基于小波神经网络的轴承未知异常诊断

针对滚动轴承振动信号复杂,故障类型难以预知的问题,提出基于小波-神经网络技术的滚动轴承未知异常诊断的新方法.利用小波包对滚动轴承振动信号进行分解与重构,获得振动信号的突变信息,提取与滚动轴承故障相关的特征信息,将其作为特征向量输入自组织特征映射(Self-Organizing Feature Maps,SOFM)神经网络,对其进行自动分类识别,根据数据映射位置,可实现对滚动轴承未知异常的诊断,并为专家系统知识的自动获取提供了一条新途径.通过对仿真结果的分析,证实这种诊断方法的可行性.

Unknown Exception Diagnosisof Bearing Based on Wavelet Neural Network

According to the questions that vibration signal is complex and fault mode foreknew is difficult,a novel method of unknown exception diagnosis in rolling bearing based on the wavelet neural network is proposed.Based on the advantage of multi-dimensional multi-scaling decomposition of wavelet packets,the abrupt change information can be obtained and the features related to the fault of roll bearing is extracted through the decomposing and reconstruction of the vibration sign of the roll bearing.The extract features are inputted into self-organizing feature map(SOFM) to realize the automatic classification of the fault.The trained SOFM can be used to the unknown exception diagnosis of roll bearing and automatic knowledge acquisition of expert system.The feasibility of this novel method is proved by the simulation results.