TY  - CONF
CY  - Kuala Lumpur
AV  - none
N2  - This work presents a Fault Detection and Diagnosis (FDD) system that uses a combination of discrete wavelet transform and auto-associative neural network. The neural network is trained by Levenberg-Marquardt (LM) algorithm. As a case study, it considers a 5.2MW Siemens Taurus 60S industrial gas turbine. The work is unique in the sense that it addresses the signals in the gas path, generator coils, lubrication system, and vibration sensors. Real data are used to train and corroborate the models. In order to test validity of the FDD system, we used abrupt and incipient faults generated by implanting controlled bias to the normal signals. Results show that the proposed method could detect a 10 bias with an average true detection higher than 95 while the diagnoses performance is in the range of 96 to 100. Since it is designed and tested based on real data, it can be considered competent for practical use. © 2012 IEEE.
N1  - cited By 12; Conference of 2012 IEEE Business, Engineering and IndustrialApplications Colloquium, BEIAC 2012 ; Conference Date: 7 April 2012 Through 8 April 2012; Conference Code:91285
KW  - Autoassociative neural networks; Fault detection and diagnosis; Fault detection and diagnosis systems; FDD systems; Gas path; Generator Coils; Incipient faults; Industrial gas turbines; Levenberg-Marquardt algorithm; Lubrication system; Siemens; Test validity; Vibration sensors
KW  -  Damage detection; Discrete wavelet transforms; Gases; Industrial applications; Lubrication; Neural networks; Signal detection; Wavelet analysis; Wavelet transforms
KW  -  Gas turbines
SP  - 103
ID  - scholars2930
TI  - Wavelet analysis and auto-associative neural network based fault detection and diagnosis in an industrial gas turbine
Y1  - 2012///
SN  - 9781467304269
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-84864259998&doi=10.1109%2fBEIAC.2012.6226031&partnerID=40&md5=bfb801d106237f0def2483d32c6f4fe3
A1  - Lemma, T.A.
A1  - Hashim, F.M.
EP  - 108
ER  -