Ulster University Logo

A combined diagnosis system design using model-based and data-driven methods

Jung, Daniel, Ng, Kok Ng, Frisk, Erik and Krysander, Mattias (2016) A combined diagnosis system design using model-based and data-driven methods. In: 2016 3rd Conference on Control and Fault-Tolerant Systems (SysTol) Barcelona, Spain, Barcelona, Spain. IEEE. 6 pp. [Conference contribution]

[img] Text - Accepted Version
Indefinitely restricted to Repository staff only.

336kB
[img] Text - Supplemental Material
Indefinitely restricted to Repository staff only.

329kB

URL: http://dx.doi.org/10.1109/SYSTOL.2016.7739747

DOI: 10.1109/SYSTOL.2016.7739747

Abstract

A hybrid diagnosis system design is proposed that combines model-based and data-driven diagnosis methods for fault isolation. A set of residuals are used to detect if there is a fault in the system and a consistency-based fault isolation algorithm is used to compute all diagnosis candidates that can explain the triggered residuals. To improve fault isolation, diagnosis candidates are ranked by evaluating the residuals using a set of one-class support vector machines trained using data from different faults. The proposed diagnosis system design is evaluated using simulations of a model describing the air-flow in an internal combustion engine.

Item Type:Conference contribution (Paper)
Keywords:fault diagnosis, model-based, data-driven, vehicular system
Faculties and Schools:Faculty of Computing & Engineering
Faculty of Computing & Engineering > School of Engineering
ID Code:38284
Deposited By: Dr Mark Kok Ng
Deposited On:10 Apr 2018 13:56
Last Modified:10 Apr 2018 14:13

Repository Staff Only: item control page