文献类型：期刊文献

英文题名：Data-driven individual-joint learning framework for nonlinear process monitoring

作者：Jiang, Qingchao[1];Yan, Shifu[1];Yan, Xuefeng[1];Chen, Shutian[1];Sun, Jinggao[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：2020

卷号：95

外文期刊名：CONTROL ENGINEERING PRACTICE

收录：;EI(收录号：20194807748636);WOS:【SCI-EXPANDED(收录号:WOS:000510526900022)】；

基金：This work was supported in part by National Natural Science Foundation of China under Grants 61603138 and 61973119, in part by Shanghai Pujiang Program, China under Grant 17PJD009, in part by Fundamental Research Funds for the Central Universities, China under Grants 222201917006 and 222201714027, in part by the Programme of Introducing Talents of Discipline to Universities (the 111 Project), China under Grant B17017, and in part by Open Research Project of the State Key Laboratory of Industrial Control Technology, Zhejiang University, China (No. ICT1900331).

语种：英文

外文关键词：Individual-joint learning; Deep neural network; Nonlinear process monitoring; Fault detection

摘要：Industrial processes are generally characterized by significant nonlinearity, and the monitoring of nonlinear processes remains a challenge. This study proposes a novel data-driven individual-joint learning (IJL) framework for achieving efficient nonlinear process monitoring. First, individual learning is performed by separately establishing stacked autoencoders in process input or output variables to characterize the variable relationship within process input or output. Second, joint learning is performed between the input and output variables to characterize their relationship and extract deep correlated representations. Subsequently, fault detection residuals and statistics are constructed to examine the process status. Given the superiority of deep neural network in representation learning, the complex relationship among process variables can be efficiently characterized, and satisfactory monitoring performance is then obtained. IJL monitoring is tested on the Tennessee Eastman benchmark process and applied on a glycerol distillation process, through which its effectiveness and superiority are demonstrated.