In this article, a feed-forward neural network is explored to reconstruct the performance map of an axial compressor through the utilization of a limited number of experimental data. The Levenberg—Marquardt algorithm with Bayesian regularization method is used to adjust the weights and biases of the network. The proposed technique is utilized to estimate the mass flowrate, the pressure ratio, the shaft speed, and the efficiency in regions where no experimental data are available. The surge line is predicted and the line of maximum efficiencies is determined. The results are compared with experimental data.
WalshP. P.FletcherP., Gas turbine performance (New York: ASME Press2004) co-published with Blackwell Science, UK.
2.
KurzkeJ., ‘How to get component maps for an aircraft gas-turbine's performance calculations’ (1996) paper no. 96-GT-164.
3.
IsmailI. H.BhinderF. S., ‘Simulation of aircraft gas-turbine engine’ASME, J. Eng. Gas Turbines Power113 (1991): 95–99.
4.
El-GammalM. A., ‘An algorithm and criteria for compressor characteristics real time modeling and approximation’ASME, J. Eng. Gas Turbines Power113 (1991): 112–117.
5.
SierosG.StamatisA.MathioudakisK., ‘Jet engine component maps for performance modeling and diagnosis’AIAA, J. Propuls. Power135 (1997): 665–674.
6.
MoraalP.KolmanovskyI., ‘Turbocharger modeling for automotive control application’SAE Trans.108 (1999): 1324–1338.
7.
OrkiszM.StawarzS., ‘Modeling of turbine engine axial-flow compressor and turbine characteristics’AIAA, J. Propuls. Power162 (2000): 336–339.
8.
KongC. D.KhoS.KiJ. Y., ‘Component map generation of a gas turbine using genetic algorithms’ASME, J. Eng. Gas Turbines Power1281 (2006): 92–96.
9.
KongC. D.KiJ. Y., ‘Components map generation of gas turbine engine using genetic algorithms and engine performance deck data’ASME, J. Eng. Gas Turbines Power1292 (2007): 312–317.
10.
FallerW.ScottJ. S.LuttgesM. W., ‘Neural network prediction and control of three-dimensional unsteady separated flowfields’AIAA, J. Aircr.321 (1995): 1213–1220.
11.
RaiM. M.MadavanN. K., ‘Application of artificial neural networks to the design of turbomachinery airfoils’AIAA, J. Propuls. Power171 (2001): 176–183.
12.
LazzarettoA.ToffoloA., ‘Analytical and neural network models for gas turbine design and off-design simulation’Int. J. Appl. Thermodyn.44 (2001): 173–182.
13.
JolyR. B.OgajiO. T.SinghR.ProbertS. D., ‘Gas-turbine diagnostics using an artificial neural network for a high bypass ratio military turbofan engine’J. Appl. Energy784 (2004): 397–418.
14.
VermaR.RoyN.GanguliR., ‘Gas turbine diagnostics using a soft computing approach’Appl. Math. Comput.1721 (2006): 1342–1363.
15.
VolponiA.J.DepoldH.GanguliR.DaguangC., ‘The use of kalman filter and neural network methodologies in gas turbine performance diagnostics: A comparative study’ASME, J. Eng. Gas Turbines Power1254 (2003): 917–924.
16.
GanguliR., ‘Application of fuzzy logic for fault isolation of jet engines’ASME, J. Eng. Gas Turbines Power1253 (2003): 617–623.
17.
GanguliR., ‘A fuzzy logic intelligent system for gas turbine module and system fault isolation’AIAA, J. Propuls. Power182 (2002): 440–447.
18.
BaoC.OuyangM.YiB., ‘Modeling and optimization of the air system in polymer exchange membrane fuel cell system’J. Power Sources1562 (2006): 232–243.
19.
YuY.ChenL.SunF.WuC., ‘Neural network based analysis and prediction of a compressor's characteristic performance map’J. Appl. Energy841 (2007): 48–55.
VenturiniM., ‘Development and experimental validation of a compressor dynamic model’ASME, J. Turbomach.1273 (2005): 599–608.
24.
VenturiniM., ‘Simulation of compressor transient behavior through recurrent neural network models’ASME, J. Turbomach.1284 (2006): 1–11.
25.
VenturiniM., ‘Optimization of a real-time simulator based on recurrent neural networks for compressor transient behavior prediction’ASME, J. Turbomach.1293 (2007): 1–11.
26.
HansenK. E.JorgensenP.LarsenP. S., ‘Experimental and theoretical study of surge in a small centrifugal compressor’ASME, J. Fluids Eng.103 (1981): 391–395.
27.
MooreF. K.GreitzerE. M., ‘A theory of post-stall transients in axial compression systems: Part I—development of equations’ASME, J. Eng. Gas Turbines Power108 (1986): 68–76.
28.
PinsleyJ. E.GuenetteG. R.EpsteinA. H.GreitzerE. M., ‘Active stabilization of centrifugal compressor surge’ASME, J. Turbomach.113 (1991): 723–732.
29.
BadmusO. O.ChowdhuryS.NettC. N., ‘Nonlinear control of surge in axial compression systems’Automatica32 (1996): 59–70.
30.
MeulemanC. H. J., Measurement and unsteady flow modeling of centrifugal compressor surge (2002) PhD Dissertation Technische Universiteit Eindhoven, Eindhoven, Netherlands, 2002.
31.
GravdahlJ. T.EgelandO., ‘Centrifugal compressor surge and speed control. IEEE Trans’. Control Syst. Technol.7 (1999): 567–579.
32.
GravdahlJ. T.WillemsF.JagerB. D. E.EgelandO., ‘Modeling of surge in free-spool centrifugal compressors: Experimental validation’AIAA, J. Propuls. Power20 (2004): 849–857.
33.
Van HelvoirtJ., Centrifugal compressor surge modeling and identification for control (2007) PhD Dissertation.
HaganM. T.MenhajM., ‘Training multilayer networks with the marquardt algorithm’IEEE Trans., Neural Netw.56 (1994): 989–993.
39.
MacKayD. J. C., ‘Bayesian interpolation’Neural Comput.43 (1992): 415–447.
40.
ForeseeF. D.HaganM. T., ‘Gauss-newton approximation to bayesian learning’ In Proceedings of the International Joint Conference on Neural networks, Houston, TX, USA, 9–12 June 1997, pp. 1930–1935.
41.
GravdahlJ. T.EgelandO., Compressor surge and rotating stall modeling and control (London: Springer1999).
