Cover Image

Investigation of fault detection and isolation accuracy of different Machine learning techniques with different data processing methods for gas turbine

Classification is an essential task for many applications, including text classification, image classification, data classification, and so on. The present study investigates the accuracy of different machine learning classification algorithms with three different data smoothing techniques for gas t...

Full description

Saved in:
Bibliographic Details
Main Authors: Molla Salilew, W., Ambri Abdul Karim, Z., Alemu Lemma, T.
Format: Article
Published: Elsevier B.V. 2022
Online Access:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85133405683&doi=10.1016%2fj.aej.2022.06.026&partnerID=40&md5=5592a5b7b2809a9d6a23372fce456819
http://eprints.utp.edu.my/33296/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utp.eprints.33296
record_format eprints
spelling my.utp.eprints.332962022-07-26T06:39:55Z Investigation of fault detection and isolation accuracy of different Machine learning techniques with different data processing methods for gas turbine Molla Salilew, W. Ambri Abdul Karim, Z. Alemu Lemma, T. Classification is an essential task for many applications, including text classification, image classification, data classification, and so on. The present study investigates the accuracy of different machine learning classification algorithms with three different data smoothing techniques for gas turbine fault detection and isolation task. The gas turbine performance model was developed by considering variable inlet guide vane and bleed air. Fouling and erosion were injected into all six main components of the gas turbine engine. Faulty and non-faulty data were generated from the developed performance model. Based on sensitivity analysis, 12 measurement parameters and 11,824 data points were selected for the development of a fault detection and isolation model. The faulty and non-faulty data were balanced, smoothed, corrected and normalized. Finally, the classification accuracy of the machine learning techniques was analyzed. The result shows that K-Nearest Neighbours, Neural Network and Decision Tree classifiers exhibited high classification accuracy, about 99 with all three data smoothing techniques. It is also observed that the computation time of Support Vector Machine is higher whereas K-Nearest Neighbours shows the lowest. Finally, the research proves that K-Nearest Neighbours is the best classification technique for gas turbine engine fault detection and isolation application. © 2022 THE AUTHORS Elsevier B.V. 2022 Article NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85133405683&doi=10.1016%2fj.aej.2022.06.026&partnerID=40&md5=5592a5b7b2809a9d6a23372fce456819 Molla Salilew, W. and Ambri Abdul Karim, Z. and Alemu Lemma, T. (2022) Investigation of fault detection and isolation accuracy of different Machine learning techniques with different data processing methods for gas turbine. Alexandria Engineering Journal, 61 (12). pp. 12635-12651. http://eprints.utp.edu.my/33296/
institution Universiti Teknologi Petronas
building UTP Resource Centre
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Petronas
content_source UTP Institutional Repository
url_provider http://eprints.utp.edu.my/
description Classification is an essential task for many applications, including text classification, image classification, data classification, and so on. The present study investigates the accuracy of different machine learning classification algorithms with three different data smoothing techniques for gas turbine fault detection and isolation task. The gas turbine performance model was developed by considering variable inlet guide vane and bleed air. Fouling and erosion were injected into all six main components of the gas turbine engine. Faulty and non-faulty data were generated from the developed performance model. Based on sensitivity analysis, 12 measurement parameters and 11,824 data points were selected for the development of a fault detection and isolation model. The faulty and non-faulty data were balanced, smoothed, corrected and normalized. Finally, the classification accuracy of the machine learning techniques was analyzed. The result shows that K-Nearest Neighbours, Neural Network and Decision Tree classifiers exhibited high classification accuracy, about 99 with all three data smoothing techniques. It is also observed that the computation time of Support Vector Machine is higher whereas K-Nearest Neighbours shows the lowest. Finally, the research proves that K-Nearest Neighbours is the best classification technique for gas turbine engine fault detection and isolation application. © 2022 THE AUTHORS
format Article
author Molla Salilew, W.
Ambri Abdul Karim, Z.
Alemu Lemma, T.
spellingShingle Molla Salilew, W.
Ambri Abdul Karim, Z.
Alemu Lemma, T.
Investigation of fault detection and isolation accuracy of different Machine learning techniques with different data processing methods for gas turbine
author_facet Molla Salilew, W.
Ambri Abdul Karim, Z.
Alemu Lemma, T.
author_sort Molla Salilew, W.
title Investigation of fault detection and isolation accuracy of different Machine learning techniques with different data processing methods for gas turbine
title_short Investigation of fault detection and isolation accuracy of different Machine learning techniques with different data processing methods for gas turbine
title_full Investigation of fault detection and isolation accuracy of different Machine learning techniques with different data processing methods for gas turbine
title_fullStr Investigation of fault detection and isolation accuracy of different Machine learning techniques with different data processing methods for gas turbine
title_full_unstemmed Investigation of fault detection and isolation accuracy of different Machine learning techniques with different data processing methods for gas turbine
title_sort investigation of fault detection and isolation accuracy of different machine learning techniques with different data processing methods for gas turbine
publisher Elsevier B.V.
publishDate 2022
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85133405683&doi=10.1016%2fj.aej.2022.06.026&partnerID=40&md5=5592a5b7b2809a9d6a23372fce456819
http://eprints.utp.edu.my/33296/
_version_ 1739833202592186368
score 13.211869

Similar Items