Dynamic transfer soft sensor for concept drift adaptation. (March 2023)

• Record Type: Journal Article
• Authors: Zhang, Tianming; Yan, Gaowei; Ren, Mifeng; Cheng, Lan; Li, Rong; Xie, Gang
• Is Part Of: Journal of process control. Volume 123(2023)
• Page Start: 50
• Page End: 63
• Publication Date: 2023-03
• Subjects: Soft sensor -- Time-varying -- Concept drift -- Transfer learning -- Dynamic partial least squares; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2023.01.012
• Languages: English
• ISSNs: 0959-1524

Abstract

Abstract: Data-driven soft sensor technology has been widely used in process monitoring, quality prediction, etc. However, there are dynamic time-varying and concept drift problems in industrial processes, making the accurate modeling of the soft sensor is still a challenging task. To solve the above problems, this paper proposes a concept drift adaptive dynamic partial least squares method. The method maps high-dimensional process data into a low-dimensional latent variable subspace. Dynamic information is introduced by establishing the dynamic regression relationship between process latent variables and quality latent variables. At the same time, transfer learning is used to align second-order statistics between latent variables of data from different distributions to solve the concept drift problem. The experiments on multiple industrial datasets show that the method proposed in this paper can effectively reduce prediction errors and improve the generalization ability of the model. Graphical abstract: Highlights: Distribution alignment and dynamic system modeling are realized under NIPALS. The objective function is organized into the form of Rayleigh quotient. There are few hyperparameters and they have better interpretability. Experiments show that our method can adapt to the change of data distribution well.