摘要
阐述和证明了基于输入输出微分方程描述的系统可逆性的充分条件 ,并给出了相应的解析逆系统的实现方法。文中同时研究了采用积分器和静态神经网络组成动态神经网络结构的方法 ,并将这种神经网络结构与逆系统理论相结合 ,提出了神经网络 α阶逆系统的结构及其实现步骤 ,运用该神经网络α阶逆系统对 TCSC控制器进行了设计。实际系统的仿真结果证实了所设计控制策略的有效性。
This paper presents and proves a sufficient condition of the invertibility of a general class of dynamic systems, which are represented by input-output differential equations. The realization of the corresponding analytic inverse system is also discussed. A novel dynamic neural network (NN), constructed based on a number of integrators and the static neural network, is investigated. Based on neural networks and the inverse system theory, an α-th order NN inverse system is proposed and its application to power system TCSC control has been attempted. Simulation results show the effectiveness of the proposed methods. This project is supported by National Natural Science Foundation of China (No. 69784001 and No. 59925718).
出处
《电力系统自动化》
EI
CSCD
北大核心
2001年第3期11-17,29,共8页
Automation of Electric Power Systems
基金
国家自然科学基金资助项目! (6 97840 0 15 992 5 718)
关键词
神经网络
逆系统
电力系统
协调控制
暂态稳定性
Computer simulation
Differential equations
Neural networks
Nonlinear control systems
