A Novel Process Monitoring Framework Combined Temporal Feedback Autoencoder and Multilevel Correlation Analysis for Large-Scale Industrial Processes

作     者：Zhang, Cuicui Dong, Jie Zhang, Hongjun Peng, Kaixiang 

作者机构：Key Laboratory of Knowledge Automation for Industrial Processes Ministry of Education School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China National Engineering Research Center for Advanced Rolling and Intelligent Manufacturing University of Science and Technology Beijing Beijing100083 China 

出 版 物：《SSRN》 

年 卷 期：2024年

核心收录：

主　　题：Process monitoring 

摘      要：Modeling and monitoring generally face numerous challenges such as complex characteristics of multi-unit, temporal correlations and strong interaction among subblocks in large-scale industrial processes. To handle those challenges, in this paper, a novel process monitoring framework combined temporal feedback autoencoder and multilevel correlation analysis is proposed. Firstly, the large-scale industrial processes are decomposed into multiple subblocks in spatial order based on process knowledge. Secondly, an improved autoencoder with temporal feedback mechanism is constructed as local monitoring model to capture the important latent variables of each subblock. Then, considering the sequential transmission and correlations among subblocks in series, a multilevel correlation analysis method is employed to efficiently extract the unique features of subblock and the joint features of the whole process. Finally, the irregular contribution indices of the unique features and joint features are designed for hierarchical monitoring. The superiority of the proposed framework can be verified by Tennessee Eastman process. © 2024, The Authors. All rights reserved.