An innovative approach in fault diagnostics of steam turbine performance using ANN and M-SVM algorithms

S. Devi(1*), L. Siva Kumar(2)

(1) Department of ECE at V.S.B Engineering College, Karur, India., India
(2) Sri Krishna College of Engineering & Technology, Coimbatore., India
(*) Corresponding author

DOI's assignment:
the author of the article can submit here a request for assignment of a DOI number to this resource!
Cost of the service: euros 10,00 (for a DOI)


In this study, an artificial neural network (ANN) and multi-support vector machine (M-SVM) models are developed to predict seven kinds of faults associated with turbine of thermal power plant. Information about changes with respect to base (design / performance guaranteed) values in seven key parameters/indices namely  throttle flow, throttle pressure, first stage pressure, hot reheat pressure, cross-over pressure, HP efficiency and IP efficiency enable proper interpretation of different faults such as solid particle erosion (SPE ) in HP turbine, IP turbine, deposits and peening in HP turbine, deposits and peening in IP turbine, deposits in IP turbine, rubs in IP turbine and deposits and damages in IP turbine. All the fault types are diagnosed based on observation of seven process parameters/ indices over a long time.  The trends of changes - either increasing or decreasing direction – with respect to base values are fed as inputs to the networks and their output identifies the type of fault. A comparison between the classifier models is discussed with the proposed action plan to improve the smooth running of the machines
Copyright © 2014 Praise Worthy Prize - All rights reserved.


Thermal Power plant, Steam turbine, Artificial Neural Network, Multi class- SVM

Full Text:



Devi, S., Sivakumar, L., Saravanan, M., An innovative study and binary modeling of thermal power plant using artificial neural network and multiple linear regression, (2013) International Review of Mechanical Engineering (IREME), 7 (6), pp. 1171-1179.

M. Fast., and M. Assadi., S. Deb, Development and multi-utility of an ANN model for an industrial gas turbine, Applied Energy, vol. 86, pp. 9–17, 2009.

Olausson P., On the selection of methods and tools for analysis of heat and power plants, doctoral discussion, Lund University, Sweden; 2003.

Mesbahi E., Genrup M., Assadi M., Fault prediction/diagnosis and sensor validation technique for a steam power plant. J Marine Eng Technol A, vol. 2005, no. 7, pp. 33–40, 2005.

Sivakumar. L, Performance Analysis, Diagnosis And Optimisation (Pado) for Power Plants. Seminar on Power Plant Automation Concepts and Applications –by The Instrumentation Systems and automation Society- Bangalore , April 22 2006 ,

K. Salahshoor., M. Kordestani., M. Khoshro., Fault detection and diagnosis of an industrial steam turbine using fusion of SVM (support vector machine) and ANFIS (adaptive neuro-fuzzy inference system) classifiers. Energy, vol. 35, no. 12, pp. 5472–5482, 2010.

Shiwei Yu., Kejun Zhu., Xian Zhang., Energy demand projection of China using a path-coefficient analysis and PSO–GA approach, Energy Conversion and Management, vol. 53, no. 1, pp. 142–153, January 2012.

DePold H., Douglas Gass F., The application of expert systems and neural networks to gas turbine prognostics and diagnostics. J. Eng. Gas Turbines Power, vol. 121, no. 4, pp. 607-612, 1999.

C. W. Hsu., and C. J. Lin., A comparison of methods for multiclass support vector machines, IEEE transactions on Neural Networks, vol.13, no. 2, pp. 415-425, 2002.

Sivakumar.L and Ganapathiraman. G, Performance Analysis Diagnostics And Optimisation In Generation, Conference on: IT POWER- IMPROVING PERFORMANCE AND PRODUCTIVITY , New Delhi ; Sep 2006.

Embrechts M., Schweizerhof A., Bushman M., Sabatella M., Neural network modelling of turbofan parameters. In: ASME turbo expo, Paper no. 2000-GT- 0036; 2000.

Bettocchi R., Spina P., Torella G., Gas turbine health indices determination using neural networks. In: ASME turbo expo, Paper no. GT-2002-30276; 2002.

Cortes, C., and Vapnik, V., Support-vector networks. Machine Learning, vol. 20, no. 3, pp. 273-297, 1995.

Vapnik, V., The Nature of Statistical Learning Theory; Berlin: Springer, 1995. (book)

Crammer, Koby., and Singer, Yoram., "On the Algorithmic Implementation of Multiclass Kernel-based Vector Machines". J. of Machine Learning Research, vol. 2, no. 2, pp. 265–292, 2001.

K.C. Cotton., “Evaluating and Improving Steam Turbine Performance”, Cotton Fact Inc, 1988.

Sham M. Kakade, Dean P. Foster, Multi-view Regression Via Canonical Correlation Analysis, Learning Theory Lecture Notes in Computer Science, vol. 4539, pp 82-96, 2007.

H J P Timmermans, Multiattribute shopping models and ridge regression analysis, Environment and planning A, vol. 13, pp. 43-56, 1981.

Hui Zou and Trevor Hastie, Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society B, vol. 67, pp. 301–320, 2005.

