Abstract
The paper presents readily implementable approaches for fault detection and diagnosis (FDD) based on measurements from multiple sensor groups, for industrial systems. Specifically, the use of hierarchical clustering (HC) and self-organizing map neural networks (SOMNNs) are shown to provide robust and user-friendly tools for application to industrial gas turbine (IGT) systems. HC fingerprints are found for normal operation, and FDD is achieved by monitoring cluster changes occurring in the resulting dendrograms. Similarly, fingerprints of operational behaviour are also obtained using SOMNN based classification maps (CMs) that are initially determined during normal operation, and FDD is performed by detecting changes in their CMs. The proposed methods are shown to be capable of FDD from a large group of sensors that measure a variety of physical quantities. A key feature of the paper is the development of techniques to accommodate transient system operation, which can often lead to false-alarms being triggered when using traditional techniques if the monitoring algorithms are not first desensitized. Case studies showing the efficacy of the techniques for detecting sensor faults, bearing tilt pad wear and early stage pre-chamber burnout, are included. The presented techniques are now being applied operationally and monitoring IGTs in various regions of the world.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
M. Jiang, M. A. Munawar, T. Reidemeister, P. A. S. Ward. Efficient fault detection and diagnosis in complex software systems with information-theoretic monitoring. IEEE Transactions on Dependable and Secure Computing, vol.8, no. 4, pp. 510–522, 2011.
Q. Y. Su, Y. C. Li, X. Z., Dai, J. Li. Fault detection for a class of impulsive switched systems. International Journal of Automation and Computing, vol. 11, no. 2, pp. 223–230, 2014.
F. Y. Chen, S. J. Zhang, B. Jiang, G. Tao. Multiple modelbased fault detection and diagnosis for helicopter with actuator faults via quantum information technique. Proceedings of the Institution of Mechanical Engineers, Part I: Journal of Systems and Control Engineering, vol. 228, no. 3, pp. 182–190, 2014.
A. Soualhi, G. Clerc, H. Razik. Detection and diagnosis of faults in induction motor using an improved artificial ant clustering technique. IEEE Transactions on Industrial Electronics, vol. 60, no. 9, pp. 4053–4062, 2013.
F. Lu, J. Q. Huang, Y. D. Xing. Fault diagnostics for turboshaft engine sensors based on a simplified on-board model. Sensors, vol. 12, no. 8, pp. 11061–11076, 2012.
P. M. Frank. Fault diagnosis in dynamic systems using analytical and knowledge-based redundancy: A survey and some new results. Automatica, vol. 26, no. 3, pp. 459–474, 1990.
Y. Zhang, C. M. Bingham, M. Gallimore. Fault detection and diagnosis based on extensions of PCA. Advances in Military Technology, vol. 8, no. 2, pp. 27–41, 2013.
W. Deng, X. H. Yang, J. J. Liu, H. M. Zhao, Z. G. Li, X. L. Yan. A novel fault analysis and diagnosis method based on combining computational intelligence methods. Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering, vol. 227, no. 3, pp. 198–210, 2013.
M. F. Harkat, S. Djelel, N. Doghmane, M. Benouaret. Sensor fault detection, isolation and reconstruction using nonlinear principal component analysis. International Journal of Automation and Computing, vol. 4, no. 2, pp. 149–155, 2007.
B. Lee, X. S. Wang. Fault detection and reconstruction for micro-satellite power subsystem based on PCA. In Proceedings of the 3rd International Symposium on Systems and Control in Aeronautics and Astronautics (ISSCAA), IEEE, Harbin, China, pp. 1169–1173, 2010.
H. B. Liu, M. J. Kim, O. Y. Kang, B. Sankararao, J. T. Kim, C. K. Yoo. Sensor validation for monitoring indoor air quality in a subway station. In Proceedings of the 5th International Symposium on Sustainable Healthy Buildings, Seoul, Korea, pp. 477–489, 2011.
Y. H. Li, M. J. Pont, N. B. Jones, J. A. Twiddle. Applying MLP and RBF classifiers in embedded condition monitoring and fault diagnosis systems. Transactions of the Institute of Measurement and Control, vol. 23, no. 5, pp. 315–343, 2001.
J. B. Yu. A hybrid feature selection scheme and selforganizing map model for machine health assessment. Applied Soft Computing, vol. 11, no. 5, pp. 4041–4054, 2011.
X. Chen, T. Limchimchol. Monitoring grinding wheel redress-life using support vector machines. International Journal of Automation and Computing, vol. 3, no. 1, pp. 56–62, 2006.
N. Laouti, S. Othman, M. Alamir, N. Sheibat-Othman. Combination of model-based observer and support vector machines for fault detection of wind turbines. International Journal of Automation and Computing, vol. 11, no. 3, pp. 274–287, 2014.
L. B. Jack, A. K. Nandi. Fault detection using support vector machines and artificial neural networks, augmented by genetic algorithms. Mechanical Systems and Signal Processing, vol. 16, no. 2–3, pp. 373–390, 2002.
