| Neuromorphic Continuous-Time State Space Pole Placement Adaptive Control |
| |
| 作者姓名： | 卢钊 孙明伟 |
| |
| 作者单位： | Lu Zhao & Sun Mingwei
Department of Electrical and Computer Engineering University of Houston，Houston，U.S. A; The Third Academy，China Aerospace Science and Industry Corporation，Beijing 100074，P. R. China |
| |
| 摘 要： | Abstract: A neuromorphic continuous-time state space pole assignment adaptive controller is proposed, which is particularlyappropriate for controlling a large-scale time-variant state-space model due to the parallely distributed nature ofneurocomputing. In our approach, Hopfield neural network is exploited to identify the parameters of a continuous-timestate-space model, and a dedicated recurrent neural network is designed to compute pole placement feedback control law inreal time. Thus the identification and the control computation are incorporated in the closed-loop, adaptive, real-timecontrol system. The merit of this approach is that the neural networks converge to their solutions very quickly andsimultaneously.
|
Neuromorphic Continuous-Time State Space Pole Placement Adaptive Control |
| |
| Lu Zhao & Sun Mingwei.Neuromorphic Continuous-Time State Space Pole Placement Adaptive Control[J].Journal of Systems Engineering and Electronics,2003,14(1). |
| |
| Authors: | Lu Zhao & Sun Mingwei |
| |
| Institution: | 1. Department of Electrical and Computer Engineering University of Houston, Houston, U.S. A
2. The Third Academy, China Aerospace Science and Industry Corporation, Beijing 100074, P. R. China |
| |
| Abstract: | A neuromorphic continuous-time state space pole assignment adaptive controller is proposed, which is particularly appropriate for controlling a large-scale time-variant state-space model due to the parallely distributed nature of neurocomputing. In our approach, Hopfield neural network is exploited to identify the parameters of a continuous-time state-space model, and a dedicated recurrent neural network is designed to compute pole placement feedback control law in real time. Thus the identification and the control computation are incorporated in the closed-loop, adaptive, real-time control system. The merit of this approach is that the neural networks converge to their solutions very quickly and simultaneously. |
| |
| Keywords: | Pole assignment Parameter identification Hopfield neural network Sylvester's equation Recurrent neural network |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
