Adaptive inference for Bayesian network soft‐sensor in the presence of process and sensor drift. (6th July 2022)

• Record Type: Journal Article
• Authors: Khosbayar, Anudari; Valluru, Jayaram; Huang, Biao
• Is Part Of: Canadian journal of chemical engineering. Volume 100:Number 9(2022)
• Page Start: 2119
• Page End: 2134
• Publication Date: 2022-07-06
• Subjects: adaptive soft‐sensors -- Bayesian inference -- Bayesian networks; Chemical engineering -- Periodicals; Technology -- Periodicals; 660.05
• DOI: 10.1002/cjce.24487
• Languages: English
• ISSNs: 0008-4034

Abstract

Abstract: Due to its incorporation of prior process knowledge and handling of uncertainty in a probabilistic sense, Bayesian network (BN)‐based soft‐sensors have shown significant advantages compared to conventional regression‐based soft‐sensors. In the literature, these soft‐sensors are developed under the assumption that the process is operated around certain operating points. Due to the time‐varying nature of the process, the prediction performance of the existing BN‐based soft‐sensors may deteriorate over time. To account for this, in the current work, adaptive Bayesian inference using a random walk model for both process and sensor drift is proposed. The efficacy of the proposed approaches is demonstrated through simulation and industrial case studies, and they are shown to perform better than the conventional bias updated approach.