An artificial neural network-based diagnostic methodology for gas turbine path analysis—part II: case study

Abstract

The reliability of gas path components (compressor, burners and turbines) of a gas turbine is generally high, when compared with those of other systems. However, in case of forced stops, downtime is usually high, with a relatively low availability. The purpose of conditions monitoring and faults diagnostics is to detect, isolate and evaluate (i.e., to estimate quantitatively the extent) defects within a system. One effective technique could provide a significant improvement in economic performance, reduce operating costs and maintenance, increase the availability and improve the level of safety achieved. However, conventional analytical techniques such as gas path analysis and its variants are limited in their engine diagnostic, due to several reasons, including their inability to effectively operate in the presence of noise measures, to distinguish anomalies of component from a failure sensor, to preserve the linearity in the relations between parameters of gas turbines and to manage the sensors range to achieve accurate diagnosis. In this paper, the approach of a diagnostic scenario to detect faults in the gas path of a gas turbine has been presented. The model provides a large-scale integration of artificial neural networks designed to detect, isolate and evaluate failures during the operating conditions. The engine measurements are considered as input for the model, such as the speed, pressure, temperature and fuel flow rate. The output supplies any changes in the sensor or in the efficiency levels and flow rate, in the event of fault components. The diagnostic method has the ability to evaluate both anomalies of multiple components or multiple sensors, within the range of operating points. In the case of components failures, the system provides diagnostic changes in efficiency and flow rate, which can be interpreted to determine the nature of the physical problem. The technique has been applied in different operating conditions by comparing the results obtained with the solutions provided by linear and nonlinear analysis.

Keywords

Gas turbine diagnostic / Gas path analysis / Neural network

References

[1] Agrawal RK, MacIsaac BD, Saravanamuttoo HIH (1978) An analysis procedure for validation of on-site performance measurements of gas turbines. ASME J Eng Power (78-GT-152)

[2] Aker GF, Saravanamuttoo HIH. Predicting gas turbine performance behavior due to compressor fouling using computer simulation techniques. ASME J Eng Gas Turbines Power, 1989, 111: 343-350

[3] Anderson D, McNeill G (1992) Artificial neural networks technology. Data and analysis center for software (DACS), Technical Reports. Contract no. F30602-89-C-0082

[4] Angelakis C, Loukis EN, Pouliezos AD, Stavrakakis GS. A neural network based method for gas turbine blading fault diagnosis. Int J Model Simul, 2001, 21(1): 51-60

[5] Bakal B, Adali T, Fakory R, Sonmez MK, Tsaoi O (1995) Neural network simulation of real time core neutronic model. In: Proceedings of the SCS simulation multiconference, Phoenix, AZ, USA

[6] Barlett EB, Uhrig RE. Power plant status diagnostics using artificial neural network. J Nucl Technol, 1992, 97: 272-281

[7] Barschdorff D (1991) Comparison of neural and classical decision algorithms. IFAC/IMACS symposium on fault detection, supervision and safety for technical processes, 10–13 Sept, Baden-Baden, Germany

[8] Boyce MP. Gas turbine engineering handbook, 1984 Houston Gulf Publishing

[9] Brotherton T, Jahns G, Jacobs J, Wroblewski D. Prognosis of faults in gas turbine engines. IEEE Aerosp Conf Proc, 2000, 6: 163-171

[10] Brownell TA. Neural networks for sensor management and diagnostics. Aerosp Electron Conf Proc IEEE, 1992, 3: 923-929

[11] Centeno P, Egido I, Domingo C, Fernández F, Rouco L, González M. Review of gas turbine models for power system stability studies. http://aedie.org/9CHLIE-paper-send/368-Centeno.pdf

[12] Cheng B, Titterington DM. Neural networks: a review from a statistical perspective. Stat Sci, 1994, 9(1): 2-54

[13] DePold HR, Gass FD. The application of expert systems and neural networks to gas turbine prognostics and diagnostics. J Eng Gas Turbines Power, 1999, 121: 607-612

[14] Dong DW, Hopfield JJ, Unnikrishnan KP (1997) Neural networks for engine fault diagnostics. Neural Netw Signal Process VII:636–644

[15] ENEA, Department of Energy Technology (DTE), ENEA, Casaccia, Roma. Personal communication (April 2016–July 2016)

[16] Fantoni PF, Mazzola A. Multiple failure signal validation in nuclear power plants using artificial neural networks. Nucl Technol, 1996, 113(3): 368-374

[17] Féraud R, Clérot F. A methodology to explain neural network classification. Neural Netw, 2002, 15(29): 237-246

[18] Hajagos LM, Bérubé GR (2001) Utility experience with gas turbine testing and modeling. Power Eng Soc Winter Meet IEEE 3. doi:10.1109/PESW.2001.916934

[19] Tamuno-Ojuemi SOT (2003) Advanced gas-path fault diagnostics for stationary gas turbines. PhD thesis, Cranfield University, School of Engineering