Engine-fault diagnostics:an optimisation procedure

Suresh Sampath, Stephen Ogaji, Riti Singh and Douglas Probert

Applied Energy, 2002, vol. 73, issue 1, 47-70

Abstract: A diagnostic process capable of providing an early warning of a fault in a gas turbine is of tremendous value to the user and can result in substantial financial savings. The approach in the Genetic Algorithm based technique adopted is to treat the problem of engine diagnostics as an optimisation exercise using sensor-based and mathematical behavioural model based information. The engine performance model would simulate a range of possible combinations of potential faults (i.e the effects of model-based information) and a comparison would be made with values of the actual (sensor-based) parameters obtained from an engine. The difference between the actual and simulated values of would be converted into a suitable objective-function and the aim of the optimisation technique such as the genetic algorithm would be to minimise the objective function. The technique has given promising results for simple cycle engines.

Keywords: Engine; diagnostics; Genetic; algorithm; Optimisation (search for similar items in EconPapers)
Date: 2002
References: View complete reference list from CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306-2619(02)00051-X
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:73:y:2002:i:1:p:47-70

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().