摘要: This paper describes how a neural network, structured as multi layer perceptron, is trained to predict, simulate and control non-linear process. The identified model the well-known known innovation state space model, identification based only on input/output measurements, so in fact extended Kalman filter problem solved. training method recursive prediction error using Gauss-Newton search direction, from linear system theory. Finally, methods are tested noisy, strongly non-linear, dynamic process, showing excellent results for net act an actual identifier, predictor simulator. Further, allows on-line extraction of parameter matrices giving basis better >
sci-hub.se 参考文章(8)
K.J. Hunt, D. Sbarbaro, R. Żbikowski, P.J. Gawthrop, Neural networks for control systems: a survey Automatica. ,vol. 28, pp. 1083- 1112 ,(1992) , 10.1016/0005-1098(92)90053-I
S. A. BILLINGS, H. B. JAMALUDDIN, S. CHEN, Properties of neural networks with applications to modelling non-linear dynamical systems International Journal of Control. ,vol. 55, pp. 193- 224 ,(1992) , 10.1080/00207179208934232
S.A. Billings, H.B. Jamaluddin, S. Chen, A comparison of the backpropagation and recursive prediction error algorithms for training neural networks Mechanical Systems and Signal Processing. ,vol. 5, pp. 233- 255 ,(1991) , 10.1016/0888-3270(91)90045-7
S. CHEN, S. A. BILLINGS, P. M. GRANT, Non-linear system identification using neural networks International Journal of Control. ,vol. 51, pp. 1191- 1214 ,(1990) , 10.1080/00207179008934126
D. Psaltis, A. Sideris, A.A. Yamamura, A multilayered neural network controller IEEE Control Systems Magazine. ,vol. 8, pp. 17- 21 ,(1988) , 10.1109/37.1868
Kurt Hornik, Maxwell Stinchcombe, Halbert White, Multilayer feedforward networks are universal approximators Neural Networks. ,vol. 2, pp. 359- 366 ,(1989) , 10.1016/0893-6080(89)90020-8
K.S. Narendra, K. Parthasarathy, Identification and control of dynamical systems using neural networks IEEE Transactions on Neural Networks. ,vol. 1, pp. 4- 27 ,(1990) , 10.1109/72.80202
HornikK., StinchcombeM., WhiteH., Multilayer feedforward networks are universal approximators Neural Networks. ,(1989) , 10.5555/70405.70408