【摘要】 为提高发电机励磁控制系统的稳定性,分析了同步发电机的自并励励磁系统的结构和数学模型,介绍了神经网络预测控制的结构和算法,分别基于PID控制、神经网络预测控制和神经网络预测-PID串级控制算法对自并励励磁系统进行了仿真分析.通过仿真结果的对比分析,说明神经网络预测-PID串级控制在励磁控制中的应用提高了励磁系统的动态性、稳定性和抗干扰能力.更多还原

【Abstract】 The principle,structure and mathematical model of the self-shunt excitation control system of synchronous generator are analyzed,at the same time,the structure and algorithm of neural network predictive control are introduced in this paper. Self-shunt excitation system is simulated respectively based on PID control algorithm,neural network predictive control algorithm and neural network-PID cascade control algorithm.The comparative analysis of simulation results shows that neural network-PID cascade control algorithm used in the Excitation Control has potential and advantage.更多还原