摘要
传统的线性PI控制器在非线性系统的特定运行点有较好的性能,但在其他运行点它的性能会降低。应用启发式动态规划算法设计了静止同步串联补偿器(Static Series Synchronous Compensator,SSSC)的外部非线性最优神经控制器,总共包含3个神经网络;第一个为模型网络,它的主要作用是模拟系统的输入输出动态特性;第二个为神经网络为评价网络,它的主要作用是评价动作网络给出控制量的好坏;第三个为动作网络,它的作用是产生控制量;这三个为神经网络互相协作,从而得到最佳的控制序列。在Matlab/Simulink动态仿真环境中搭建了含SSSC双机电力系统的仿真模型,并对线路阻抗的调节过程和电容电压的变化过程进行了仿真,与传统的PI控制器相比,具有响应快、超调小的特点。
Conventional linear PI controllers have good performance at one specific operating point of the nonlinear power system. At other operating points its performance degrades. Therefore, the outer nonlinear optimized neuro-controller using Heuristic Dynamic Programming （HDP） is designed for SSSC. The controller based HDP contains a total of three neural networks. The first one is model network which simulates the input and output dynamic characteristics of the system; the second one is critic network, and its main role is to evaluate the controller output given by action network; the last one is action network which is used to give the controller variable. These three neural networks are in collaboration with each other to obtain the optimal control sequence. A studying example for simulating the regulating process of transmission line impedance and DC link capacitor voltage and the transient stabilization is carried out. Compared with the traditional PI controller, the proposed method has fast response, small overshoot characteristics.
出处
《电力系统保护与控制》
EI
CSCD
北大核心
2010年第23期87-92,共6页
Power System Protection and Control
