文献类型：期刊文献

英文题名：Variable-Scale Probabilistic Just-in-Time Learning for Soft Sensor Development with Missing Data

作者：Huang, Haojie[1];Peng, Xin[1,3];Jiang, Chao[1,4];Li, Zhi[1];Zhong, Weimin[1,2]

机构：[1]East China Univ Sci & Technol, Key Lab Adv Control & Optimizat Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[2]Tongji Univ, Shanghai Inst Intelligent Sci & Technol, Shanghai 200092, Peoples R China;[3]Univ Duisburg Essen, Inst Automat Control & Complex Syst, D-47057 Duisburg, Germany;[4]Univ Alberta, Dept Chem & Mat Engn, Edmonton, AB T6G 2V4, Canada

年份：2020

卷号：59

期号：11

起止页码：5010

外文期刊名：INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH

收录：;EI(收录号：20201508389044);WOS:【SCI-EXPANDED(收录号:WOS:000526416200017)】；

基金：The authors are grateful for the National Natural Science Foundation of China under Grants 61925305, 61890930-3, and 61803157; the Programme of Introducing Talents of Discipline to Universities (the 111 Project) under Grant B17017; the Natural Science Foundation of Shanghai under Grant 16ZR1407300; and Fundamental Research Funds for the Central Universities under Grant 222201917006. In addition, the authors thank Prof. Xiao-feng Yuan at Central South University in the People's Republic of China for his research support.

语种：英文

外文关键词：Catalytic reforming - Just in time production - Mean square error

摘要：Just-in-time learning (JITL) has been widely applied to data-driven modeling to deal with the nonlinearity problems in industrial processes. To mitigate the effects of noise existing in JITL, probabilistic JITL (PJITL) selects samples based on the probability distributions. Considering the existence of missing data situation, the PJITL algorithm could also cope with that. However, traditional JITL-based methods, including PJITL, cannot flexibly select the number of training samples for each query sample, which would in return influence the accuracy of prediction for a part of query samples. To solve this problem, we proposed a method named "variable-scale PJITL" (VS-PJITL) which can determine the sizes of the local models for each query sample using a new sample selection criterion. Based on the Euclidean distance, the sample selection criterion also applies to the variable-scale JITL (VS-JITL). Then, comparisons of VS-PJITL, PJITL, JITL, and VS JITL are tested on a simulated data set and a real industrial data set from the catalytic naphtha reforming process. By analyzing the two cases above, VS-PJITL is considered to have superior performance to the original PJITL (root-mean-square error reduced by 0.3355 and 0.4778).