Domain Adaptation Mixture of Gaussian Processes for Online Soft Sensor Modeling of Multimode Processes When Sensor Degradation Occurs

• Published in: IEEE transactions on industrial informatics 2022-07, Vol.18 (7), p.4654-4664
• Main Authors: Zhang, Xiangrui, Song, Chunyue, Zhao, Jun, Deng, Xiaogang
• Format: Article
• Language: English
• Subjects: Adaptation; Adaptation models; Basis functions; Data models; Degradation; Domains; Gaussian domain adaptation (DA); Gaussian process; Gaussian processes; Informatics; Mapping; mixture of Gaussian processes (MGP); Mixtures; Modelling; robust soft sensor; Robustness; sensor degradation; Sensors; Transfer learning
• ISSN: 1551-3203; 1941-0050
• DOI: 10.1109/TII.2021.3120509

Sensor degradation seriously hinders the practical application of soft sensors. To reduce the negative effect of sensor degradation, in this article, we propose a robust domain adaptation mixture of Gaussian processes (DA-MGP) for online soft sensor modeling of multimode processes. Based on the decomposition of industrial data into a group of Gaussian domains, Gaussian domain discrepancy (GDD) is designed for domain adaptation and process mode recognition. After recognizing the process mode based on GDD, a Gaussian domain adaptation is presented to correct the drifted online input data by domain mapping, which can significantly improve the robustness of the soft sensor against sensor degradation. Furthermore, the domain mapping matrix is utilized as a transferred basis function for a local transferred Gaussian process component, which is used for robust soft sensor modeling. Additionally, an online block processing framework is adopted when the DA-MGP-based soft sensor is applied in online quality prediction. Finally, the TE benchmark process and a real industrial polypropylene process are employed to verify the effectiveness of the proposed method. In the designed five cases of sensor degradation, the DA-MGP-based soft sensor shows its strong robustness against sensor degradation.