| Interval standard neural network models for nonlinear systems |
| |
| 作者姓名： | LIU Mei-qin |
| |
| 作者单位： | School of Electrical Engineering，Zhejiang University，Hangzhou 310027，China |
| |
| 基金项目： | Project supported by the National Natural Science Foundation of China (No. 60504024), and Zhejiang Provincial Education Depart-ment (No. 20050905), China |
| |
| 摘 要： | INTRODUCTION Neural networks have been successfully em- ployed for controlling nonlinear systems since the 1990’s (Narendra and Parthasarathy 1990; Hunt et al., 1992; Suykens et al., 1996). In these nonlinear control systems, neural networks have been used either for modelling the system to be controlled, or for design- ing a controller, or both. Recently, the robustness issue has been an important focus of research in neuro-control circles (Suykens et al., 1996; Wams et al., 1999; Aya…
|
| 关 键 词： | 神经网络 ISNNM 非线性系统 LMI 渐近稳定度 鲁棒控制 |
| 收稿时间： | 2005-05-09 |
| 修稿时间： | 2005-11-21 |
Interval standard neural network models for nonlinear systems |
| |
| LIU Mei-qin.Interval standard neural network models for nonlinear systems[J].Journal of Zhejiang University Science,2006,7(4):530-538. |
| |
| Authors: | Mei-qin Liu |
| |
| Institution: | (1) School of Electrical Engineering, Zhejiang University, Hangzhou, 310027, China |
| |
| Abstract: | A neural-network-based robust control design is suggested for control of a class of nonlinear systems. The design ap- proach employs a neural network, whose activation functions satisfy the sector conditions, to approximate the nonlinear system. To improve the approximation performance and to account for the parameter perturbations during operation, a novel neural network model termed standard neural network model (SNNM) is proposed. If the uncertainty is bounded, the SNNM is called an interval SNNM (ISNNM). A state-feedback control law is designed for the nonlinear system modelled by an ISNNM such that the closed-loop system is globally, robustly, and asymptotically stable. The control design equations are shown to be a set of linear matrix inequalities (LMIs) that can be easily solved by available convex optimization algorithms. An example is given to illustrate the control design procedure, and the performance of the proposed approach is compared with that of a related method reported in literature. |
| |
| Keywords: | Interval standard neural network model (ISNNM) Linear matrix inequality (LMI) Nonlinear system Asymptotic stability Robust control |
| 本文献已被 CNKI 维普 万方数据 SpringerLink 等数据库收录！ |
