摘要
分析高压断路器机械振动信号的特性,提出一种以改进的经验模态分解(empirical mode decomposition,EMD)能量熵和支持向量机(support vector machine,SVM)相结合的诊断高压断路器机械故障的方法,并给出了可行的诊断步骤和分析。首先利用经验模态分解方法将高压断路器的振动信号分解成一些相互独立的内禀模态函数(intrinsic mode function,IMF),然后利用正常状态标准信号所得各固有内禀模态函数包络信号的等能量分段方式,实现对待测状态信号各IMF包络的时间轴分段,计算各待测信号IMF包络的能量熵向量,以此构造的经验模态分解能量熵向量作为支持向量机的输入向量。采用"次序二叉树"向量机分类,利用梯度法和交叉检验优化支持向量机模型参数。实验结果表明,该方法诊断高压断路器机械故障能取得良好的效果。
To research the characteristics of mechanical vibration signals of high voltage circuit breakers,a new method for fault diagnosis was proposed based on improved empirical mode decomposition（EMD） energy entropy and support vector machine（SVM）;and feasible diagnostic steps and analysis were also introduced.Firstly,the original vibration signals were decomposed into a number of intrinsic mode functions（IMF） by the EMD method.Secondly,the energy entropy vector was extracted with the segmental energy of IMF based on the theory of entropy and the method of equal energy,and was considered as the input vector of SVM.The Binary tree vector machine was used to solve the multi-class classification problem;and the gradient method and cross-validation were taken to optimize model parameters.The experiment shows that the proposed method is effective to diagnose the machinery faults of high voltage circuit breakers.
出处
《中国电机工程学报》
EI
CSCD
北大核心
2011年第12期108-113,共6页
Proceedings of the CSEE
基金
国家自然科学基金项目(50875011)~~
关键词
高压断路器
振动信号
能量熵
支持向量机
故障诊断
high voltage circuit breaker
vibration signal
energy entropy
support vector machine（SVM）
fault diagnosis
