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

Daniel Jung, Mark Ng, Erik Frisk, Mattias Krysander

Research output: Contribution to journalArticle

7 Citations (Scopus)
55 Downloads (Pure)

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.
Original languageEnglish
Pages (from-to)146-156
Number of pages11
JournalControl Engineering Practice
Volume80
Early online date9 Sep 2018
DOIs
Publication statusPublished - Nov 2018

    Fingerprint

Keywords

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

Cite this