A semi-supervised soft sensor method based on vine copula regression and tri-training algorithm for complex chemical processes. (December 2022)

• Record Type: Journal Article
• Authors: Liu, Shisong; Li, Shaojun
• Is Part Of: Journal of process control. Volume 120(2022)
• Page Start: 115
• Page End: 128
• Publication Date: 2022-12
• Subjects: Soft sensor -- Tri-training algorithm -- Vine copula -- Probability model; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2022.11.004
• Languages: English
• ISSNs: 0959-1524

Abstract

Abstract: Soft sensor technology is an important solution for timely prediction of some difficult-to-measure variables in the chemical process. For the data-driven soft sensor models, the modeling process needs a certain amount of labeled samples. In some actual processes, the number of unlabeled samples is very large, but the labeling process of unlabeled samples is very time-consuming and laborious. When soft sensor modeling is performed in the case of sparse labeled samples, the generalization ability of the model is bound to be poor. To address this problem, a semi-supervised soft sensor method based on vine copula regression and tri-training algorithm (tri-training VCR) is proposed in this paper. Semi-supervised learning is to enhance the performance of supervised learning models by using unlabeled samples. The tri-training algorithm is used to expand the labeled samples through the cooperation of three vine copula regression models with different structures and a new method to judge the confidence degree of pseudo-labeled samples, so as to improve the prediction accuracy of the soft sensor model. A numerical example and an industrial example are used to demonstrate the effectiveness of the proposed method. Highlights: A semi-supervised style algorithm based on vine copula regression and tri-training algorithm has been developed. A new confidence evaluation method is proposed to more accurately judge the reliability of pseudo-label samples. Multiple vine copula regression models are reasonably integrated through variance information. Two examples are used to demonstrate the effectiveness of the proposed method.