文献类型：期刊文献

英文题名：Consistency Regularization Auto-Encoder Network for Semi-Supervised Process Fault Diagnosis

作者：Ma, Yao[1];Shi, Hongbo[1];Tan, Shuai[1];Tao, Yang[1];Song, Bing[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：2022

卷号：71

外文期刊名：IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT

收录：;EI(收录号：20222812348749);WOS:【SCI-EXPANDED(收录号:WOS:000838523900017)】；

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 62073140, Grant 62073141, and Grant 62103149; in part by the National Key Research and Development Program of China under Grant 2020YFC1522502 and Grant 2020YFC1522505; in part by the Shanghai Rising-Star Program under Grant 21QA1401800; and in part by The Shanghai Natural Science Foundation under Grant 22ZR1417000.

语种：英文

外文关键词：Fault diagnosis; Feature extraction; Training; Semisupervised learning; Data models; Supervised learning; Deep learning; Consistency regularization (CR); data augmentation; encoder--decoder; fault diagnosis; semi-supervised

摘要：Industrial processes are developing toward intelligence and complexity, which brings challenges to intelligent process monitoring. An effective fault diagnosis model plays a vital role in ensuring process safety. However, labeling process samples is time-consuming and costly, which make it hard to obtain enough labeled samples to train an effective diagnostic model. This motivates the development of semi-supervised learning which basic idea is to use unlabeled data to help limited labeled data for model training. In this article, a consistency regularization autoencoder (CRAE) framework based on encoder-decoder network is proposed to overcome the problem caused by limited labeled samples. The proposed CRAE captured temporal and spatial correlations from both labeled and unlabeled samples to realize fault diagnosis. First, single process sample is processed as sample matrix using proposed data augmented strategy which can help the proposed method to extract more representative features. Second, local encoder and global encoder are proposed to extract local and global temporal and spatial features from sample matrices. Next, the local and global features are fused as the input of decoder network, which improve the ability of reconstruction. Finally, the consistency regularization (CR) method is introduced into the encoder-decoder framework to push the decision boundary to the low-density area, which make the distinction among different categories more obvious to help the model better achieve the classification task. Experiments on the Tennessee Eastman (TE) process show that the proposed method is effective for process fault diagnosis when labeled samples are limited compared to the other semi-supervised algorithms.