Streaming parallel variational Bayesian supervised factor analysis for adaptive soft sensor modeling with big process data. (January 2020)

• Record Type: Journal Article
• Authors: Yang, Zeyu; Yao, Le; Ge, Zhiqiang
• Is Part Of: Journal of process control. Volume 85(2020)
• Page Start: 52
• Page End: 64
• Publication Date: 2020-01
• Subjects: Adaptive soft sensor -- Streaming variational Bayesian -- Parallel computing strategy -- Supervised factor analysis -- Big process data; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2019.10.010
• Languages: English
• ISSNs: 0959-1524

Abstract

Highlights: Time-varying and state shifting features are considered for soft sensor modeling. Variational Bayesian Supervised Factor Analysis is proposed for adaptive soft sensor development. A streaming parallel form of Variational Bayesian Supervised Factor Analysis is constructed to improve the modeling efficiency. A numerical example and a real industrial process are provided for performance evaluation. Abstract: Time-varying and state shifting are two of the main process factors that cause poor prediction performance of soft sensors. Adaptive soft sensor is commonly an alternative practice to ensure high predictive accuracy. However, the large scale of process data often leads to inefficiency of model updating. In this paper, a streaming variational Bayesian supervised factor analysis (S-VBSFA) model is first proposed to capture the process time-varying and state shifting features through online updating of the posterior of model parameters. During the updating process, the symmetric Kullback–Leibler (SKL) divergence is utilized to determine priors of the next variation Bayesian inference. To improve the modeling efficiency for large-scale process data, the parallel computing strategy is further applied to the streaming model. As a result, the proposed streaming parallel VBSFA (SP-VBSFA) algorithm not only relieves the computing pressure of modeling big process data, but also improves the prediction accuracy and further reduces the tracking time delay for process variations. Two case studies demonstrate the superiority of the proposed method, compared to conventional methods.