基于类加权支持向量机的永磁直流电机故障模式识别方法  

A Method of Failure Recognition Based on Weighted Support Vector Machines for Permanent Magnetic DC Motor

作　　者：刘曼兰[1,2] 崔淑梅[3] 郭斌[2] 

机构地区：[1]哈尔滨工业大学机电工程学院,哈尔滨150001 [2]哈尔滨工业大学材料科学与工程学院,哈尔滨150001 [3]哈尔滨工业大学电气工程学院,哈尔滨150001

出　　处：《微电机》2011年第5期79-82,共4页Micromotors

摘　　要：该文针对永磁直流电机故障在线诊断中存在类样本数目不平衡、误判损失不等、在线样本数据缺少类别标识等问题,通过对支持向量机数学模型中的误差惩罚因子进行加权,构建了一种基于加权支持向量机的永磁直流电机故障模式识别算法。理论分析和实验结果表明:该算法可以提高小样本类(故障样本类)诊断精度,降低误判损失。To overcome the problems existing in the online fault diagnosis of permanent-magnetic DC motor,such as non-symmetry of dataset,different loss by misjudgments and interference of noisy or outliers,the recognition algorithms of SVM is improved in following way.A weighted support vector machine algorithm is developed through weighting error punishing factor of SVM.Both results of several experiments and analysis in theory show that this weighted support vector machines improve classification accuracy for class with small size,and reduce the different loss by misjudgments in fault diagnosis for permanent-magnetic DC motors.

关 键 词：永磁直流电机 类加权支持向量机 模式识别 故障诊断 

分 类 号：TM351[电气工程—电机] TM33