基于主成分分析和支持向量机的滚动轴承故障特征融合分析

为有效降低滚动轴承故障特征的维数并提高诊断准确率，将主成分分析（PCA）和支持向量机（SVM）方法应用到轴承故障特征的融合分析中，给出了相应的决策流程。应用基于小波包分解的特征提取算法及特征向量的构造方法对不同状态下的振动信号进行分解，得到用于表征轴承运行状态的8维特征集合；应用PCA提取累积贡献率达到95%的特征主成分并输入SVM分类器中进行识别。结果表明，将滚动轴承故障特征从8维降低到5维，仍可有效表征轴承的状态，但大大降低了计算的复杂性；故障诊断的准确率达到97%以上，诊断时间也相对较短；4种轴承状态识别的准确率从高到低依次为正常、外圈剥落、滚动体剥落和内圈剥落，可为确保设备安全运行和快速故障诊断提供理论依据。

Rolling Bearing Fault Feature Fusion Based on PCA and SVM

To  effectively  reduce the dimension of rolling bearing fault features  and improve the accuracy of diagnosis,the PCA and SVM were applied in the fusion of bearing  fault features,and the corresponding decision-making process was presented.By using the fault feature extraction algorithm and eigenvector constructing methods which were proposed based on wavelet packet decomposition, the  bearing  vibration signals  in different states  were  decomposed to get the 8-dimensional  feature sets  which could be used to characterize the running conditions   of   the bearing.The cumulative contribution rate of  95%   principal  components were extracted by using  PCA  method and were input into SVM  classifier for identification.Results show that the fault feature dimensions  of  rolling bearing can be reduced from  8-dimensions to 5-dimensions,which can still characterize the bearing status effectively,and the computational  complexity  can   be  reduced.The fault diagnosis accuracy is higher than 97%,and the diagnosis time is short  relatively.The identification accuracy of four bearing status from high to low in turn is normal, outer ring peel, roller peel and inner ring peel.It can ensure the safe operation of  the equipment and provide theoretical basis for fast  fault diagnosis.