Adaptive soft sensors for quality prediction under the framework of Bayesian network. (March 2018)

• Record Type: Journal Article
• Authors: Liu, Ziwei; Ge, Zhiqiang; Chen, Guangjie; Song, Zhihuan
• Is Part Of: Control engineering practice. Volume 72(2018)
• Page Start: 19
• Page End: 28
• Publication Date: 2018-03
• Subjects: Model degradation -- Adaptive soft sensor -- Bayesian network -- Quality prediction; Automatic control -- Periodicals; 629.89
• DOI: 10.1016/j.conengprac.2017.10.018
• Languages: English
• ISSNs: 0967-0661

Abstract

Abstract: Soft sensor is widely used to predict quality-relevant variables which are usually hard to measure timely. Due to model degradation, it is necessary to construct an adaptive model to follow changes of the process. Adaptive models—moving windows (MW), time difference (TD), and locally weighted regression (LWR) under the framework of Bayesian network (BN) are proposed in this paper. BN shows great superiorities over other traditional methods, especially in dealing with missing data and the ability of learning causality. Furthermore, the acquisition of variances in BN makes it possible to perform fault detection, on the basis of 3-sigma criterion. A debutanizer column and CO2 absorption column are provided as two industrial examples to validate the effectiveness of our proposed techniques. In a debutanizer column, RMSE of MW-BN is decreased by 40% in comparison to MW-PLS. In a CO2 absorption column, the largest absolute prediction error of TD-BN is reduced by approximate 7% when compared with that of TD-PLS. Furthermore, about 38% improvements of prediction precision can be achieved in LW-BN in contrast to LW-PLS. Highlights: Bayesian network with adaptive techniques is introduced for quality prediction. The capacity of coping with missing values stands it out among other traditional soft sensor models. Acquisition of variances in the proposed methods makes it possible to perform preliminary fault detection. A more satisfactory performance has been achieved in two real-world industrial examples.