can be considered together in the network. Then, MBTCN constructs a global feature representation built by concatenating local features of sub-blocks. Besides, in the supervised training phase, training labels are modified by label smoothing technology to alleviate the overfitting. Finally, a Tennessee Eastman (TE) process is used to test the proposed model's effectiveness. The code of MBTCN can be found in https://github.com/heyumi0901/MBTCN.