Research Papers: Gas Turbines: Turbomachinery

Effects of Humidity Condensation on the Trend of Gas Turbine Performance Deterioration

[+] Author and Article Information
Houman Hanachi

Department of Mechanical and
Aerospace Engineering,
Carleton University,
1125 Colonel By Drive,
Ottawa, ON K1S 5B6, Canada
e-mail: houman.hanachi@carleton.ca

Jie Liu

Department of Mechanical and
Aerospace Engineering,
Carleton University,
1125 Colonel By Drive,
Ottawa, ON K1S 5B6, Canada
e-mail: jie.liu@carleton.ca

Avisekh Banerjee

Life Prediction Technologies, Inc.,
Unit 23, 1010 Polytek Street,
Ottawa, ON K1J 9J1, Canada
e-mail: banerjeea@lifepredictiontech.com

Ying Chen

Life Prediction Technologies, Inc.,
Unit 23, 1010 Polytek Street,
Ottawa, ON K1J 9J1, Canada
e-mail: cheny@lifepredictiontech.com

1Corresponding author.

Contributed by the Turbomachinery Committee of ASME for publication in the JOURNAL OF ENGINEERING FOR GAS TURBINES AND POWER. Manuscript received February 23, 2015; final manuscript received June 4, 2015; published online June 30, 2015. Assoc. Editor: Klaus Brun.

J. Eng. Gas Turbines Power 137(12), 122604 (Jun 30, 2015) (11 pages) Paper No: GTP-15-1081; doi: 10.1115/1.4030815 History: Received February 23, 2015

Performance deterioration in gas turbine engines (GTEs) depends on various factors in the ambient and the operating conditions. For example, humidity condensation at the inlet duct of a GTE creates water mist, which affects the fouling phenomena in the compressor and varies the performance. In this paper, the effective factors on the short-term performance deterioration of a GTE are identified and studied. GTE performance level is quantified with two physics-based performance indicators, calculated from the recorded operating data from the control system of a GTE over a full time between overhaul (TBO) period. A regularized particle filtering (RPF) framework is developed for filtering the indicator signals, and an adaptive neuro-fuzzy inference system (ANFIS) is then trained with the filtered signals and the effective ambient and the operating conditions, i.e., the power, the air mass flow, and the humidity condensation rate. The trained ANFIS model is then run to simulate the GTE performance deterioration in different conditions for system identification. The extracted behavior of the system clearly shows the dependency of the trend of performance deterioration on the operating conditions, especially the humidity condensation rate. The developed technique and the results can be utilized for GTE performance prediction, as well as for suggesting the optimum humidity supply at the GTE intake to control the performance deterioration rate.

