文献类型：期刊文献

英文题名：Enhanced variational autoencoder with continual learning capability for multimode process monitoring

作者：Yu, Zhenhua[1];Wang, Guan[2];Jiang, Qingchao[1];Yan, Xuefeng[1];Cao, Zhixing[1,2]

机构：[1]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, State Key Lab Bioreactor Engn, Shanghai 200237, Peoples R China

年份：2025

卷号：156

外文期刊名：CONTROL ENGINEERING PRACTICE

收录：;EI(收录号：20250117622863);WOS:【SCI-EXPANDED(收录号:WOS:001421362400001)】；

基金：Acknowledgments This work was supported in part by the National Natural Science Foundation of China under Grant 62322309, Shanghai Rising-Star Pro-gram under Grant 21QA1402400, Shanghai Pilot Program for Basic Research under Grant 22TQ1400100-16, and Shanghai Science and Technology Innovation Action Plan under Grant 23S41900500.

语种：英文

外文关键词：Multimode process monitoring; Mode segmentation; Continual learning; Catastrophic forgetting

摘要：Existing mode segmentation methods in multimode process monitoring generally fail to simultaneously determine the number of modes and segmentation points. In addition, traditional monitoring methods typically suffer from "catastrophic forgetting", resulting in poor monitoring performance. This paper proposes a novel mode segmentation method called latent variable mapping greedy Gaussian segmentation (LMGGS) and enhances the variational autoencoder (VAE) with continual learning (CL-VAE) capability to address the problem of catastrophic forgetting. First, the LMGGS is used for mode segmentation, which reformulates the mode segmentation problem as a covariance-regularized maximum likelihood estimation problem. Second, weights in VAE deemed unimportant were set to zero, and the remaining ones were updated by training the model with important samples in a direction orthogonal to the gradient space of the previous modes. Finally, statistics and thresholds based on the reconstruction error were established to determine the system states. The LMGGS can simultaneously determine the segmentation point and the number of modes, while the CLVAE can effectively address catastrophic forgetting and reduce data storage requirements. The superiority of the proposed methods was validated through experiments on two simulated datasets and an actual penicillin fermentation dataset.