基于MKLSVM的MVB端接故障诊断

列车通信网络的故障诊断一直是列车健康管理中的难点,复杂的工作环境、分布式的系统结构也使得故障难以被发现和定位.在分析多功能车辆总线(Multifunction Vehicle Bus,MVB)网络端接故障和反射形成机理的基础上,提出了一种以MVB网络物理波形参数为样本特征,结合多核学习支持向量机(Multiple Kernel Learning Support Vector Machine,MKLSVM)的网络故障诊断方法,以完成由端接电阻造成的网络故障诊断.搭建平台,进行了数据采集、模型训练、结果测试.分别利用普通支持向量机及MKLSVM对样本集进行了测试,并从不同性能度量角度评估了分类器性能.结果显示:以物理波形参数为样本特征能够表征端接网络故障的故障模式,结合支持向量机(Support Vector Machine,SVM)的模式识别方法能够有效对端接网络故障进行诊断.在查准率、查全率、分类精度、代价函数方面,MKLSVM均优于普通SVM分类器.

Fault location of two-parallel transmission line for double phase-to-earth fault using one-terminal data

An accurate algorithm for fault location of double phase-to-earth fault on transmission line of direct ground neutral system is presented. The algorithm, which employs the faulted phase network and zero-sequence network as fault-location model in which the source impedance at the remote end is not involved, ef-fectively eliminates the effect of load flow and fault resistance on the accuracy of fault location. The algorithm achieves accurate location by measuring only one local end data and is used in a procedure that provides automatic determination of faulted types and phases, and does not require the engineer to specify them. Simulation results showed the effectiveness of the algorithm under the condition of double phase-to-earth fault.