文献类型：期刊文献

英文题名：Specific index-related process monitoring using a two-step information extraction method

作者：Zhao, Bo[1]; Song, Bing[1]; Tan, Shuai[1]; Shi, Hongbo[1]

机构：[1] Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education, East China University of Science and Technology, Shanghai, 200237, China

年份：2018

起止页码：2533

外文期刊名：Proceedings of the 30th Chinese Control and Decision Conference, CCDC 2018

收录：EI(收录号：20183205650738)

语种：英文

摘要：Specific index-related process monitoring covers a wide range of requirements from industrial production. At present, it is still a challenge to divide into the specific index-related information and the specific index-unrelated information more accurately. In this paper, a two-step information extraction method is presented to solve this problem. In the first step, the overall process variables are separated into a strongly related variable set and a weakly related variable set. In the second step, the two sets are further divided into a specific index-related subset and a specific index-unrelated subset, respectively. Two specific index-related subsets form a new subspace related to the specific index. Two specific index-unrelated subsets are combined into a specific index-unrelated subspace. Two T2 statistics are built in the specific index-related subspace and the specific index-unrelated subspace, respectively. Finally, the proposed method is applied for Tennessee Eastman (TE). The results indicate the effectiveness of the proposed method. ? 2018 IEEE.