摘要
针对电力系统的日益复杂性和故障原因的不可预测性,为达到准确的限流控制,提出了基于人工神经网络的限流控制策略．对具有可控串补功能的短路限流器进行了分析,提出了由两个独立子网络组成的人工神经网络控制模型．应用实际模型,使用电磁暂态仿真程序对电力系统可能发生的各种故障进行了动态仿真．新控制模型训练样本的输出结果和检验样本的输出结果相差不大,验证了两个子网具有很强的适应能力和逼近能力．使用基于人工神经网络的限流控制策略得到的限流波形峰值比使用PID控制策略得到的限流波形峰值要小得多,验证了新限流控制策略的可行性和准确性．
To make current-limit control more accurate for the more complicated power system and the more unpredictable reason of the fault, a new strategy of limiting the fault current based on the artificial neural network （ANN） is proposed. The fault current limiter with thyristor controlled series compensation（TCSC） is analysed. The control model with ANN composed of two independent subnets is presented. With the application of actual model ,the dynamic simulation by the alternative transients program（ATP） is performed. The outputs of training samples of the new control model is nearly the same as the ones of checkout samples, and the strong adaptability and accuracy of the two subnets are verified. The peak of short circuit current by the control of the new strategy is much smaller than the one by the control of the proportional integral derivative （PID） strategy, and the feasibility and the accuracy of the new control strategy are proved.
出处
《天津大学学报》
EI
CAS
CSCD
北大核心
2006年第5期548-552,共5页
Journal of Tianjin University(Science and Technology)
关键词
短路限流器
可控串联补偿电容
人工神经网络
动态仿真
fault current limiter
thyristor controlled series compensation
artificial neural network
dynamic simulation
