局部均值分解与支持向量机相融合的传感器故障诊断  

Sensor fault diagnosis fusing local mean decomposition with support vector machine

作　　者：武青海[1] WU Qinghai(Jilin Agricultural Science and Technology University,Jilin 132101,China)

机构地区：[1]吉林农业科技学院,吉林吉林132101

出　　处：《现代电子技术》2017年第3期110-113,共4页Modern Electronics Technique

基　　金：基金项目:农业院校科技孵化园对推进大学生创新创业教育的研究(ZD115088)

摘　　要：为了提高传感器故障诊断精度,提出一种基于局部均值分解和支持向量机相融合的传感器故障诊断算法。首先利用局部均值分解方法将传感器的输出信号分解成一系列由包络信号和纯调频信号相乘所得的PF分量;然后利用支持向量机进行故障识别;最后采用Matlab编程实现仿真对比实验。实验结果表明,该方法可以较好地识别传感器故障,提高了传感器故障诊断的稳定性和准确性。In order to improve the diagnosis accuracy of the sensor fault,a sensor fault diagnosis algorithm based on the fusion of local mean decomposition and support vector machine is proposed. The local mean decomposition method is used to decompose the sensor′s output signal into a series PF components obtained by multiplying the envelope signal by pure FM signal. The support vector machine(SVM)is employed to recognize the sensor fault. The Matlab programming is used to realize the simulation comparison experiments. The results show this method can identify the sensor fault better,and improve the stability and accuracy of the sensor fault diagnosis.

关 键 词：局部均值分解 支持向量机 传感器故障诊断 故障识别 

分 类 号：TN911.7.34[电子电信—通信与信息系统] TP911[电子电信—信息与通信工程]