Research Papers: Gas Turbines: Turbomachinery

A New Gas Path Fault Diagnostic Method of Gas Turbine Based on Support Vector Machine

[+] Author and Article Information
Dengji Zhou

Gas Turbine Research Institute,
Shanghai Jiao Tong University,
800 Dongchuan Road,
Minhang District,
Shanghai 200240, China
e-mail: zhoudj@sjtu.edu.cn

Huisheng Zhang

Gas Turbine Research Institute,
Shanghai Jiao Tong University,
800 Dongchuan Road,
Minhang District,
Shanghai 200240, China
e-mail: zhslm@sjtu.edu.cn

Shilie Weng

Gas Turbine Research Institute,
Shanghai Jiao Tong University,
800 Dongchuan Road,
Minhang District,
Shanghai 200240, China
e-mail: slweng@sjtu.edu.cn

Contributed by the Turbomachinery Committee of ASME for publication in the JOURNAL OF ENGINEERING FOR GAS TURBINES AND POWER. Manuscript received December 30, 2014; final manuscript received March 4, 2015; published online May 6, 2015. Editor: David Wisler.

J. Eng. Gas Turbines Power 137(10), 102605 (Oct 01, 2015) (6 pages) Paper No: GTP-14-1687; doi: 10.1115/1.4030277 History: Received December 30, 2014; Revised March 04, 2015; Online May 06, 2015

As a crucial section of gas turbine maintenance decision-making process, to date, gas path fault diagnostic has gained a lot of attention. However, model-based diagnostic methods, like nonlinear gas path analysis (GPA) and genetic algorithms, need an accurate gas turbine model, and diagnostic methods without gas turbine model, like expert system, need a knowledge database. Both are difficult to gain. Thus, data-driven approach for gas path diagnosis, like artificial neural network, is increasingly attractive. Support vector machine (SVM), a novel computational learning method, seems to be a good choice for data-driven gas path fault diagnosis of gas turbine. In this paper, SVM is employed to diagnose a deteriorated gas turbine. The effect of sample number, kernel function, and monitoring parameters on diagnostic accuracy are studied, respectively. Additionally, the diagnostic result of SVM is compared to the result of artificial neural networks. The comparing result confirms that SVM has an obvious advantage over artificial neural networks method based on a small sample of data and can be employed to gas path fault diagnosis of gas turbine. In addition, SVM with radial basis kernel function is the best choice for gas turbine gas path fault diagnosis based on small sample.

Copyright © 2015 by ASME
Your Session has timed out. Please sign back in to continue.


