Abstract
Hot components operate in a high-temperature and high-pressure environment. The occurrence of a fault in hot components leads to high economic losses. In general, exhaust gas temperature (EGT) is used to monitor the performance of hot components. However, during the early stages of a failure, the fault information is weak, and is simultaneously affected by various types of interference, such as the complex working conditions, ambient conditions, gradual performance degradation of the compressors and turbines, and noise. Additionally, inadequate effective information of the gas turbine also restricts the establishment of the detection model. To solve the above problems, this paper proposes an anomaly detection method based on frequent pattern extraction. A frequent pattern model (FPM) is applied to indicate the inherent regularity of change in EGT occurring from different types of interference. In this study, based on a genetic algorithm and support vector machine regression, the relationship model between the EGT and interference was tentatively built. The modeling accuracy was then further improved through the selection of the kernel function and training data. Experiments indicate that the optimal kernel function is linear and that the optimal training data should be balanced in addition to covering the appropriate range of operating conditions and ambient temperature. Furthermore, the thresholds based on the Pauta criterion that is automatically obtained during the modeling process, are used to determine whether hot components are operating abnormally. Moreover, the FPM is compared with the similarity theory, which demonstrates that the FPM can better suppress the effect of the component performance degradation and fuel heat value fluctuation. Finally, the effectiveness of the proposed method is validated on seven months of actual data obtained from a Titan130 gas turbine on an offshore oil platform. The results indicate that the proposed method can sensitively detect malfunctions in hot components during the early stages of a fault, and is robust to various types of interference.
Similar content being viewed by others
References
Volponi A J. Gas turbine engine health management: Past, present, and future trends. J Eng Gas Turbines Power, 2014, 136: 051201
Hu J, Zhang L, Ma L, et al. An integrated safety prognosis model for complex system based on dynamic Bayesian network and ant colony algorithm. Expert Syst Appl, 2011, 38: 1431–1446
Fast M, Palmé T. Application of artificial neural networks to the condition monitoring and diagnosis of a combined heat and power plant. Energy, 2010, 35: 1114–1120
Tayarani-Bathaie S S, Sadough Vanini Z N, Khorasani K. Dynamic neural network-based fault diagnosis of gas turbine engines. Neurocomputing, 2014, 125: 153–165
Vanini Z N S, Khorasani K, Meskin N. Fault detection and isolation of a dual spool gas turbine engine using dynamic neural networks and multiple model approach. Inf Sci, 2014, 259: 234–251
Meskin N, Naderi E, Khorasani K. A multiple model-based approach for fault diagnosis of jet engines. IEEE Trans Contr Syst Technol, 2013, 21: 254–262
Berrios R, Núñez F, Cipriano A. Fault tolerant measurement system based on Takagi-Sugeno fuzzy models for a gas turbine in a combined cycle power plant. Fuzzy Sets Syst, 2011, 174: 114–130
Kobayashi T, Simon D. Application of a bank of kalman filters for aircraft engine fault diagnostics. In: ASME Turbo Expo 2003, Collocated with the 2003 International Joint Power Generation Conference. Atlanta, Georgia, 2003. 461–470
Kobayashi T, Simon D L. Hybrid Kalman filter approach for aircraft engine in-flight diagnostics: Sensor fault detection case. J Eng Gas Turbines Power, 2007, 129: 746
Simon D, Simon D. Aircraft turbofan engine health estimation using constrained Kalman filtering. J Eng Gas Turbines Power, 2005, 127: 1930–1934
Sarkar S, Jin X, Ray A. Data-driven fault detection in aircraft engines with noisy sensor measurements. J Eng Gas Turbines Power, 2011, 133: 081602
Yu B, Liu D, Zhang T. Fault diagnosis for micro-gas turbine engine sensors via wavelet entropy. Sensors, 2011, 11: 9928–9941
Ogaji S O T, Sampath S, Singh R, et al. Parameter selection for diagnosing a gas-turbine’s performance-deterioration. Appl Energy, 2002, 73: 25–46
