改善系统暂态稳定性的HVDC模糊神经控制器

提出了一种HVDC在线模糊神经控制器以提高交直流系统的暂态稳定性。该控制器的特点是结合了模糊系统处理复杂和不确定性问题及神经网络具有自学习能力的优点,选取整流侧交流母线电压相位误差及其变化率作为模糊逻辑控制部分的输入,其输出结果作为神经网络的一个输入,采用改进BP算法进行在线训练神经网络,神经网络的输出用来修正整流器的触发角,并利用NETOMAC软件对控制器主要参数进行了离线优化。仿真结果表明该控制器能有效地抑制有功功率振荡,改善发电机的功角特性,提高系统的暂态稳定性。

HVDC fuzzy neural controller for improving the transient stability of system

This paper puts forward an on-line controller for the HVDC transmission system to improve the transient stability of the AC/DC system. Based on the combination of fuzzy and ANN, this controller selects the voltage value of the AC bus at rectifier and its rate ratio as input signals of fuzzy control, the output of fuzzy part as one of the input signals of neural network, employs improved BP algorithm to perform neural network on-line training and NETOMAC software to perform off-line optimization. Simulation results show this proposed controller can damp the active power oscillation and enhance the transient stability of system. This project is supported by National Natural Science Foundation of China(No.50377017).