基于BP神经网络的提速道岔故障诊断算法

Algorithm of Speed-up Turnout Fault Diagnosis Based on BP Neural Network

在分析提速道岔动作电流曲线变化规律的基础上,提出一种基于BP神经网络的提速道岔故障智能诊断算法。通过总结典型提速道岔故障动作电流曲线,提取动作电流曲线特征向量值,采用BP神经网络对提速道岔特征向量与道岔故障类型的映射样本集进行训练及测试。实验表明,基于BP神经网络的提速道岔故障诊断算法精度高、效果好。

According to the change rule of action current curves in speed-up turnout, an intelligent algorithm of speed- up turnout fault diagnosis was presented based on BP neural network, which summarized the typical speed-up turnout fault action current curves, extracted the feature vector value of action current curves, and used the BP neural network to train and test the speed-up turnout feature vector and the mapping data sets of turnout fault types. The experimental results show that the algorithm based on BP neural network has higher accuracy and better effect.