摘要
针对电机震动信号的频谱特点,提出基于小波-神经网络技术的电机故障模式识别与诊断的新方法。利用小波包可进行多维多分辨率的特性,对电机振动信号进行分解与重构,获得震动信号的突变信息,实现电机状态的特征提取。对提取出的特征,用ART2神经网络进行状态分类,进而诊断故障类型,并利用这种方法进行仿真试验,通过对仿真结果的分析证实这种诊断的可行性。
New method of pattern recognition and fault diagnose based on the wavelet -neural network in electrical machine has been put forward according to their vibrational frequency spectrum characteristics. Based on the advantage of multi-dimensional, multi-scaling decomposition of wavelet packets, the abrupt change information can be obtained through decomposing and reconstruction of the vibrational signals of the electrical machine, and extracting the features of vibrational signals of the electrical machine. The extracted features are inputted into ART2 neural network to diagnose the type of the fault. Then the method is simulated, the simulation results prove that the diagnosis is feasible.
出处
《计算机测量与控制》
CSCD
2004年第3期231-233,共3页
Computer Measurement &Control
基金
国家高技术研究发展计划(863)经费资助项目(2001AA411230)
