文献类型：期刊文献

英文题名：Global-and-local-structure-based neural network for fault detection

作者：Zhao, Haitao[1];Lai, Zhihui[2,4];Chen, Yudong[2,3]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Automat Dept, Shanghai 200237, Peoples R China;[2]Shenzhen Univ, Coll Comp Sci & Software Engn, Shenzhen 518060, Peoples R China;[3]Shenzhen Univ, Natl Engn Lab Big Data Syst Comp Technol, Shenzhen 518060, Peoples R China;[4]Shenzhen Univ, Guangdong Key Lab Intelligent Informat Proc, Shenzhen 518060, Peoples R China

年份：2019

卷号：118

起止页码：43

外文期刊名：NEURAL NETWORKS

收录：;EI(收录号：20192507075871);WOS:【SCI-EXPANDED(收录号:WOS:000483920500004)】；

基金：This research is sponsored by National Natural Science Foundation of China (61375007, 61573248, 61802267, 61732011), Basic Research Programs of Science and Technology Commission Foundation of Shanghai, China (15JC1400600), in part by the Shenzhen Municipal Science and Technology Innovation Council, China under Grant JCYJ20180305124834854 and in part by the Natural Science Foundation of Guangdong Province, China (Grant 2017A030313367).

语种：英文

外文关键词：Statistical process monitoring; Fault detection; Feedforward neural network; Principal component analysis; Dimension reduction

摘要：A novel statistical fault detection method, called the global-and-local-structure-based neural network (GLSNN), is proposed for fault detection. GLSNN is a nonlinear data-driven process monitoring technique through preserving both global and local structures of normal process data. GLSNN is characterized by adaptively training a neural network which takes both the global variance information and the local geometrical structure into consideration. GLSNN is designed to extract the meaningful low-dimensional features from original high-dimensional process data. After nonlinear feature extraction, Hotelling T-2 statistic and the squared prediction error (SPE) statistic are adopted for online fault detection. The merits of the proposed GLSNN method are demonstrated by both theoretical analysis and case studies on the Tennessee Eastman (TE) benchmark process. Extensive experimental results show the superiority of GLSNN in terms of missed detection rate (MDR) and false alarm rate (FAR). The source code of GLSNN can be found in https://github.com/htzhaoecust/glsnn. (C) 2019 Elsevier Ltd. All rights reserved.