Gaussian feature learning based on variational autoencoder for improving nonlinear process monitoring. (March 2019)

• Record Type: Journal Article
• Authors: Zhang, Zehan; Jiang, Teng; Zhan, Chengjun; Yang, Yupu
• Is Part Of: Journal of process control. Volume 75(2019)
• Page Start: 136
• Page End: 155
• Publication Date: 2019-03
• Subjects: Nonlinear process monitoring -- Deep learning -- Variational autoencoder -- Gaussian feature learning; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2019.01.008
• Languages: English
• ISSNs: 0959-1524

Abstract

Highlights: Gaussian feature learning based on variational autoencoder for improving nonlinear process monitoring. VAE is used to automatically learn the patterns inherent in the nonlinear process and extract Gaussian features. New monitoring statistic that is H 2 is constructed, whose control limit can be easily determined by a χ 2 distribution. The effectiveness of the proposed method is verified by two case studies including a nonlinear numerical example and TE benchmark process. Abstract: Deep learning algorithms, especially the autoencoders, have been applied in nonlinear process monitoring recently. However, the features extracted by the autoencoders can hardly follow the Gaussian distribution, consequently, the control limit of the corresponding monitoring statistic can not be determined by an F or χ 2 distribution. Recent improvements in the unsupervised learning domain of deep learning offer opportunities to avoid the problem. In this paper, a novel nonlinear process monitoring method based on variational autoencoder (VAE) is proposed to tackle the Gaussian assumption problem. Due to the Gaussian distribution limitation added in the hidden layer of the VAE, it can not only automatically learn the key features of the nonlinear system, but also learn features that follow the Gaussian distribution. The Gaussian feature representations obtained from VAE are then provided to construct a new statistic H 2 whose control limit can be easily determined by a χ 2 distribution. A nonlinear numerical study and the TE benchmark process have verified the effectiveness of the proposed method.