A hybrid framework for process monitoring: Enhancing data-driven methodologies with state and parameter estimation

• Published in: Journal of process control 2020-08, Vol.92, p.333-351
• Main Authors: Destro, Francesco, Facco, Pierantonio, García Muñoz, Salvador, Bezzo, Fabrizio, Barolo, Massimiliano
• Format: Article
• Language: English
• Subjects: Extended Kalman filter; Fault detection; Fault diagnosis; Hybrid modeling; Industry 4.0; Process monitoring; State estimation
• ISSN: 0959-1524; 1873-2771
• DOI: 10.1016/j.jprocont.2020.06.002

In this study we bridge traditional standalone data-driven and knowledge-driven process monitoring approaches by proposing a novel hybrid framework that exploits the advantages of both simultaneously. Namely, we design a process monitoring system based on a data-driven model that includes two different data types: i) “actual” data coming from sensor measurements, and ii) “virtual” data coming from a state estimator, based on a first-principles model of the system under investigation. We test the proposed approach on two simulated case studies: a continuous polycondensation process for the synthesis of poly-ethylene terephthalate, and a fed-batch fermentation process for the manufacturing of penicillin. The hybrid monitoring model shows superior fault detection and diagnosis performances with respect to conventional monitoring techniques, even when the first-principles model is relatively simple and process/model mismatch exists. [Display omitted] •Monitoring system built on a hybrid knowledge-driven/data-driven framework.•Knowledge-driven block estimates states, and passes them to data-driven block.•Augmented data matrix including measurements and estimated states.•Improved detection and diagnosis than with data- or knowledge-driven in isolation.