Zhang C L, Li B, Chen B Q, et al. Weak fault signature extraction of rotating machinery using flexible analytic wavelet transform. Mech Syst Signal Process, 2015, 64-65: 162–187
Song Y, Zhang K, Shi Y. Research on aeroengine performance parameters forecast based on multiple linear regression forecasting method (in Chinese). J Aerosp Power, 2009, 24: 427–431
Yilmaz I. Evaluation of the relationship between exhaust gas temperature and operational parameters in CFM56-7B engines. Proc Inst Mech Eng Part G-J Aerosp Eng, 2009, 223: 433–440
Korczewski Z. Exhaust gas temperature measurements in diagnostic examination of naval gas turbine engines. Polish Marit Res, 2011, 18: 49–53
Lee M C. Effects of H2/CO/CH4 syngas composition variation on the NOx and CO emission characteristics in a partially-premixed gas turbine combustor. Sci China Tech Sci, 2016, 59: 1804–1813
Liu Z, Hyun B S, Jin J Y, et al. OWC air chamber performance prediction under impulse turbine damping effects. Sci China Tech Sci, 2016, 59: 657–666
Hamilton, Patrick P, Ha D. Exhaust gas temperature capabilities now in system 1 software. Product Update, 2005: 88–89
General Electric Company. Heavy Duty Gas Turbine Monitoring & Protection. Nevada: General Electric Company, 2015
Johnson D, Gilbert K, Buckley L. The SPEEDTRONIC Mark IV Control™, a distributed fault tolerant gas turbine control system. In: ASME 1983 International Gas Turbine Conference and Exhibit. Phoenix, Arizona, 1983
Mao D, Zhu Y. Analysis on control system for mitsubishi M701F gas turbine (in Chinese). J Hunan Univ Technol, 2008, 22: 76–79
Hu Y, Chen X. SIEMENS V94.3A Gas Turbine Control System. Vol 2. Shanghai: Shanghai Electric Power, 2006. 152–155
Medina P, Saez D, Roman R. On line fault detection and isolation in gas turbine combustion chambers. In: ASME Turbo Expo 2008: Power for Land, Sea, and Air. Berlin, 2008. 315–324
Benvenuti E. Innovative gas turbine performance diagnostics and hot parts life assessment techniques. In: Proceedings of the 30th Turbomachinery Symposium. College Station, Texas, 2001. 23–31
Tarassenko L, Nairac A, Townsend N, et al. Novelty detection for the identification of abnormalities. Int J Syst Sci, 2000, 31: 1427–1439
Gülen S, Griffin P, Paolucci S. Real-time on-line perfor-mance diagnostics of heavy-duty industrial gas turbines. J Eng Gas Turbines Power, 2000, 124: 58–66
Liu J, Liu J, Wan J, et al. Early fault detection of hot components in gas turbines. J Eng Gas Turbines Power, 2017, 139: 021201
Vapnik V. The nature of statistical learning theory. IEEE Trans Neural Netw, 1997, 8: 1564
Suykens J A K, Vandewalle J. Least squares support vector machine classifiers. Neural Process Lett, 1999, 9: 293–300
Goldberg D. Genetic Algorithms in Search, Optimization and Machine Learning. Boston, MA: Addison-Wesley Longman Publishing Co., Inc., 1989
Andrew A M. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. New York, NY: Cambridge University Press, 2000
Xiao D, Shang B, Wu B, et al. Resource prediction based on program granularity combined with data purification. In: International Conference on Fuzzy Systems and Knowledge Discovery. Zhangjiajie, China: IEEE, 2015
Ding Y, Huang X H, Zhang T H. The research of gas turbine performance modeling based on theory of similarity (in Chinese). J Aerosp Power, 2004, 19: 689–694
Schlechtingen M, Ferreira Santos I. Comparative analysis of neural network and regression based condition monitoring approaches for wind turbine fault detection. Mech Syst Signal Process, 2011, 25: 1849–1875
Zong W, Huang G B, Chen Y. Weighted extreme learning machine for imbalance learning. Neurocomputing, 2013, 101: 229–242
Liu J, Hu Q, Yu D. A weighted rough set based method developed for class imbalance learning. Inf Sci, 2008, 178: 1235–1256
Liu J, Hu Q, Yu D. A comparative study on rough set based class imbalance learning. Knowl-Based Syst, 2008, 21: 753–763
Liu X Y, Wu J, Zhou Z H. Exploratory undersampling for class-imbalance learning. IEEE Trans Syst Man Cybern B, 2009, 39: 539–550
Author information
Authors and Affiliations
Corresponding authors
Rights and permissions
About this article
Cite this article
Liu, J., Zhu, L., Ma, Y. et al. Anomaly detection of hot components in gas turbine based on frequent pattern extraction. Sci. China Technol. Sci. 61, 567–586 (2018). https://doi.org/10.1007/s11431-017-9165-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11431-017-9165-7