Liu, D. Y., and Zhang, H. P., 2008, “Development and Electric Power Generation Technology of the Combustion Turbine,” Appl. Energy Technol., 121(1), pp. 5–8. [CrossRef]
Xia, D., 2008, “Gas Turbine Diagnostic Theory and Experiment Research Based on Thermal Parameters,” Ph.D. thesis, Shanghai Jiao Tong University, Shanghai, China.
Niu, G., Yang, B. S., and Pecht, M., 2010, “Development of an Optimized Condition-Based Maintenance System by Data Fusion and Reliability-Centered Maintenance,” Reliab. Eng. Syst. Saf., 95(7), pp. 786–796. [CrossRef]
Kraft, J., Sethi, V., and Singh, R., 2014, “Optimization of Aero Gas Turbine Maintenance Using Advanced Simulation and Diagnostic Methods,” ASME J. Gas Turbines Power, 136(11), p. 111602. [CrossRef]
Volponi, A. J., 2014, “Gas Turbine Engine Health Management: Past, Present, and Future Trends,” ASME J. Gas Turbines Power, 136(5), p. 051201. [CrossRef]
Razak, A. M. Y., and Carlyle, J. S., 2000, “An Advanced Model Based Health Monitoring System to Reduce Gas Turbine Ownership Cost,” ASME Paper No. 2000-GT-0627. [CrossRef]
Urban, L. A., 1975, “Parameter Selection for Multiple Fault Diagnostics of Gas Turbine Engines,” ASME J. Eng. Gas Turbines Power, 97(2), pp. 225–230. [CrossRef]
Urban, L. A., 1969, Gas Turbine Engine Parameter Interrelationships, 2nd ed., Hamilton Standard Division of United Aircraft Corp. (HSDUTC), Windsor Locks, CT.
Vanini, Z. N. S., Meskin, N., and Khorasani, K., 2014, “Multiple-Model Sensor and Components Fault Diagnosis in Gas Turbine Engines Using Autoassociative Neural Networks,” ASME J. Gas Turbines Power, 136(9), p. 091603. [CrossRef]
Li, Y. G., 2002, “Performance Analysis Based Gas Turbine Diagnostic: A Review,” Proc. Inst. Mech. Eng., 216(5), pp. 363–377. [CrossRef]
Maimon, O., and Rokach, L., 2010, Data Mining and Knowledge Discovery Handbook, 2nd ed., Springer, New York, pp. 231–248.
Saimurugan, M., Ramachandran, K. I., Sugumaran, V., and Sakthivel, N. R., 2011, “Multi Component Fault Diagnosis of Rotational Mechanical System Based on Decision Tree and Support Vector Machine,” Expert Syst. Appl., 38(4), pp. 3819–3826. [CrossRef]
Chen, J., and Patton, R. J., 1998, Robust Model-Based Fault Diagnosis for Dynamic Systems, Kluwer Academic Publishers, Boston.
Cortes, C., and Vapnik, V., 1995, “Support-Vector Network,” Mach. Learn., 20(3), pp. 273–297. [CrossRef]
Vapnik, V., 1995, The Nature of Statistical Learning Theory, Springer, New York.
Xie, F. F., 2006, “Support Vector Machine for Fault Diagnosis,” Ph.D. thesis, Hunan University, Changsha, China.
Deng, N. Y., and Tian, Y. J., 2004, A New Method for Data Mining—Support Vector Machine, Science Press, Beijing.
Jack, L. B., and Nandi, A. K., 2001, “Support Vector Machines for Detection and Characterization of Rolling Element Bearing Faults,” Proc. Inst. Mech. Eng., Part C, 215(9), pp. 1065–1071. [CrossRef]
Samanta, B., Al-Balushi, K. R., and Al-Araimi, S. A., 2003, “Artificial Neural Networks and Support Vector Machines With Genetic Algorithm for Bearing Fault Detection,” Eng. Appl. Artif. Intell., 16(7–8), pp. 657–665. [CrossRef]
Lv, G. Y., Chen, H. Z., and Zhang, H. B., 2005, “Fault Diagnosis of Power Transformer Based on Multi-Layer SVM Classifier,” Electr. Power Syst. Res., 74(1), pp. 9–15. [CrossRef]
Cui, H. X., Zhang, L. B., and Kang, R. Y., 2009, “Research on Fault Diagnosis for Reciprocating Compressor Valve Using Information Entropy and SVM Method,” J. Loss Prev. Process Ind., 22(6), pp. 864–967. [CrossRef]
Xu, Q., Zhang, Y., and Cui, Y. X., 2006, “Technical Characteristics of the Siemens Gas Turbine V94.3A,” Shanghai Electric Power, 23(1), pp. 3–6.


Grahic Jump Location
Fig. 1

Gas turbine gas path fault diagnostic theory

Grahic Jump Location
Fig. 2

Application process of SVM for gas path diagnosis

Grahic Jump Location
Fig. 3

The traditional SVM model for gas path diagnosis

Grahic Jump Location
Fig. 4

The novel SVM model for gas path diagnosis

Grahic Jump Location
Fig. 7

Effect of monitoring parameters number on SVM diagnostic accuracy (sample size = 144)

Grahic Jump Location
Fig. 6

Effect of monitoring parameters number on SVM diagnostic accuracy (sample size = 400)

Grahic Jump Location
Fig. 5

Effect of sample size and kernel function on SVM diagnostic accuracy

Grahic Jump Location
Fig. 8

Diagnostic accuracy comparison of SVM and neural networks



Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In