A new wavelet network structure combining polynomial models with continuous wavelet decomposition is introduced for the identification of a synchronous generator model. The proposed structure uses features of polynomial models and wavelet networks to model non-linearities in the system. In this study, a serial-parallel identification model is applied to system modelling. In this structure, real system outputs are exercised for prediction of the future system outputs, so that stability and approximation of the network are guaranteed. This method is applied to identify the model of a synchronous machine from experimental data collected on a physical machine. The results show that the identified model has very good accuracy and may be valid for a broad range of operating conditions.
IEEE Std 115-1995, IEEE guide: test procedures for synchronous machines, Part I - acceptance and performance testing, Part II - test procedures and parameter determination for dynamic analysis.
2.
ParkR. H.‘Two reaction theory of synchronous machines.’Trans. AIEE Part I48 (1929): 716–729
3.
KarrariM.MalikO. P.‘Nonlinear state space identification of a synchronous generator.’ IEEE Proceedings of Power Engineering Society General Meeting, Toronto, Canada, 2003, vol. 4, pp. 2399–2404.
4.
KarrariM.MalikO. P.‘Identification of physical parameters of a synchronous generator from on-line measurements.’Trans. IEEE Energy Conversion19 (2) (2004): 407–415
5.
KyriakidesE.HeydtG. T.‘Estimation of synchronous generator parameters using an observer for damper currents and a graphical user interface.’Electric Power Syst. Res.69 (1) (2004): 7–16
6.
KyriakidesE.HeydtG. T.VittalV.‘Online parameter estimation of round rotor synchronous generators including magnetic saturation.’Trans. IEEE Energy Conversion20 (3) (2005): 529–537
7.
MelgozaJ. J. R.JesusR.HeydtG. T.KeyhaniA.‘An algebraic approach for identifying operating point dependent parameters of synchronous machine using orthogonal series expansions.’Trans. IEEE Energy Conversion16 (1) (2001): 92–98
8.
MelgozaJ. J. R.HeydtG. T.KeyhaniA.AgrawalB. L.SelinD.‘Synchronous machine parameter estimation using Hartley series.’Trans. IEEE Energy Conversion16 (1) (2001): 49–54
9.
NellesO.Nonlinear system identification: from classical approaches to neural networks and fuzzy models, (Springer, Berlin—New York).2001)
10.
KarrariM.MalikO. P.‘Identification of synchronous generators using discrete wavelet transform.’ Intelligent System Applications to Power Systems (ISAP), Lemnos, Greece, 2003.
11.
KarrariM.MenhajM. B.‘Application of different neural networks for identification of power systems.’ In Proceedings of International Conference onControl, UKACC UK, 2000.
12.
ShamsollahiP.MalikO. P.‘On-line identification of synchronous generator using neural networks.’ In Proceedings of Canadian Conference onElectrical and computer engineering (CCECE'96), Calgary, Canada, Part II, 1996, pp. 595–598.
13.
WeiH. L.BillingsS. A.‘A unified wavelet-based modeling framework for nonlinear system identification: The WANARX model structure.’Int. J. Control77 (4) (2004): 351–366
14.
WeiH. L.BillingsS. A.BalikhinM. A.‘Wavelet based nonparametric NARX models for nonlinear input-output system identification.’Int. J. Syst. Sci.37 (15) (2006): 1089–1096
15.
BillingsS. A.WeiH. L.‘The wavelet-NARMAX representation: A hybrid model structure combining polynomial models with multiresolution wavelet decompositions.’Int. J. Syst. Sci.36 (3) (2005): 137–152
16.
HeY.ChuF.ZhongB. A.‘A hierarchical evolutionary algorithm for constructing and training wavelet networks.’Neural Comput. Appl.10 (2002): 357–366
MallatS.‘A theory for multiresolution signal decomposition: The wavelet transform.’Trans. IEEE Pattern Anal. Mach. Intell.11 (7) (1989): 674–693
19.
ZhangJ.WalterG. G.MiaoY.LeeW. W. N.‘Wavelet neural networks for function learning.’Trans. IEEE Signal Processing43 (6) (1995): 1485–1497
20.
BillingsS. A.LeontaritisI. J.‘Parameter estimation techniques for nonlinear system.’ In Proceedings of 6th IFAC symposium onIdentification and system parameter estimation, Washington, DC, 1982, pp. 235–244.
21.
NarendraK. S.ParthasaratyK.‘Identification and control of dynamical system using neural networks.’Trans. IEEE Neural Networks1 (1) (1990): 4–27
22.
PostalciogluS.BecerikliY.‘Wavelet networks for nonlinear system modeling.’Neural Comput. and Applic.16 (4) (2007): 433–441
23.
HangM. T.MenhajM. B.‘Training feed forward networks with the Marquardt algorithm.’Trans. IEEE Neural Networks5 (6) (1994): 989–993
24.
NortonJ. P.An introduction to identification, (Academic Press, London, UK.1986)
25.
KundurP.Power system stability and control, (McGraw-Hill.1994)
