Performance Based Anomaly Detection Analysis of a Gas Turbine Engine by Artificial Neural Network Approach



Amar Kumar Alka Srivastava Avisekh Banerjee Alok Goel


This present work follows our earlier research efforts on fault diagnosis and prognosis solutions considering statistical and physics based approaches. In-service performance analysis and detection of any malfunctioning in an operating small sized gas turbine engine using artificial neural network approach is the central theme of this work. The measured engine operating and performance parameters are used to train two neural network models, namely back propagation and generalized regression. Following the training and validation of the neural network model, simulation results for test data corresponding to various engine usage stages are found to be close by two models. The analysis identifies an anamoly in the simulated and measured data collected 17 months after the engine overhauling which may be attributed to deliberate adjustments in the operating parameters. A threshold for anomaly detection in terms of the probability levels for variation of the rated power capacity of the engine is also studied.

How to Cite

Kumar, A. ., Srivastava, A., Banerjee, A., & Goel, A. . (2012). Performance Based Anomaly Detection Analysis of a Gas Turbine Engine by Artificial Neural Network Approach. Annual Conference of the PHM Society, 4(1).
Abstract 45 | PDF Downloads 34



anomaly detection, artificial neural networks, gas turbine, overhauling, performance analysis

Clifton, D., (2006). Condition monitoring of gas turbine engines, Doctoral thesis, Department of Engineering Science, University of Oxford.

Hoeft, R., Janawitz, J. & Keck, R., (2003). Heavy duty gas turbine operating and maintenance considerations, GE Power Systems, GER-3620J

Sobanska, P. & Szczepaniak, P., (2006). Neural modeling of steam turbines, Proceedings of the International Multiconference on Computer Science and Information Technology, (pp. 197–205), November 6-10, 2006, Wisla, Poland

Fast, M., (2010). Artificial neural networks for gas turbine monitoring, Doctoral thesis, Faculty of Engineering, Lund University, Sweden

Fast, M. & Palmé, T., (2010). Application of artificial neural network to the condition monitoring and diagnosis of a combined heat and power plant, Journal of Energy, vol. 35 (2), pp. 1114-1120

Angeli, C. & Chatzinikolaou, A., (2004). On-Line fault detection techniques for technical systems: A survey, International Journal of Computer Science & Applications, Technomathematics Research Foundation, vol. I (1), pp. 12 – 30

Russell, S. & Norvig, P., (1995). Artificial intelligence: A modern approach, New York, Prentice-Hall Inc.

Saxena, B., Kumar, A., Srivastava, A. & Goel, A., (2011). Real time diagnostic prognostic solution for life cycle management of thermomechanical system, IEEE Canadian Conference on Electrical and Computer Engineering (pp. 999-1003), May 8-10, Niagara Falls, Canada

Kumar, A., Saxena, B., Srivastava,A. & Goel, A., (2011). Physics based prognostic health management for thermal Barrier Coating System, Proceeding.
Prognostic and Health Management Society Conference, vol. 2 (6), September 25-29, Montreal, Canada

Michael J. A. Berry & Gordon Linoff, (1997). Data Mining Techniques: For Marketing, Sales, and Customer Support, Database management, New Y ork, Computer Publishing Wiley

Boger, Z. & Guterman, H., (1997). Knowledge extraction from artificial neural network models, Proceedings of the IEEE Conference on Systems, Man and Cybernetics (pp. 3030 - 3035), October 12-15, Orlando, USA

Zhu, J., (2009). Marine diesel engine condition monitoring by use of BP neural network, Proceedings of the International Multi Conference of Engineers and Computer Scientists, Vol. II, March 18-20, Hong Kong

Kumara, K.P ., Rao, K.V .N.S. , Krishnan, K.R.& Thejaa, B., (2012). Neural network based vibration analysis with novelty in data detection for a large gas turbine, Shock and Vibration, vol. 19, pp. 25–35

Patel, P. M. & Prajapati, J.M., (2011). A review on artificial intelligent system for bearing condition monitoring, International journal of engineering science and technology, vol. 3 (2), pp. 1520-1525

Samhouri, M. , Al-Ghandoor, A., Alhaj Ali, S., Hinti, I. & Massad, I., (2009). An intelligent machine condition monitoring system using time-based analysis: neuro- fuzzy versus neural network, Jordan Journal of Mechanical and Industrial Engineering, vol. 3 (4), pp. 294 – 305.

Riad, A.M, Elminir K.H., & Elattar, M. H., (2010). Evaluation of neural networks in the subject of prognostics as compared to linear regression model, International Journal of Engineering & Technology IJET-IJENS, vol: 10 (6), pp. 52 - 58

Specht, D. F. (1991). A general regression neural network, IEEE Transactions on Neural Networks, vol. 2 (6), pp. 568-577.

Kaminski, M., (2010). General regression neural networks as rotor fault detectors of the induction motor, IEEE International Conference on Industrial Technology (ICIT'10) (pp. 1239 – 1244), March 14-17, Vina del Mar, Chile
Poster Presentations

Most read articles by the same author(s)