摘要
研究一种渐近超稳定的神经元智能控制器结构.基于POPOV超稳定性定理,提出一种能保证控制系统渐近超稳定的控制器参数学习算法.针对神经元智能控制的直流全数字调速系统做了仿真实验,给出了仿真结果.
An adaptive neural controller are used to control a given plant. A learning architecture is proposed for modifying the weights of the neural controller to provide appropriate inputs to the plant so that a desired response is obtained and global asymptotic hyperstability is guaranteed. The properties of the proposed control architecture is studied by simulating a D. C. digital speed-regulating system.
出处
《中山大学学报(自然科学版)》
CAS
CSCD
北大核心
2001年第1期35-38,共4页
Acta Scientiarum Naturalium Universitatis Sunyatseni
基金
中山大学青年基金资助项目(99-020-429119)