Early fault detection of gas turbine hot components under different ambient and operating conditions

Abstract

Failure of hot components in gas turbines often causes catastrophic results. Early fault detection can prevent serious incidents and improve the availability. A novel early fault detection method of hot components is proposed in this article. Exhaust gas temperature is usually used as the indicator to detect the fault in the hot components, which is measured by several exhaust thermocouples with uniform distribution at the turbine exhaust section. The healthy hot components cause uniform exhaust gas temperature (EGT) profile, whereas the hot component faults could cause the uneven EGT profile. However, the temperature differences between different thermocouple readings are also affected by different ambient and operating conditions, and it sometimes has a greater influence on EGT than the faults. In this article, an accurate EGT model is presented to eliminate the influence of different ambient and operating conditions on EGT. Especially, the EGT profile swirl under different ambient and operating conditions is also included by considering the information of the thermocouples’ spatial correlations and the EGT profile swirl angle. Based on the developed EGT model, the detection performance of early fault detection of hot components in gas turbine is improved. The accuracy and effectiveness of the developed early fault detection method are evaluated by the real-world gas turbine data.

Keywords

Hot components gas turbine fault detection prognostics and health management

Get full access to this article

View all access options for this article.

References

Heavy duty gas turbine monitoring & protection. Nevada, US: General Electric Company, 2015.

Liu

Jiang

, et al. Sparse Bayesian learning for gas path diagnostics. ASME J Eng Gas Turbines Power 2013; 135(7): 071601.

Kamboukos

Mathioudakis

. Comparison of linear and nonlinear gas turbine performance diagnostics. J Eng Gas Turbines Power 2005; 127(1): 49–56.

Liu

Jiang

, et al. Adaptive gas path diagnostics using strong tracking filter. Proc Inst Mech Eng G: J Aerospace Eng 2014; 228(4): 577–585.

Wang

Huang

, et al. Fusing unscented Kalman filter for performance monitoring and fault accommodation in gas turbine. Proc Inst Mech Eng Part G: J Aerospace Eng 2018; 232: 556–570.

Ghafir

MFA

Wang

, et al. Nonlinear multiple points gas turbine off-design performance adaptation using a genetic algorithm. ASME J Eng Gas Turbines Power 2011; 133(7): 71701.

Loboda

Feldshteyn

Ponomaryov

. Neural networks for gas turbine fault identification: Multilayer perceptron or radial basis network? Int J Turbo Jet-engines 2012; 29(1): 37–48.

Bettocchi

Pinelli

Spina

, et al. Artificial intelligence for the diagnostics of gas turbines-part I: Neural network approach. J Eng Gas Turbines Power 2007; 129(3): 711–719.

Miller

Iasillo

Lemmon

. Method of monitoring for combustion anomalies in a gas turbomachine and a gas turbomachine including a combustion anomaly detection system. U.S Patent No 20,150,267,591, 24 September 2015.

10.

JIN

. Study on deflection laws of 9FA gas-turbine exhaust temperature field. Electric Power Construction 2009; 3: 026.

11.

Gulen

Griffin

Paolucci

. Real-time on-line performance diagnostics of heavy-duty industrial gas turbines. ASME J Eng Gas Turbines Power 2002; 124(4): 910–921.

12.

Yılmaz

. Evaluation of the relationship between exhaust gas temperature and operational parameters in CFM56-7B engines. Proc Inst Mech Eng Part G: J Aerospace Eng 2009; 223(4): 433–440.

13.

Song

Zhang

Shi

. Research on aeroengine performance parameters forecast based on multiple linear regression forecasting method. J Aerosp Power 2009; 24(2): 427–431.

14.

Tarassenko

Nairac

Townsend

, et al. Novelty detection for the identification of abnormalities. Int J Syst Sci 2000; 31(11): 1427–1439.

15.

Yan

. On accurate and reliable anomaly detection for gas turbine combustors: a deep learning approach. Proc Annu Conf Prognostics Health Manag Soc 2015; 6: 025.

16.

Yan

One-class extreme learning machines for gas turbine combustor anomaly detection. International Joint Conference on Neural Networks (IJCNN). Vancouver, BC, Canada: IEEE, July 2016, pp. 242909–292914.

17.

Basseville

Benveniste

Mathis

, et al. Monitoring the combustion set of a gas turbine. IFAC symposium on fault detection. Supervision and Safety for Technical Processes – SAFEPROCESS 1994; 1: 397–402.

18.

Zhang

Basseville

Benveniste

. Early warning of slight changes in systems. Automatica 1994; 30(1): 95–113.

19.

Medina

Saez

Roman

. On line fault detection and isolation in gas turbine combustors. In: ASME Paper, Berlin, Germany, 9–13 June 2008. pp. 315–324.

20.

Liu

Wan

, et al. Early fault detection of hot components in gas turbines. ASME J Eng Gas Turbines Power 2017; 139(2): 021201.