基于GPS同步量测量的模糊神经网络用于暂态稳定预测研究

利用GPS同步时钟获得系统各机组的功角或系统内最大摇摆角 ,然后通过模糊神经网络进行暂态稳定性预测 ,充分利用了模糊系统和神经网络的优点 ,一方面考虑了专家的经验 ,另一方面又通过样本集进行学习 ,能自动提取模糊规则、优化隶属函数等 ,因此具有较高的模式分类正确率和函数逼近精度。对 6机 2 2节点的算例表明 ,所提方法是有效的。

Power systems transient stability prediction by using fuzzy neural network based on GPS synchronized measurements

This paper presents a transient stability prediction method in which a fuzzy neural network can, on the basis of GPS synchronized generator angles, predict whether the power systems is stable or not after large disturbances. This approach has fully exploited the advantages of fuzzy logic and neural network, i.e., integrating the expert's experience, learning from the sample set, extracting automatically the fuzzy rules and optimizing the membership functions, etc. Therefore, it has high accuracy of pattern recognition and function approximation. The simulation indicates the validity of the proposed method of transient stability prediction.