基于小波变换和人工神经网络的保护原理研究

提出了一种利用小波变换提取信号特征，并结合神经网络来识别电力系统短路故障的方法．该方法首先对测量信号作小波变换，提取特征量，作为多层前向神经网络的输入．对不同的输出要求，提出采用不同的神经网络，判断出发生故障的相位、性质和位置．

Study for Protection Principle Based on Wavelet Transformation and Artificial Neural Network

A new approach which combines wavelet transformation and artificial neural network to identify the fault in power systems,is proposed. The measured signal is transformed by wavelet and the features of the signal are extracted. Then these features are used as input to a three layer forward neural network. Different neural networks are employed in different output. So the fault property and location can be identified. The experimental results show that this approach is efficient for fault identification.