基于FOA-LSSVM的高速铁路道岔故障诊断

High-speed Railway Switch Failure Diagnosis Based on FOA-LSSVM

道岔故障类型识别对高速铁路设备维护具有重要的意义。在提出的基于FOA-LSSVM的高铁提速道岔故障诊断算法中,以道岔动作电流曲线监测数据为分析基础,选择5个特征指标组成道岔故障诊断模型的特征输入向量,降低了输入向量的维数,缩短训练时间,并采用果蝇优化算法,能够提高计算速度,保持良好的回归性能。通过实例分析证明:基于FOA-LSSVM的道岔故障诊断算法的分类性能好、识别准确率高,能够保证道岔故障类型测定的准确性和可靠性,缩短故障处理时间,确保高速铁路运输的安全与实效。

The railway switch failure type identification for high-speed railway signal equipment maintenance play an important role. In the paper, based on FOA-LSSVM high-speed railway switch failure diagnosis algorithm, in railway switch actuating current curves based on monitoring data for the analysis, chose five characteristic index composed of railway switch failure diagnosis models characteristic input vectors, not only reduces the dimension of input vectors, shortening training time, using a fruit fly optimization algorithm to accelerate the computing speed, while maintaining a good regression performance. Proved by an example： based on FOA-LSSVM railway switch failure diagnosis algorithm has strong selflearning ability and higher prediction accuracy, but also to accelerate the speed of switch failure prediction and improve the accuracy and reliability of railway switch failure prediction, to ensure the safety and effectiveness of high-speed rail transportation.