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


Schneider, E. , Bussjaeger, S. D. , Franco, S. , and Therkorn, D. , 2010, “Analysis of Compressor On-Line Washing to Optimize Gas Turbine Power Plant Performance,” ASME J. Eng. Gas Turbines Power, 132(6), p. 062001. [CrossRef]
Kurz, R. , and Brun, K. , 2001, “Degradation in Gas Turbine Systems,” ASME J. Eng. Gas Turbines Power, 123(1), pp. 70–77. [CrossRef]
Boyce, M. P. , and Gonzalez, F. , 2007, “A Study of On-Line and Off-Line Turbine Washing to Optimize the Operation of a Gas Turbine,” ASME J. Eng. Gas Turbines Power, 129(1), pp. 114–122. [CrossRef]
Meher-Homji, C. B. , and Bromley, A. , 2004, “Gas Turbine Axial Compressor Fouling and Washing,” 33rd Turbomachinery Symposium, Houston, TX, Sept. 20–23, pp. 163–192.
Stalder, J. , 2001, “Gas Turbine Compressor Washing State of the Art: Field Experiences,” ASME J. Eng. Gas Turbines Power, 123(2), pp. 363–370. [CrossRef]
Walsh, P. P. , and Fletcher, P. , 2004, Gas Turbine Performance, Blackwell Science, Malden, MA, Chap. 6.
Li, Y. , Ghafir, M. A. , Wang, L. , Singh, R. , Huang, K. , and Feng, X. , 2011, “Nonlinear Multiple Points Gas Turbine Off-Design Performance Adaptation Using a Genetic Algorithm,” ASME J. Eng. Gas Turbines Power, 133(7), p. 071701. [CrossRef]
Hanachi, H. , Liu, J. , Banerjee, A. , Chen, Y. , and Koul, A. , 2015, “A Physics-Based Modeling Approach for Performance Monitoring in Gas Turbine Engine,” IEEE Trans. Reliab., 64(1), pp. 197–205. [CrossRef]
Hanachi, H. , Liu, J. , Banerjee, A. , and Chen, Y. , 2015, “Effects of the Intake Air Humidity on the Gas Turbine Performance Monitoring,” ASME Paper No. GT2015-43026.
Hanachi, H. , Liu, J. , Banerjee, A. , and Chen, Y. , 2015, “A Framework With Nonlinear System Model and Nonparametric Noise for Gas Turbine Degradation State Estimation,” Meas. Sci. Technol., 26(6), p. 065604. [CrossRef]
Buck, A. L. , 1981, “New Equations for Computing Vapor Pressure and Enhancement Factor,” J. Appl. Meteorol., 20(12), pp. 1527–1532. [CrossRef]
Cengel, Y. A. , Boles, M. A. , and Kanoğlu, M. , 2011, Thermodynamics: An Engineering Approach, McGraw-Hill, New York.
Simon, D. , 2006, Optimal State Estimation: Kalman, H Infinity, and Nonlinear Approaches, Wiley, Hoboken, NJ, Chap. 5.
Arulampalam, M. S. , Maskell, S. , Gordon, N. , and Clapp, T. , 2002, “A Tutorial on Particle Filters for Online Nonlinear/Non-Gaussian Bayesian Tracking,” IEEE Trans. Signal Process., 50(2), pp. 174–188. [CrossRef]
Liu, J. , Wang, W. , and Ma, F. , 2011, “A Regularized Auxiliary Particle Filtering Approach for System State Estimation and Battery Life Prediction,” Smart Mater. Struct., 20(7), p. 075021. [CrossRef]
Kacprzynski, G. J. , Gumina, M. , Roemer, M. J. , Caguiat, D. E. , and Galie, T. R. , 2001, “A Prognostic Modeling Approach for Predicting Recurring Maintenance for Shipboard Propulsion Systems,” ASME Paper No. 2001-GT-0218.
Loboda, I. , and Feldshteyn, Y. , 2010, “Polynomials and Neural Networks for Gas Turbine Monitoring: A Comparative Study,” ASME Paper No. GT2010-23749.
Salahshoor, K. , Kordestani, M. , and Khoshro, M. S. , 2010, “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, 35(12), pp. 5472–5482. [CrossRef]
Salahshoor, K. , Khoshro, M. S. , and Kordestani, M. , 2011, “Fault Detection and Diagnosis of an Industrial Steam Turbine Using a Distributed Configuration of Adaptive Neuro-Fuzzy Inference Systems,” Simul. Modell. Pract. Theory, 19(5), pp. 1280–1293. [CrossRef]
Cavarzere, A. , and Venturini, M. , 2012, “Application of Forecasting Methodologies to Predict Gas Turbine Behavior Over Time,” ASME J. Eng. Gas Turbines Power, 134(1), p. 012401. [CrossRef]
Asgari, H. , Chen, X. , Menhaj, M. B. , and Sainudiin, R. , 2013, “Artificial Neural Network-Based System Identification for a Single-Shaft Gas Turbine,” ASME J. Eng. Gas Turbines Power, 135(9), p. 092601. [CrossRef]
Cohen, M. E. , and Hudson, D. L. , 1995, Comparative Approaches to Medical Reasoning, World Scientific, Singapore, Chap. 2.
Jang, J. , 1993, “ANFIS: Adaptive-Network-Based Fuzzy Inference System,” IEEE Trans. Syst., Man, Cybern., 23(3), pp. 665–685. [CrossRef]
Takagi, T. , and Sugeno, M. , 1985, “Fuzzy Identification of Systems and Its Applications to Modeling and Control,” IEEE Trans. Syst., Man, Cybern., SMC-15(1), pp. 116–132. [CrossRef]


Grahic Jump Location
Fig. 1

Performance deterioration during the operating life: (a) EH performance indicator and (b) ER performance indicator

Grahic Jump Location
Fig. 2

Humidity in inlet air: (a) total humidity, (b) condensed humidity, and (c) comparison in selected time window

Grahic Jump Location
Fig. 3

RPF state estimation on the performance indicator signals: (a) EH performance indicator and (b) ER performance indicator

Grahic Jump Location
Fig. 4

Variation rates of the performance indicators do not constitute functions over PW–Wcon space: (a) variation rate of EH and (b) variation rate of ER

Grahic Jump Location
Fig. 5

ANFIS structure for system identification. Dashed line shows the use of output as input of the next step for profile simulation.

Grahic Jump Location
Fig. 6

Training data points and the result of ANFIS model prediction: (a) EH data and prediction, (b) ER data and prediction, and (c) scarcity of data points in some regions of the domain

Grahic Jump Location
Fig. 8

ER simulated profiles at PW = 3500 kW

Grahic Jump Location
Fig. 9

EH simulated profiles at Wcon = 16.75 kg/s

Grahic Jump Location
Fig. 10

Lack of training data points for ER simulation with WCiWcon data

Grahic Jump Location
Fig. 7

ANFIS model simulated profiles for EH: (a) EH profiles at constant power and humidity condensation rates and (b) EH profiles at PW = 2400 kW



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