模糊小波神经网络在电机断条故障检测的研究  

Fault Diagnosis of Electrical Fault Based on Fuzzy Wavelet Neural Network

作　　者：王新[1] 戴丽[1] 

机构地区：[1]河南理工大学,河南焦作454000

出　　处：《仪表技术与传感器》2009年第4期140-142,共3页Instrument Technique and Sensor

基　　金：河南省重点科技攻关项目(072102240006);河南省高校科技创新人才支持计划项目(2008HASTIT022);河南省青年骨干教师资助项目;河南理工大学博士基金项目(B050801)

摘　　要：鼠笼式异步电机的转子绕组由导条和端环组成,最常见的故障是断条和端环断裂。诱发原因主要有:设计制造不合理、频繁起停、交变负载使导条和端环因冷热循环而疲劳断裂、电压波动造成电流过大而过热等。针对这些故障,文中用模糊小波神经网络的分析方法,有效地提取了转子断条故障的特征信息,克服了传统基于FFT分析方法难以提取故障特征频率分量的难点,并依靠神经网络诊断方法,准确地识别出了电动机转子断条故障。The squirrel-cage asynchronous motor rotor windings consists of the conducting bar and the end ring. The most common fault is broken bar and fracture-ring. The main reasons are the unreasonable design and manufacturing, frequent stop, alternating load making the end ring fatigue fracture because of thermal cycles, or the large current caused by voltage fluctuation, results in overheating. According to this fault,this paper used wavelet neural network analysis method,effectively coUected the broken bars feature information,overcame the traditional method based on FFT analysis which was difficult to collect the fault characteristic frequency component. And it adopted the neural network diagnostic methods, accurately identify the broken rotor fault of the motor rotor.

关 键 词：模糊小波神经网络 转子断条 故障检测 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]