Detection of Emerging Faults on Industrial Gas Turbines Using Extended Gaussian Mixture Models

This paper extends traditional Gaussian mixture model (GMM) techniques to provide recognition of operational states and detection of emerging faults for industrial systems. A variational Bayesian method allows a GMM to cluster with its mixture components to facilitate the extraction of steady-state...

Full description

Saved in:
Bibliographic Details
Main Authors: Yu Zhang, Chris Bingham, Miguel Martínez-García, Darren Cox
Format: Article
Language:English
Published: Wiley 2017-01-01
Series:International Journal of Rotating Machinery
Online Access:http://dx.doi.org/10.1155/2017/5435794
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832554604405981184
author Yu Zhang
Chris Bingham
Miguel Martínez-García
Darren Cox
author_facet Yu Zhang
Chris Bingham
Miguel Martínez-García
Darren Cox
author_sort Yu Zhang
collection DOAJ
description This paper extends traditional Gaussian mixture model (GMM) techniques to provide recognition of operational states and detection of emerging faults for industrial systems. A variational Bayesian method allows a GMM to cluster with its mixture components to facilitate the extraction of steady-state operational behaviour; this is recognised as being a primary factor in reducing the susceptibility of alternative prognostic/diagnostic techniques, which would initiate false-alarms resulting from control set-point and load changes. Furthermore, a GMM with an outlier component is discussed and applied for direct novelty/fault detection. An advantage of the variational Bayesian method over traditional predefined thresholds is the extraction of steady-state data during both full- and part-load cases, and a primary advantage of the GMM with an outlier component is its applicability for novelty detection when there is a lack of prior knowledge of fault patterns. Results obtained from the real-time measurements on the operational industrial gas turbines have shown that the proposed technique provides integrated preprocessing, benchmarking, and novelty/fault detection methodology.
format Article
id doaj-art-ef82855420e64d089014f37ff556832c
institution Kabale University
issn 1023-621X
1542-3034
language English
publishDate 2017-01-01
publisher Wiley
record_format Article
series International Journal of Rotating Machinery
spelling doaj-art-ef82855420e64d089014f37ff556832c2025-02-03T05:51:04ZengWileyInternational Journal of Rotating Machinery1023-621X1542-30342017-01-01201710.1155/2017/54357945435794Detection of Emerging Faults on Industrial Gas Turbines Using Extended Gaussian Mixture ModelsYu Zhang0Chris Bingham1Miguel Martínez-García2Darren Cox3School of Engineering, University of Lincoln, Lincoln LN6 7TS, UKSchool of Engineering, University of Lincoln, Lincoln LN6 7TS, UKSchool of Engineering, University of Lincoln, Lincoln LN6 7TS, UKSiemens Industrial Turbomachinery Ltd., Lincoln LN5 7FD, UKThis paper extends traditional Gaussian mixture model (GMM) techniques to provide recognition of operational states and detection of emerging faults for industrial systems. A variational Bayesian method allows a GMM to cluster with its mixture components to facilitate the extraction of steady-state operational behaviour; this is recognised as being a primary factor in reducing the susceptibility of alternative prognostic/diagnostic techniques, which would initiate false-alarms resulting from control set-point and load changes. Furthermore, a GMM with an outlier component is discussed and applied for direct novelty/fault detection. An advantage of the variational Bayesian method over traditional predefined thresholds is the extraction of steady-state data during both full- and part-load cases, and a primary advantage of the GMM with an outlier component is its applicability for novelty detection when there is a lack of prior knowledge of fault patterns. Results obtained from the real-time measurements on the operational industrial gas turbines have shown that the proposed technique provides integrated preprocessing, benchmarking, and novelty/fault detection methodology.http://dx.doi.org/10.1155/2017/5435794
spellingShingle Yu Zhang
Chris Bingham
Miguel Martínez-García
Darren Cox
Detection of Emerging Faults on Industrial Gas Turbines Using Extended Gaussian Mixture Models
International Journal of Rotating Machinery
title Detection of Emerging Faults on Industrial Gas Turbines Using Extended Gaussian Mixture Models
title_full Detection of Emerging Faults on Industrial Gas Turbines Using Extended Gaussian Mixture Models
title_fullStr Detection of Emerging Faults on Industrial Gas Turbines Using Extended Gaussian Mixture Models
title_full_unstemmed Detection of Emerging Faults on Industrial Gas Turbines Using Extended Gaussian Mixture Models
title_short Detection of Emerging Faults on Industrial Gas Turbines Using Extended Gaussian Mixture Models
title_sort detection of emerging faults on industrial gas turbines using extended gaussian mixture models
url http://dx.doi.org/10.1155/2017/5435794
work_keys_str_mv AT yuzhang detectionofemergingfaultsonindustrialgasturbinesusingextendedgaussianmixturemodels
AT chrisbingham detectionofemergingfaultsonindustrialgasturbinesusingextendedgaussianmixturemodels
AT miguelmartinezgarcia detectionofemergingfaultsonindustrialgasturbinesusingextendedgaussianmixturemodels
AT darrencox detectionofemergingfaultsonindustrialgasturbinesusingextendedgaussianmixturemodels