基于EMD和SVM的传感器故障诊断方法.pdfVIP

文章编号【】 基于EMD 和SVM 的传感器故障诊断方法 (20 字以内) （二号黑体） 1 2 2 冯志刚 ，王 祁 ，信太克规 (1.沈阳航空工业学院 自动化学院，沈阳110136，fzg1023@yeah.net; 2.哈尔滨工业大学 自动化测试与控制系，哈尔滨150001) 摘 要：为了解决自确认压力传感器的故障诊断问题，提出了一种基于经验模式分解（EMD ）和支持 向量机（SVM ）的传感器故障诊断方法，该方法对传感器输出信号进行经验模态分解，将其分解为若 干个固有模态函数（IMF），对每个IMF 通过一定的削减算法增强故障特征，然后计算每个 IMF 和残 余项的能量以及整个信号的削减比作为特征向量，以此作为输入来建立支持向量多分类机，判断传 感器的故障类型。通过压力传感器的故障诊断结果表明，该方法能有效的应用于传感器的故障诊断 中。 关键词：经验模态分解；支持向量机；特征提取；传感器故障诊断 中图分类号：TH133; TP183 Sensor fault diagnosis based on empirical mode decomposition and support vector machines 1 2 2 FENG Zhi-gang , WANG Qi , SHIDA Katsunori (1.Department of Automation, Shenyang Institute of Aeronautical engineering, Shenyang 110136, China, fzg1023@yeah.net; 2.Department of Automatic Measurement and Control, Harbin Institute of Technology, Harbin 150001, China ) Abstract: To solve the fault diagnosis problem of self-validating pressure sensor, a sensor fault diagnosis approach based on empirical mode decomposition (EMD) method and support vector machines (SVM) is proposed. The EMD method is used to decompose the sensor output signal into a number of intrinsic mode function (IMF) components and a residue component. With some cutting algorithm, the IMFs with fault character are strengthened. After that, the energy of each IMF and residue component, and the average cutting ratio of all the IMFs and residue component are calculated, which are regarded as the feature vector. Then, the support vector machines for multi-classification used as fault classifiers are established to id