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。 Based on the analysis of the changing rules of the current curve of the speed-increasing turnout, an intelligent fault diagnosis algorithm of the speed-increasing switch based on BP neural network is proposed. By summarizing the fault current curves of typical speed-up switch, the eigenvector values ​​of the operating current curves are extracted, and the BP neural network is used to train and test the mapped sample sets of feature vectors and turnout fault types. Experiments show that the fault diagnosis algorithm of speed-up switch based on BP neural network has high accuracy and good effect.