文献类型：期刊文献

英文题名：A semi-supervised feature contrast convolutional neural network for processes fault diagnosis

作者：Yang, Yuguo[1];Shi, Hongbo[1];Tao, Yang[1];Ma, Yao[1];Song, Bing[1];Tan, Shuai[1]

机构：[1]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China

年份：2023

卷号：151

外文期刊名：JOURNAL OF THE TAIWAN INSTITUTE OF CHEMICAL ENGINEERS

收录：;EI(收录号：20233514660960);WOS:【SCI-EXPANDED(收录号:WOS:001087522700001)】；

基金：This work was supported by the National Key Research and Development Program of China (Grant No. 2020YFC1522502, 2020YFC1522505); National Natural Science Foundation of China (No. 62073140, 62073141, 62103149), Shanghai Rising-Star Program (No. 21QA1401800), National Natural Science Foundation of Shanghai (No. 19ZR1473200)

语种：英文

外文关键词：Convolutional neural network; Unit features extraction; Fault diagnosis; Semi-supervised learning; Contrastive learning

摘要：Background: Modern industrial processes involve multiple operating units, which perform their respective functions and are coupled with each other. Accurate extraction of complex non-linear relationship contained in process variables is the key to fault diagnosis. Most fault diagnosis methods based on deep learning heavily rely on labeled date, yet labelled samples are limited in the real industrial process.Methods: This paper proposes a semi-supervised feature contrast convolutional neural network (SS-FCCNN) model for multi-unit, non-linear, label-deficient industrial process. Firstly, based on the physical structure of industrial process, local unit convolutional neural network (LU-CNN) and global unit convolutional neural network (GU-CNN) are proposed. LU-CNN extracts the deep features of the variables involved in each operating unit as the local intra-unit features. GU-CNN extracts global inter-unit features and models the complex relationship between operating units due to fault propagation. Subsequently, the unit feature contrast network (UFCN) and data corrosion strategy are applied to labeled data and unlabeled data respectively, which restricts the unit features and enhances the generalization of unit features extracted by the network. Case studies of Tennessee Eastman process demonstrate the effectiveness of SS-FCCNN.