论文部分内容阅读
本文利用BP神经网络逼近受控系统的动态及其逆动态，设计了一种静止无功补偿装置（SVC）的自校正内模控制器。该控制器的正模型和逆模型都以三层BP神经网络为主体，实现对SVC及电网的动态描述和对SVC的控制。所设计的控制器不需要电力网络及SVC的数学模型，并且具有良好的鲁棒性和控制精度。
In this paper, by using BP neural network to approximate the dynamics of the controlled system and its inverse dynamics, a self-tuning internal model controller of Static Var Compensator (SVC) is designed. Both the positive model and the inverse model of the controller are based on the three-layer BP neural network, which realizes the dynamic description of SVC and grid and the control of SVC. The designed controller does not need the mathematical model of power network and SVC, and has good robustness and control precision.