文献类型：期刊文献

英文题名：Data-Driven Mode Identification and Unsupervised Fault Detection for Nonlinear Multimode Processes

作者：Wang, Bei[1,2];Li, Zhichao[1];Dai, Zhenwen[3];Lawrence, Neil[3];Yan, Xuefeng[1]

机构：[1]East China Univ Sci & Technol, Minist Educ, Key Lab Adv Control & Optimizat Chem Proc, Shanghai 200237, Peoples R China;[2]Shanghai Elect Windpower Grp, Shanghai 200241, Peoples R China;[3]Univ Sheffield, Dept Comp Sci, Sheffield S10 2TN, S Yorkshire, England

年份：2020

卷号：16

期号：6

起止页码：3651

外文期刊名：IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS

收录：;EI(收录号：20201208315221);WOS:【SCI-EXPANDED(收录号:WOS:000526381800003)】；

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 21878081, in part by the Fundamental Research Funds for the Central Universities under Grant of China under Grant 222201717006, and in part by China Scholarship Council. Paper no. TII-19-0697. (B.Wang and Z. Li contributed equally to this work.) (Corresponding author: Xuefeng Yan.)

语种：英文

外文关键词：Monitoring; Hidden Markov models; Data models; Biological system modeling; Fault detection; Adaptation models; Indexes; Data-driven process monitoring; Dirichlet process Gaussian mixed model (DPGMM); fault detection; multimode systems; nonlinear dimensionality reduction

摘要：In modern plants, industrial processes typically operate under different states to meet the different requirements of high-quality products. Many monitoring models for industrial processes were constructed based on the prior knowledge (the mechanism's model or the process data characteristics) to monitor such processes (called multimode processes). However, obtaining this prior knowledge is difficult in practice. Efficiently monitoring nonlinear multimode processes without any prior knowledge is an open problem that demands further exploration. Since data from different modes follow different distributions while data from the same mode are considered to be sampled from the same distribution, the modes of multimode processes can be uncovered based on the characteristics of the process data. This article proposes using a Dirichlet process Gaussian mixed model to classify the modes of multimode processes based on historical data, and then, determine the mode types of the monitored data. A nonlinear monitoring strategy based on the t-distributed stochastic neighbor embedding is then proposed to achieve nonlinear dimensionality reduction and visualize the data. Finally, a monitoring index that is integrated with support vector data description is constructed for comprehensive monitoring. The proposed nonlinear multimode framework completely realizes data-driven mode identification and unsupervised fault detection without knowing any prior knowledge. The effectiveness and feasibility of the proposed model are demonstrated using data from a simulated wastewater treatment plant.