Combining model-based diagnosis and data-driven anomaly classifiers for fault isolation. (November 2018)

• Record Type: Journal Article
• Authors: Jung, Daniel; Ng, Kok Yew; Frisk, Erik; Krysander, Mattias
• Is Part Of: Control engineering practice. Volume 80(2018)
• Page Start: 146
• Page End: 156
• Publication Date: 2018-11
• Subjects: Fault diagnosis -- Fault isolation -- Machine learning -- Artificial intelligence -- Classification; Automatic control -- Periodicals; 629.89
• DOI: 10.1016/j.conengprac.2018.08.013
• Languages: English
• ISSNs: 0967-0661

Abstract

Abstract: Machine learning can be used to automatically process sensor data and create data-driven models for prediction and classification. However, in applications such as fault diagnosis, faults are rare events and learning models for fault classification is complicated because of lack of relevant training data. This paper proposes a hybrid diagnosis system design which combines model-based residuals with incremental anomaly classifiers. The proposed method is able to identify unknown faults and also classify multiple-faults using only single-fault training data. The proposed method is verified using a physical model and data collected from an internal combustion engine.