基于小波包—贝叶斯的小电流接地系统故障选线方法  

A fault line selection method of small current grounding system based on wavelet packet and Bayes theory

作　　者：王晓卫[1] 高杰[1] 魏向向[1] 侯雅晓 

机构地区：[1]河南理工大学电气工程与自动化学院,河南焦作454000

出　　处：《工矿自动化》2014年第6期54-59,共6页Journal Of Mine Automation

基　　金：河南省教育厅科学技术研究重点项目(12B470002;14A470004);河南省控制工程重点学科开放实验室资助项目(KG2011-15);河南理工大学青年基金项目(Q2012-28)

摘　　要：针对现有小电流接地系统故障选线方法存在故障状况复杂、故障信号特征不明显等问题,提出了一种基于小波包-贝叶斯的小电流接地系统故障选线方法。该方法首先按故障过渡电阻值的大小将小电流接地系统故障分为强故障模式、中等故障模式、弱故障模式,并分别构建相应的贝叶斯分类器;在故障特征提取方面,采用db小波包按照能量最大原则选取各条线路的故障特征频带,对所构建的3类分类器进行训练后,再将提取的各条线路的特征频带输入到分类器进行故障类型的判别;最后,采用"少数服从多数"的原则,对3类分类器的输出结果进行表决,进而得出选线结果。仿真结果表明,该方法选线准确率高。In view of problems of complex fault situation and unobvious characteristics of fault signal of fault line selection method of existing small current grounding system, a fault line selection method of small current grounding system based on wavelet packet and Bayes theory was proposed. Firstly, the method divides faults of small current grounding system into strong fault mode, medium fault mode and weak fault mode according to transition resistance, and constructs the Bayes classifier. Then, in extraction of fault features, it selects characteristic frequency band according to the maximum energy by db wavelet packet, and inputs the characteristic frequency band of every line into the classifier to judge fault type after training the Bayes classifier. Finally, it votes the output results of the three-classifier by majority principle, and acquires the fault line selection result. The simulation results show that the method has high accurate rate of line selection.

关 键 词：小电流接地系统 故障选线 故障模式 贝叶斯分类器 特征频带 

分 类 号：TD611[矿业工程—矿山机电]