Machine learning-based scheme for multi-class fault detection in turbine engine disks

Fault detection of rotating engine components in the aircraft engine is a challenging task that must constantly be monitored to provide aviation safety. In this paper, we propose a novel approach based on multi-layer perceptron (MLP) to detect in real time the degree of faults in a turbine engine di...

Full description

Bibliographic Details
Main Authors:	Carla E. Garcia, Mario R. Camana, Insoo Koo
Format:	Article
Language:	English
Published:	Elsevier 2021-03-01
Series:	ICT Express
Subjects:	Turbine engine disk Fault detection Multi-layer perceptron (MLP) Recursive feature elimination (RFE)
Online Access:	http://www.sciencedirect.com/science/article/pii/S2405959521000096

id	doaj-798d9938a6634383a8e8a55459d86e7a
record_format	Article
spelling	doaj-798d9938a6634383a8e8a55459d86e7a2021-03-11T04:25:41ZengElsevierICT Express2405-95952021-03-01711522Machine learning-based scheme for multi-class fault detection in turbine engine disksCarla E. Garcia0Mario R. Camana1Insoo Koo2Department of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan 680-749, South KoreaDepartment of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan 680-749, South KoreaCorresponding author.; Department of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan 680-749, South KoreaFault detection of rotating engine components in the aircraft engine is a challenging task that must constantly be monitored to provide aviation safety. In this paper, we propose a novel approach based on multi-layer perceptron (MLP) to detect in real time the degree of faults in a turbine engine disk due to a crack. To further improve detection accuracy while reducing computational complexity, the recursive feature elimination (RFE) is applied as a potent feature selection method. Satisfactorily, simulation results show that the proposed framework is robust to changes in operating conditions and outperforms comparative approaches.http://www.sciencedirect.com/science/article/pii/S2405959521000096Turbine engine diskFault detectionMulti-layer perceptron (MLP)Recursive feature elimination (RFE)
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Carla E. Garcia Mario R. Camana Insoo Koo
spellingShingle	Carla E. Garcia Mario R. Camana Insoo Koo Machine learning-based scheme for multi-class fault detection in turbine engine disks ICT Express Turbine engine disk Fault detection Multi-layer perceptron (MLP) Recursive feature elimination (RFE)
author_facet	Carla E. Garcia Mario R. Camana Insoo Koo
author_sort	Carla E. Garcia
title	Machine learning-based scheme for multi-class fault detection in turbine engine disks
title_short	Machine learning-based scheme for multi-class fault detection in turbine engine disks
title_full	Machine learning-based scheme for multi-class fault detection in turbine engine disks
title_fullStr	Machine learning-based scheme for multi-class fault detection in turbine engine disks
title_full_unstemmed	Machine learning-based scheme for multi-class fault detection in turbine engine disks
title_sort	machine learning-based scheme for multi-class fault detection in turbine engine disks
publisher	Elsevier
series	ICT Express
issn	2405-9595
publishDate	2021-03-01
description	Fault detection of rotating engine components in the aircraft engine is a challenging task that must constantly be monitored to provide aviation safety. In this paper, we propose a novel approach based on multi-layer perceptron (MLP) to detect in real time the degree of faults in a turbine engine disk due to a crack. To further improve detection accuracy while reducing computational complexity, the recursive feature elimination (RFE) is applied as a potent feature selection method. Satisfactorily, simulation results show that the proposed framework is robust to changes in operating conditions and outperforms comparative approaches.
topic	Turbine engine disk Fault detection Multi-layer perceptron (MLP) Recursive feature elimination (RFE)
url	http://www.sciencedirect.com/science/article/pii/S2405959521000096
work_keys_str_mv	AT carlaegarcia machinelearningbasedschemeformulticlassfaultdetectioninturbineenginedisks AT mariorcamana machinelearningbasedschemeformulticlassfaultdetectioninturbineenginedisks AT insookoo machinelearningbasedschemeformulticlassfaultdetectioninturbineenginedisks
_version_	1724226028773048320

Machine learning-based scheme for multi-class fault detection in turbine engine disks

Similar Items