结合经验模态分解能量总量法的断路器振动信号特征向量提取  

Extraction of Vibration Signal Feature Vector of Circuit Breaker Based on Empirical Mode Decomposition Amount of Energy

作　　者：孙一航[1] 武建文[1] 廉世军 张路明 

机构地区：[1]北京航空航天大学自动化科学与电气工程学院,北京100191 [2]珠海市可利电气有限公司,珠海519085

出　　处：《电工技术学报》2014年第3期228-236,共9页Transactions of China Electrotechnical Society

基　　金：国家自然科学基金资助项目(5117704)

摘　　要：为了检测出断路器的机械结构故障类型,本文分析了断路器机械振动信号的特性,提出基于经验模态分解(EMD)能量总量法与支持向量机(SVM)理论相结合的中压断路器振动信号的特征向量提取和故障分类的分析方法。首先将断路器的振动信号进行经验模态分解,得到所需要的内禀模态函数(IMF),通过离散采样点求能量总量的方法求出包含主要故障特征信息的各个内禀模态函数分量的能量总量。利用IMF分量能量总量作为特征向量,并以此作为支持向量机输入,将测试样本信号的故障特征向量输入训练好的SVM,并对SVM及核函数参数进行遗传算法优化,采用"二叉树分类"支持向量机分类机制进行故障分类。经实验分析该方法能很好地识别出振动信号的差别及故障类型。In order to detect a mechanical type of structural failure of the circuit breaker, the characteristics of the circuit breaker mechanical vibration signal is analyzed in this paper. A combination of medium voltage circuit breaker based on empirical mode decomposition（EMD） amount of energy and support vector machine（SVM） theory vibration signal feature vector extraction and analysis of fault classification method is proposed. First, the vibration signal of the circuit breaker is decomposed by EMD, and then intrinsic mode function（IMF） is obtained. The total energy of each failure intrinsic mode function component obtained the method of discrete sampling points information which contains the main features. Using the amount of energy of IMF component as a feature vector, SVM and kernel function parameters and genetic algorithm optimization, the failure of the test sample signal as input feature vector into trained ＂BT-SVM＂ support vector machine classification mechanism for fault classification. The difference and fault type of vibration signals can be identified by this method through the experimental analysis.

关 键 词：断路器 振动信号 经验模态分解 能量法 故障诊断 SVM 

分 类 号：TM501[电气工程—电器]