Massy, W. F, Principal component regression in exploratory statistical re- search, Journal of the American Statistical Association, vol. 60, pp. 234-246, 1965.

K. Pearson, On lines and planes of closest fit to systems of points in space. Philosophical Magazine, vol. 2, pp. 559–572, 1901.

Fan, Xitao, Canonical correlation analysis and structural equation modeling: what do they have in common? Structural Equation Modeling, vol. 4, no. 1, pp. 65-79, 1997.

van den Wollenberg, A.L, Redundancy Analysis--An Alternative to Canonical Correlation Analysis, Psychometrika , vol.42, pp. 207-219, 1977.

Kiers, H. A. L. and Smilde, A. K, A comparison of various methods for multivariate regression with highly collinear variables, Statistical Methods and Applications, vol. 16, pp. 193-228, 2007.

S.Wold; A. Ruhe; H. Wold, and W. J. Dunn, The collinearity problem in linear regression. the partial least squares (PLS) approach to generalized inverses. SIAM J. Sci. Stat. Comput., vol. 5, no. 3, pp. 735–743, 1984.

William Leigh, Russel L. Purvis, James M. Ragusa, Forecasting the NYSE composite index with technical analysis, pattern recognizer, neural network, and genetic algorithm: a case study in romantic decision support, Decision Support Systems, vol. 32, no. 4, pp. 361-377, 2002.

Wold, S. Exponentially weighted moving principal component analysis and projections to latent structures. Chemomet. Intell. Lab. Syst., vol. 23, pp.149-161, 1994.

Forina, M.; Casolino, M. C.; de la Pezuela Martinez, C. Multivariate calibration: applications to pharmaceutical analysis. J. Pharm. Biomed.Anal. vol. 18, pp. 21-33, 1998,.

Ganesan, S., Subramanian, S., A novel hybrid method for thermal unit commitment problems, (2010) International Review on Modelling and Simulations (IREMOS), 3 (4), pp. 694-704.

C. M. Raguraman., A. Ragupathy., L. Sivakumar., Estimation of Overall Heat Transfer Coefficient (OHTC) of Coal-Water Slurry Based on Regression and artificial Neural Network, International Journal of Coal Preparation and Utilization, vol. 33, no. 2, pp. 59-71, 2013.

Yadaiah, N., Sivakumar, L., Deekshatulu, B.L., Parameter Identification Via Neural Networks With Fast Convergence, Mathematics and Computers in Simulation, vol. 51, no. 3-4, pp. 157-167, 2000.

Yadaiah, N., Sivakumar, L., Deekshatulu, B.L., Sree Hari Rao, V., Neural Network Architecture For Describing Nonlinear Input-Output Relations, Elektronnoe Modelirovanie, vol. 23, no. 3, pp. 48-61, 2002.

Lee, Y., Lin, Y., and Wahba, G., "Multicategory Support Vector Machines". Computing Science and Statistics, vol. 33, 2001.

Dietterich, Thomas G., and Bakiri, Ghulum., Bakiri., "Solving Multiclass Learning Problems via Error-Correcting Output Codes". Journal of Artificial Intelligence Research, vol. 2, no. 2, pp. 263–286, 1995.

L.M.R. Baccarini., V.V.R. e Silva., B.R de Menezes., W.M. Caminhas., SVM practical industrial application for mechanical faults diagnostic. Expert Systems with Applications, vol. 38, no.6, pp. 6980–6984, 2011.

C. M. Rocco S., and E. Zio., “A Support Vector Machine Integrated System for the Classification of Operation Anomalies in Nuclear Components and System,” Reliability Engineering and System Safety, vol. 92, no. 5, pp. 593-600, 2007.

Widodo., and B. S. Yang., “Support vector machine in machine condition monitoring and fault diagnosis,” Mechanical Systems and Signal Processing, vol. 21, no. 6, pp. 2560-2570, 2007.

M. Saberi a., A. Azadeh b., A. Nourmohammadzadeh b., and P. Pazhoheshfar., Comparing performance and robustness of SVM and ANN for fault diagnosis in a centrifugal pump, 19th International Congress on Modelling and Simulation, Perth, Australia, 12–16 December 2011.

Gimelli, A., Luongo, A., Amoresano, A., Experimental data and thermodynamic analysis of biomass steam power plant with two different configurations plant, (2012) International Review of Mechanical Engineering (IREME), 6 (6), pp. 1109-1116.

Abidin, A.F., Mohamed, A., Shareef, H., Intelligent classification of three phase fault and voltage collapse for correct distance relay operation using support vector machine, (2012) International Review on Modelling and Simulations (IREMOS), 5 (2), pp. 623-631.

Senoussi, H., Chebel-Morello, B., Denai, M., Zerhouni, N., Boudinar, A.H., A comparative study on feature selection to design reliable fault detection systems, (2012) International Review on Computers and Software (IRECOS), 7 (5), pp. 2070-2077.


  • There are currently no refbacks.

Please send any question about this web site to
Copyright © 2005-2021 Praise Worthy Prize