基于CCA和SOFM的轴承故障特征提取

Fault Feature Extraction of Bearings Based on CCA and SOFM

提出曲元分析(CCA)和自组织特征映射(SOFM)相结合的方法用于轴承的故障诊断特征提取.首先通过传感器测得轴承在正常和非正常状态下的信号;然后对所得数据进行归一化;考虑到数据比较庞大,利用CCA进行降维;再利用SOFM进行训练,网络对不同状态下的输入具有明显不同的输出.利用Matlab神经网络工具箱来实现上述算法.实例仿真表明,这个算法可以快速正确地提取出轴承故障特征值,并通过聚类算法完成轴承的故障诊断.

The combination of curvilinear component analysis （CCA） and self-organizing feature map （SOFM） were applied to a diagnosis for fault feature extraction of bearing. Firstly regularizing the input signal of the bearing＇s normal and abnormal states obtained from sensors; and secondly dimension-reducing the data with CCA considering its hugeness; finally training it with SOFM, the networks have different output maps for different input states. The above method was implemented by the neural network toolbox in Matlab. The simulation results show that it can be used to extract fault features of bearing quickly and exactly and completed the inspecting of bearing by clustering analysis.