基于径向基网络的同杆双回路故障类型判定

由于同杆双回线发生故障时两回线之间存在非线性耦合 ,故用传统方法无法对同杆双回线进行故障判定 ,而径向基神经网络可以通过故障线路相关电压和电流对线路故障进行准确分类 ,网络输入样本在不同故障发生地点、发生时间、过渡电阻情况下得到。仿真结果表明该网络能够进行同杆双回路故障判定。

Fault identification in double-circuit on same pole using neural network

The problems encountered by conventional techniques in fault type classification in double-circuit transmission line is presented in this paper; these arise principally due to the mutual coupling is nonlinear. However a RBF(radial basis function)neural network provides the ability to classify the fault type by identifying different patterns of the associated voltages and currents, which is tested under different fault location, inception angle and resistance. All simulation results show that the neural network is well suited for double-circuit.