摘要
运用小波包频道能量分解技术提取了不同频带反映矿用通风机不同工作状态的特征向量,以此作为BP神经网络的故障样本,经训练的网络作为故障智能分类器可对通风机的工作状态进行自动识别和诊断.研究结果表明,小波包与神经网络相融合的故障诊断与识别技术发挥了两者的优点,是提取机械故障特征进行设备状态自动识别的有效方法.
Which reflects different working state of ventilator,was extracted from different frequency segment with the technology of wavelet packet frequency segment power decomposition, and taking it as input fault sample of BP neural network.The trained network, as fault intelligent classification, has very strong identification capability, which can identify automatically the working state of ventilator.The result of research shows that the fault diagnosis and identification technology,based on syncretizing wavelet packet and neural network, exerts their strongpoints, and it's a effective method of extracting mechanical fault characteristic and auto-identifying equipment's working state.
出处
《煤炭学报》
EI
CAS
CSCD
北大核心
2004年第6期736-739,共4页
Journal of China Coal Society
基金
河南省科技攻关项目(0424260115)
关键词
小波包
BP网络
通风机
故障诊断
wavelet packet
BP network
ventilator
fault diagnosis
