Synchronous machine model identification using continuous wavelet NARX network

Abstract 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.

[1]  R. H. Park,et al.  Two-reaction theory of synchronous machines generalized method of analysis-part I , 1929, Transactions of the American Institute of Electrical Engineers.

[2]  Steve A. Billings,et al.  A unified wavelet-based modelling framework for non-linear system identification: the WANARX model structure , 2004 .

[3]  Om P. Malik,et al.  Nonlinear state space identification of a synchronous generator , 2003, 2003 IEEE Power Engineering Society General Meeting (IEEE Cat. No.03CH37491).

[4]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[5]  G.T. Heydt,et al.  Online parameter estimation of round rotor synchronous generators including magnetic saturation , 2005, IEEE Transactions on Energy Conversion.

[6]  Jun Zhang,et al.  Wavelet neural networks for function learning , 1995, IEEE Trans. Signal Process..

[7]  S. Crary.  Two-Reaction Theory of Synchronous Machines , 1937, Transactions of the American Institute of Electrical Engineers.

[8]  Qinghua Zhang,et al.  Wavelet networks , 1992, IEEE Trans. Neural Networks.

[9]  P. Kundur,et al.  Power system stability and control , 1994 .

[10]  Ali Keyhani,et al.  Synchronous machine parameter estimation using the Hartley series , 2001 .

[11]  O. Nelles.  Nonlinear System Identification: From Classical Approaches to Neural Networks and Fuzzy Models , 2000 .

[12]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[14]  I. J. Leontaritis,et al.  Parameter Estimation Techniques for Nonlinear Systems , 1982 .

[15]  S. A. Billings,et al.  The wavelet-NARMAX representation: A hybrid model structure combining polynomial models with multiresolution wavelet decompositions , 2005, Int. J. Syst. Sci..

[16]  Fulei Chu,et al.  A Hierarchical Evolutionary Algorithm for Constructing and Training Wavelet Networks , 2002, Neural Computing & Applications.

[17]  Ali Keyhani,et al.  An algebraic approach for identifying operating point dependent parameters of synchronous machines using orthogonal series expansions , 2001 .

[18]  Yasar Becerikli,et al.  Wavelet networks for nonlinear system modeling , 2007, Neural Computing and Applications.

[19]  Stephen A. Billings,et al.  Wavelet based non-parametric NARX models for nonlinear input–output system identification , 2006, Int. J. Syst. Sci..

[20]  Om P. Malik,et al.  Identification of physical parameters of a synchronous generator from on-line measurements , 2003, 2003 IEEE Power Engineering Society General Meeting (IEEE Cat. No.03CH37491).

[21]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[22]  Elias Kyriakides,et al.  Estimation of synchronous generator parameters using an observer for damper currents and a graphical user interface , 2004 .

[23]  G. MallatS..  A Theory for Multiresolution Signal Decomposition , 1989 .

[24]  O.P. Malik,et al.  Identification of physical parameters of a synchronous Generator from online measurements , 2004, IEEE Transactions on Energy Conversion.

[25]  O. P. Malik,et al.  On-line identification of synchronous generator using neural networks , 1996, Proceedings of 1996 Canadian Conference on Electrical and Computer Engineering.