Fault diagnostic model for rotating machinery based on principal component analysis and neural network

In the current economic challenge, methods to accurately predict system failure has become a holy grail in maintenance with the goal to reduce the cost of unavailability due to unscheduled shutdown. This has led to the current research with the aim to achieve a more accurate fault diagnosis for rota...

Full description

Main Authors: Muhammad, M.B, Sarwar, U., Tahan, M.R., Abdul Karim, Z.A.
Format: Article
Institution: Universiti Teknologi Petronas
Record Id / ISBN-0: utp-eprints.25316 /
Published: Asian Research Publishing Network 2016
Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85009230977&partnerID=40&md5=fca03f86730f7990ca001fa0e14380df
http://eprints.utp.edu.my/25316/
Tags: Add Tag
No Tags, Be the first to tag this record!
id utp-eprints.25316
recordtype eprints
spelling utp-eprints.253162021-08-27T12:57:14Z Fault diagnostic model for rotating machinery based on principal component analysis and neural network Muhammad, M.B Sarwar, U. Tahan, M.R. Abdul Karim, Z.A. In the current economic challenge, methods to accurately predict system failure has become a holy grail in maintenance with the goal to reduce the cost of unavailability due to unscheduled shutdown. This has led to the current research with the aim to achieve a more accurate fault diagnosis for rotating machinery using a neural network (NN) with principal component analysis (PCA) as a pre-processing step to fuse multiple sensor data. The multisensor data fusion has been proven to improve the fault detection ability for machinery compared to single source condition monitoring. In this paper, an NN-based methodology is presented, where PCA is applied as preprocessing step to detect the rotating machinery faults during operation. The effectiveness of the proposed model is illustrated by a case study on two shaft industrial gas turbine where the real-time performance monitoring data collected from the plant and used to train and test the proposed algorithm. The analysis results show that the PCA-based fusion process has significantly enhanced the performance of NNbased model when compared against NN algorithm without PCA. © 2006-2016 Asian Research Publishing Network (ARPN). All rights reserved. Asian Research Publishing Network 2016 Article NonPeerReviewed https://www.scopus.com/inward/record.uri?eid=2-s2.0-85009230977&partnerID=40&md5=fca03f86730f7990ca001fa0e14380df Muhammad, M.B and Sarwar, U. and Tahan, M.R. and Abdul Karim, Z.A. (2016) Fault diagnostic model for rotating machinery based on principal component analysis and neural network. ARPN Journal of Engineering and Applied Sciences, 11 (24). pp. 14327-14331. http://eprints.utp.edu.my/25316/
institution Universiti Teknologi Petronas
collection UTP Institutional Repository
description In the current economic challenge, methods to accurately predict system failure has become a holy grail in maintenance with the goal to reduce the cost of unavailability due to unscheduled shutdown. This has led to the current research with the aim to achieve a more accurate fault diagnosis for rotating machinery using a neural network (NN) with principal component analysis (PCA) as a pre-processing step to fuse multiple sensor data. The multisensor data fusion has been proven to improve the fault detection ability for machinery compared to single source condition monitoring. In this paper, an NN-based methodology is presented, where PCA is applied as preprocessing step to detect the rotating machinery faults during operation. The effectiveness of the proposed model is illustrated by a case study on two shaft industrial gas turbine where the real-time performance monitoring data collected from the plant and used to train and test the proposed algorithm. The analysis results show that the PCA-based fusion process has significantly enhanced the performance of NNbased model when compared against NN algorithm without PCA. © 2006-2016 Asian Research Publishing Network (ARPN). All rights reserved.
format Article
author Muhammad, M.B
Sarwar, U.
Tahan, M.R.
Abdul Karim, Z.A.
spellingShingle Muhammad, M.B
Sarwar, U.
Tahan, M.R.
Abdul Karim, Z.A.
Fault diagnostic model for rotating machinery based on principal component analysis and neural network
author_sort Muhammad, M.B
title Fault diagnostic model for rotating machinery based on principal component analysis and neural network
title_short Fault diagnostic model for rotating machinery based on principal component analysis and neural network
title_full Fault diagnostic model for rotating machinery based on principal component analysis and neural network
title_fullStr Fault diagnostic model for rotating machinery based on principal component analysis and neural network
title_full_unstemmed Fault diagnostic model for rotating machinery based on principal component analysis and neural network
title_sort fault diagnostic model for rotating machinery based on principal component analysis and neural network
publisher Asian Research Publishing Network
publishDate 2016
url https://www.scopus.com/inward/record.uri?eid=2-s2.0-85009230977&partnerID=40&md5=fca03f86730f7990ca001fa0e14380df
http://eprints.utp.edu.my/25316/
_version_ 1741196954779516928
score 11.62408

Similar Items