互感器故障诊断人工神经网络法

An artificial neural network for faultdiagnosis of instrument transformers

基于神经网络的基本结构和算法 ,该文建立了一个用于高压电磁式互感器故障诊断的人工神经网络。其中采用了有效的网络学习算法 ,旨在全面、快速和准确地实现互感器故障诊断 ,以提高互感器及电力系统运行的可靠性。根据互感器的故障特征 ,该文建立一个 3层前向神经网络 ,采用误差逆传播学习算法进行了讨论 ,并由仿真计算结果加以论证。

Based on both the basic structure and the count method of neural network. In this paper an artificial neural network has been built to diagnose faults in instrument transformers. An efficient network learning calculating method is used. The reliabilities of both the instrument transformer and the power system can benefit from the neural network. On the basis of the instrument transformers fault feature, a Three-layer feed-forward neural network was built and the Error Back——Propagation (EBP) learning calculating method was used to discuss.