文献类型：期刊文献

英文题名：Fault Detection and Classification Using Quality-Supervised Double-Layer Method

作者：Song, Bing[1];Shi, Hongbo[1]

机构：[1]East China Univ Sci & Technol, Key Lab Adv Control & Optimizat Chem Proc, Minist Educ, Shanghai 200237, Peoples R China

年份：2018

卷号：65

期号：10

起止页码：8163

外文期刊名：IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS

收录：;EI(收录号：20180704784694);WOS:【SCI-EXPANDED(收录号:WOS:000441990000001)】；

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 61703161, Grant 61374140, and Grant 61673173, in part by the Fundamental Research Funds for the Central Universities under Grant 222201714031 and Grant 222201717006, and in part by the China Postdoctoral Science Foundation under Grant 2017M611472. (Corresponding author: Hongbo Shi.)

语种：英文

外文关键词：Fault classification; fault detection; principal component analysis (PCA); quality; quality-related fault detection

摘要：In the practical process, various faults occur, which may affect the quality of products. Meanwhile, due to the presence of the feedback closed loop, the effects of certain faults might be compensated. Consequently, not all faults occurring in the system will affect the product quality. According to the impacts of faults on the quality, the faults can be categorized as a quality-unrelated fault, quality-semirelated fault, and quality-related fault. For different categories of faults, corresponding responses should be adopted. Motivated by this, a novel quality-supervised double-layer method (QSDLM) is proposed in this paper to detect and classify the faults simultaneously. The first layer is used for fault detection using principal component analysis (PCA). The second layer is to detect the occurrence of quality-related fault based on the proposed key variable-orthogonal weight PCA. By comparing the result of the first layer with that of the second layer, whether the fault is related to the product quality can be identified, and the fault classification can be conducted. The proposed QSDLM is used in the Tennessee Eastman process to prove its effectiveness. Compared with three typical methods, the proposed QSDLM method can obtain the best results.