基于RBF人工神经网络的电动机振动故障诊断  

Fault diagnosis of vibration of motors based on RBF neural network

作　　者：葛强[1] 徐俩俩[1] 仇宝云[1] 谈磊[1] 唐建军[1] 

机构地区：[1]扬州大学能源与动力工程学院,江苏扬州225009

出　　处：《河海大学学报（自然科学版）》2008年第6期842-845,共4页Journal of Hohai University(Natural Sciences)

基　　金：国家自然科学基金(50279045);全国百篇优秀博士论文专项课题;扬州大学创新培育基金;扬州大学大学生学术科技创新基金

摘　　要：针对电动机转子不平衡、不对中、油膜涡动、转子径向碰摩、喘振、轴承座松动等常见的几种振动故障,用RBF网络对提取出的6种故障信息进行分类,判断故障类型,并进行了仿真试验,最后将试验结果与BP网络的诊断结果进行了详细的分析比较.结果表明,RBF网络可以应用于电动机转子振动故障诊断,其诊断速度比BP神经网络快,诊断结果也更为准确.There are 6 familiar vibration faults of asynchronous motors： rotor imbalance, non-aligning, oil swirl, radial friction, surge and flexible bearing bracket. The extracted features were classified by use of the RBF neural network, and their fault types were diagnosed and simulated. The simulated results were compared with those of the BP neural network. The results show that the RBF neural network can be applied in the diagnosis of vibration faults of motors, the diagnosis is feasible, fast and exact.

关 键 词：RBF网络 电动机 振动 故障诊断 

分 类 号：TM307.1[电气工程—电机]