文献类型：期刊文献

英文题名：Neural networks-based hybrid beneficial variable selection and modeling for soft sensing

作者：Zhang, Zhongyi[1];Jiang, Qingchao[1];Wang, Guan[2];Pan, Chunjian[3];Cao, Zhixing[1,2];Yan, Xuefeng[1];Zhuang, Yingping[2]

机构：[1]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, State Key Lab Bioreactor Engn, Shanghai 200237, Peoples R China;[3]Shanghai Univ Elect Power, Coll Automat Engn, Shanghai 200090, Peoples R China

年份：2023

卷号：139

外文期刊名：CONTROL ENGINEERING PRACTICE

收录：;EI(收录号：20233114458205);WOS:【SCI-EXPANDED(收录号:WOS:001047370300001)】；

基金：Acknowledgments The authors gratefully acknowledge the support from the follow-ing foundations: National Key R & D Program of China under Grant No. 2021YFC2101100, National Natural Science Foundation of China under Grants (61973119, 31900073) , Shanghai Rising-Star Program, China under Grants (20QA1402600, 21QA1402400) , and Shanghai Science and Technology Innovation Action Plan, China, under Grant No. 23S41900500.

语种：英文

外文关键词：Deep neural network; Variable selection; Soft sensing; Process modeling

摘要：Variable selection plays an important role in soft sensor development. Either including redundant variables or missing important variables can degrade the modeling performance, affecting practical industrial applications. This paper proposes a novel neural networks-based hybrid beneficial variable selection (HBVS) and modeling method for effective soft sensing. First, irrelevant variables are removed through evaluating mutual information (MI) between all candidate variables and the quality variable. Second, proxy variables are introduced and a hidden gain-based evaluation method is employed to temporarily sort variables according to their significance, which facilitates to make use of process knowledge. Then, false discovery rate is employed to identify the model consistency, through which beneficial variables are determined. The proposed soft sensor development method is tested on a penicillin simulation process, and two actual industrial processes, including an oil refining process and an actual penicillin production process. Comparisons to state-of-the-art existing methods verify the effectiveness and superiority of the proposed method.