文献类型：期刊文献

英文题名：Deep relevant representation learning for soft sensing

作者：Yan, Xuefeng[1,2];Wang, Jie[1,2];Jiang, Qingchao[1,2]

机构：[1]East China Univ Sci & Technol, Minist Educ, Key Lab Adv Control & Optimizat Chem Proc, Shanghai 200237, Peoples R China;[2]Tongji Univ, Shanghai Inst Intelligent Sci & Technol, Shanghai 200092, Peoples R China

年份：2020

卷号：514

起止页码：263

外文期刊名：INFORMATION SCIENCES

收录：;EI(收录号：20195007829571);WOS:【SCI-EXPANDED(收录号:WOS:000513296600015)】；

基金：This work was supported in part by National Natural Science Foundation of China under Grants 61603138, 21878081, and 61973119, in part by Fundamental Research Funds for the Central Universities under Grants 222201917006 and 222201714027, and in part by the Programme of Introducing Talents of Discipline to Universities (the 111 Project) under Grant B17017.

语种：英文

外文关键词：Deep neural network; Stacked autoencoder; Deep relevant representation; Soft sensing; Mutual information

摘要：Soft sensing provides a reliable estimation of difficult-to-measure variables and is important for process control, optimization, and monitoring. The extraction of beneficial information from the abundance of available data in modern industrial processes and the development of data-driven soft sensors are becoming areas of increasing interest. In addition, the use of deep neural networks (DNNs) has become a popular data processing and feature extraction technique owing to its superiority in generating high-level abstract representations from massive amounts of data. A deep relevant representation learning (DRRL) approach based on a stacked autoencoder is proposed for the development of an efficient soft sensor. Representations from conventional DNN methods are not extracted for an output prediction, and thus a mutual information analysis is conducted between the representations and the output variable in each layer. Analysis results indicate that irrelevant representations are eliminated during the training of the subsequent layer. Hence, relevant information is highlighted in a layer-by-layer manner. Deep relevant representations are then extracted, and a soft sensor model is established. The results of a numerical example and an industrial oil refining process show that the prediction performance of the proposed DRRL-based soft sensing approach is better than that of other state-of-the-art methods. (C) 2019 Elsevier Inc. All rights reserved.