Combining model-based diagnosis and data-driven anomaly classifiers for fault isolation

Daniel Jung, Mark Ng, Erik Frisk, Mattias Krysander

Research output: Contribution to journalArticlepeer-review

53 Citations (Scopus)
271 Downloads (Pure)


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.
Original languageEnglish
Pages (from-to)146-156
Number of pages11
JournalControl Engineering Practice
Early online date9 Sept 2018
Publication statusPublished (in print/issue) - 30 Nov 2018


  • Fault diagnosis
  • Fault isolation
  • Machine learning
  • Artificial intelligence;
  • Classification


Dive into the research topics of 'Combining model-based diagnosis and data-driven anomaly classifiers for fault isolation'. Together they form a unique fingerprint.

Cite this