Information concentrated variational auto-encoder for quality-related nonlinear process monitoring. (October 2020)

• Record Type: Journal Article
• Authors: Zhu, Jiazhen; Shi, Hongbo; Song, Bing; Tao, Yang; Tan, Shuai
• Is Part Of: Journal of process control. Volume 94(2020)
• Page Start: 12
• Page End: 25
• Publication Date: 2020-10
• Subjects: Process monitoring -- Variational auto-encoder -- Quality-related -- Feature extraction; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2020.08.002
• Languages: English
• ISSNs: 0959-1524

Abstract

Abstract: As the deep learning technology develops, many process monitoring methods based on auto-encoder (AE) are designed for the nonlinear industrial processes. However, these methods mainly focus on process variables and ignore the quality indicator which is crucial for the final production. To extract the latent variables which represent both process information and quality information, this paper proposes a novel algorithm named information concentrated variational auto-encoder (IFCVAE). To concentrate the quality-related information, a loading matrix regularization based on mutual information is designed, so that the strongly quality-related variables tend to have larger weights in the loading matrix. In addition, to monitor processes from the quality-related and unrelated aspects, IFCVAE decomposes the original space into two subspaces that are mutually orthogonal based on variational auto-encoder (VAE). With the help of an additional regression network, the two subspaces can correspond to the quality-related and unrelated spaces. For process monitoring, two statistics are designed for the subspaces according to Kullback–Leibler divergence. Finally, the effectiveness of IFCVAE is demonstrated by a numerical case and an industrial case. Highlights: A novel algorithm (IFCVAE) is proposed for quality-related nonlinear process monitoring IFCVAE decomposes original space into quality-related and unrelated spaces based on VAE. IFCVAE imposes a loading matrix regularization to mitigate the effect of weakly quality-related variables.