文献类型：期刊文献

英文题名：Neural networks with upper and lower bound constraints and its application on industrial soft sensing modeling with missing values

作者：Lu, Yusheng[1];Yang, Dan[1];Li, Zhongmei[1];Peng, Xin[1];Zhong, Weimin[1]

机构：[1]East China Univ Sci & Technol, Minist Educ, Key Lab Smart Mfg Energy Chem Proc, Shanghai 200237, Peoples R China

年份：2022

卷号：243

外文期刊名：KNOWLEDGE-BASED SYSTEMS

收录：;EI(收录号：20221211821594);WOS:【SCI-EXPANDED(收录号:WOS:000820474200019)】；

语种：英文

外文关键词：Neural network; Upper and lower bound; Missing value; Soft sensing

摘要：Soft sensors estimate quality indicators that are difficult to measure online so that they are important in industrial processes. The sensors may malfunction so that some data may be unavailable or contain abnormal values, which means the data contain missing values. To deal with missing values, missing values are filled by evaluated estimations or utilized by probabilistic generative models. Since filling the missing values with expectations may overestimate the prediction error of the model, and using a generative model to calculate the generating probability may be harmful to prediction performance, we propose a new neural network method with the upper and lower bound constraints of the estimated missing values. Our methods will not overestimate the prediction error. From the probabilistic point of view, our optimization goal can be regarded as maximizing the posterior probability under the upper and lower bound constraints. Meanwhile, the mask-specific local models are adopted to improve the prediction reliability of the upper and lower bounds. Finally, our methods are verified in the industrial processes. (C) 2022 Elsevier B.V. All rights reserved.