S. T.Wu, T. W. S. Chow. Induction machine fault detection using SOM-based RBF neural networks. IEEE Transactions on Industrial Electronics, vol. 51, no. 1, pp. 183–194, 2004.
L. F. Gon¸calves, J. L. Bosa, T. R. Balen, M. S. Lubaszewski, E. L. Schneider, R. V. Henriques. Fault detection, diagnosis and prediction in electrical valves using self-organizing maps. Journal of Electronic Testing, vol. 27, no. 4, pp. 551–564, 2011.
A. A. Datta, C. A. Mavroidis, M. B. Hosek. A role of unsupervised clustering for intelligent fault diagnosis. In Proceedings of ASME International Mechanical Engineering Congress and Exposition, Seattle, Washington, USA, 2007.
Y. Kun, W. Bao, Q. Hu, D. Yu. Abnormal data detection based on hierarchical clustering. Power Engineering, vol. 25, no. 6, pp. 865–869, 2005.
Y. G. Zhang, J. F. Zhang, J. Ma, Z. P. Wang. Fault detection based on hierarchical cluster analysis in wide area backup protection system. Energy and Power Engineering, vol. 1, no. 1, pp. 21–27, 2009.
C. Romesis, K. Mathioudakis. Setting up of a probabilistic neural network for sensor fault detection including operation with component faults. Journal of Engineering for Gas Turbines and Power, vol. 125, no. 3, pp. 634–641, 2003.
T. Kobayashi, D. L. Simon. Hybrid Kalman filter approach for aircraft engine in-flight diagnostics: Sensor fault detection case. Journal of Engineering for Gas Turbines and Power, vol. 129, no. 3, pp. 746–754, 2006.
T. Hastie, R. Tibshirani, J. Friedman. 14.3.12 Hierarchical clustering. The Elements of Statistical Learning, NewYork, USA, Springer, pp. 520–528, 2009.
T. Kohonen. Self-organized formation of topologically correct feature maps. Biological Cybernetics, vol. 43, no. 1, pp. 59–69, 1982.
MATLAB Version 7.10.0. The Mathworks, Natick Mass, USA, 2010.
Acknowledgments
The authors would like to thank Siemens Industrial Turbomachinery, Lincoln, UK, for providing research support, access to on-line real-time data, and photos to support the research outcomes.
Author information
Authors and Affiliations
Corresponding author
Additional information
Recommended by Associate Editor Dong-Hua Zhou
Yu Zhang received the B.Eng. degree from the School of Aerospace Engineering and Applied Mechanics, Tongji University, China in 2004, and received the M. Sc. and Ph.D. degrees from the School of Civil Engineering, University of Nottingham, UK, in 2005 and 2011, respectively. She is currently a lecturer in the School of Engineering, University of Lincoln, UK.
Her research interests include fault detection and diagnosis, signal processing, neural networks and clustering analysis.
Chris Bingham received the B. Eng. degree in electronic systems and control engineering, from Shefield City Polytechnic, UK, in 1989, the M. Sc(Eng) degree in control systems engineering from the University of Shefield, Sheffield, UK, in 1990, and the Ph. D. from Cranfield University, UK, in 1994, where his research focused on control systems to accommodate nonlinear dynamic effects in aerospace flight-surface actuators. From 1994 to 2010, he held academic positions at the University of Sheffleld as a researcher, lecturer and senior lecturer. He is currently professor of Energy Conversion, and college of Science Director of Research at the University of Lincoln, UK. Prof. Bingham has made significant contributions to a diverse range of national and internationally funded research, with a bias towards industrial applications. He currently heads a research team investigating sensor fault detection and remedial strategies, and prognostic and diagnostic techniques for a global fleet of sub-15MW industrial gas turbines in order to maximize unit operational availability. He also actively pursues collaborative research into the modeling of the thermal environment of domestic buildings and their thermal control, and has a long-standing track record in EV/HEV research.
Mike Garlick received the B. Eng. degree in mechanical engineering, from Sheffield Hallam University in 2013. Having worked at Siemens Industrial Turbomachinery Ltd (Lincoln) since 2005 with a background in combustion design, he is currently working as a service support engineer involved in remote monitoring projects.
Michael Gallimore received the B.Eng. degree in mechanical and computer aided engineering from Sheffield Hallam University, UK, in 2006. He is currently a principal lecturer in the School of Engineering, University of Lincoln, UK. Prior to this, he spent ten years working for Siemens Industrial Turbomachinery Ltd, UK with various roles including design engineer, senior support engineer and service manager.
His research interests include intelligent diagnostics and prognostics for complex systems, signal processing, optimization and biomedical engineering.
Rights and permissions
About this article
Cite this article
Zhang, Y., Bingham, C., Garlick, M. et al. Applied fault detection and diagnosis for industrial gas turbine systems. Int. J. Autom. Comput. 14, 463–473 (2017). https://doi.org/10.1007/s11633-016-0967-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11633-016-0967-5