Neural network model reference control of nonlinear systems
暂无分享,去创建一个
D.H. Nguyen and B. Widrow (IEEE Contr. Syst. Mag. vol.10, no.3, April 1990) developed a procedure for training a neural network controller directly from input-output measurements of the nonlinear plant. The problem as posed is representative of designing a regulator control system for nonlinear, but stable, dynamical plants. Difficulties were encountered in attempting to apply the unmodified technique to the benchmark nonlinear control problem of stabilizing an inverted pendulum. A modified procedure for resolving these difficulties that makes use of the model reference control system design principle, common in traditional adaptive control system design, is presented. Very good results were achieved.<<ETX>>
[1] Kumpati S. Narendra,et al. Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.
[2] C.W. Anderson,et al. Learning to control an inverted pendulum using neural networks , 1989, IEEE Control Systems Magazine.
[3] Derrick H. Nguyen,et al. Neural networks for self-learning control systems , 1990 .
[4] Bernard Widrow,et al. Punish/Reward: Learning with a Critic in Adaptive Threshold Systems , 1973, IEEE Trans. Syst. Man Cybern..