茨城大学工学部 楊子江 - yoh.ise.ibaraki.ac.jp

1 1 NN LPV 2 Introduction NFIR Hammerstein Wiener Hammerstein-Wiener (sandwich) 3 4 26-9, 793-790 (1987).

2 (EKF) 1993 GMDH Group Method of Data Handling A. G. Ivakhnenko: Polynomial theory of complex systems, IEEE Trans. on Systems, Man and Cybernetics, 1-4, 364-379 (1971). 5 R. Haber and H. Unbehauen: Structure Identification of nonlinear dynamic systems-A survey on input-output approaches, Automatica, 26-4, 651-677 (1990). Hammerstein Wiener Sandwich 6 NN BP : Identication and control of dynamical systems using neural networks, IEEE Transsations on Neural Networks, 1-1, 4/27(1990).

3 7 RBFN R. M. Sanner and J. J. E. Slotine: Gaussian networks for direct adaptive control, IEEE Trans. Neural Network, NN-6, 837/863(1992). 2012 4 1317 S. S. Ge, C. C. Hang, T. H. Lee and T. Zhang, Stable Adaptive Neural Network Control, Kluwer Academic Publishers(2002). Y. H. Kim and F. L. Lewis: High-Level Feedback Control with Neural Networks, World Scientific (1998). 8(2000) ARX NARX (1997) 9 NARX NN RBFN LPV 102000 S.

4 Paoletti, A. Juloski, G. Ferrari-Trecate, and R. Vidal, Identificationof hybrid systems: a tutorial, European Journal of Control, vol. 513(2-3), pp. 242 260, 2007 -VI / / Vo l . 5 2 No. 3, pp. 103-109, 2008 PWARX(Piece-Wise affine Auto Regressive eXogenous 11 Hammerstein : Subspace Identification of Hammerstein Systems Using Least Squares Support Vector Machines, IEEE Transsations on Automatic Control, 50-10, 1509/1519(2005).)

5 Wiener R. Raich, R. G. T. Zhou, M. Viberg, Subspace based approaches for Wiener system identification, IEEE Transsations on Automatic Control, 50-10, 1629/1634 (2005). 12 (Partical Filter) Monte Carlo (Unscented KalmanFilter)Unscented Expectation-Maximization Algorithm EKF) 2006 2001 13 2010 Vol.

6 49, No. 7, 2010 142006 Gregor Gregorcic and Gordon Lightbody: Nonlinear system identification: From multiple-model networks to Gaussian processes, Engineering Applications of Artificial Intelligence 21 (2008) 1035 1055. 2 15 2 NARX NARX 16 NARX Nonlinear Auto Regressive eXogenous) NARX 17 NARX 18 NARX 19 NARX NN NN20 NN NN 22 i 23

7 E. Hernandez and Y. Arkun, Control of nonlinear systems using polynomial ARMA models, AIChE Journal, 39-3, 446/349 (1993).J. W. Glass and M. A. Franchek, NARMAX modeling and robust control of internaalcombustion engines, International Journal of Control, 72-4, 289/304 (1999). : Identication and control of dynamical systems using neural networks, IEEE Transsations on Neural Networks, 1-1, 4/27(1990). NN ..25 , , 1208/1217(2000) 26 27 28 29 LBFN Local Basis Function Network 30 2 31 RBFN Radial Basis Function Network RBF 32 g(x)

8 33 FBFN Fuzzy Basis Function Network RBF RBF FBF Partition of 34 FBF RBF Robert Shorten and Roderick Murray-Smith Side Effects of Normalising Radial Basis Function Networks, 35 36 37 38 WLBFN WaveLet Basis Function Network Q. Zhang, Using Wavelet Network in Nonparametric Estimation, IEEE Transactions on Neural networks, 8-2, 227/236 (1997)

9 39 41 42 44 m N 45 m 46 AIC BIC trade-off 3 47 3 48 NP GA)

10 49 Particle Swarm Optimization PSO GA PSO GA PSO 50 51 Gram-Schmidt S. Chen, S. A. Billings and W. Luo, Orthogonal least squares methods and their application to non-linear system identification, International Journal of Control, 50-5, 1873/1896 (1989) S.