Abstract
A kind of single-input single-output neural net adaptive controller (SISO-NNC) and its algorithm have been presented. For the computer simulation and the special requirements of control problem, we have improved traditional BP algorithm and solved the problem of local minimum to some extent. Using the SISO-NNC to control time-varying system, the simulation results show advantages of neural net controller in control field.
Similar content being viewed by others
References
Chen Fuchung. Back-propagation neural networks for nonlinear self-tuning adaptive control.IEEE Control Syst Mag, April 1990:44–48
Nguyen D H. Neural networks for self-learning control systems.IEEE Control Syst Mag, April 1990: 18–23
Hoskins D A, Hwang J N, Vagners J. Iterative inversion of neural networks and it's application to adaptive control.IEEE Trans on Neural Network, 1992,3(1):292–301
Narendra K S. Identification and control of dynamical systems using neural networks.IEEE Trans Neural Network, 1990,1(1):4–27
Qin Sizhao, Su Hongte, McAvoy J. Comparison of four neural net learning methods for dynamic system identification.IEEE Trans on Neural Network, 1992,3(1): 122–130
Zhao Meide. A hybrid learning method for mutilayer perceptrons.Journal of Harbin Institute of Technology, 1990,3:52–61
Author information
Authors and Affiliations
Additional information
Zhu Qiuping: born in 1946, Associate professor
Rights and permissions
About this article
Cite this article
Qiuping, Z., Zhihao, F. & Yinbiao, H. Dynamic back-propagation neural net for adaptive controller. Wuhan Univ. J. Nat. Sci. 3, 196–200 (1998). https://doi.org/10.1007/BF02827551
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02827551