基于独立特征选择与相关向量机的变载荷轴承故障诊断

Bearing fault diagnsis under varying load conditions based on individual feature selection and relevance vector machine

在线状态监控与故障诊断具有很大的经济与安全意义,提出了一种基于独立特征选择(IFS)与相关向量机(RVM)的智能故障诊断模型用于变载荷条件下识别多类轴承故障及其故障程度。首先混合空载(0hp)与满载(3hp)两种载荷状态下的实验数据作为训练样本;其次提取时域统计特征与全小波包域节点能量特征作为候选特征;接着采用一种改进的Fisher特征选择方法为每两类故障状态独立选择具有最大分类能力的最优特征子集;然后用"一对一"的方法训练多个RVM二类子分类器;最后采用"最大概率赢"的策略组合所有子分类器构成IFS_RVM多类故障诊断模型。用未知载荷(1hp,2hp)下的实验数据验证了模型的有效性,得到99.58%的极高诊断精度,实验结果表明,该模型精度高、鲁棒性强,满足变载荷条件下在线故障诊断的需要。

The proposed procedure for bearing fault diagnosis under varying load conditions is as follows.Vibration data measured under no-load（0hp） and full-load（3hp） were combined to be used for training.Statistical characteristics in time domain and node energies in full wavelet packet domain were extracted as candidate features.An improved Fisher feature selection method was proposed and used to select individual best feature subset for each pair of classes.By using one-against-one（OAO） approach,several RVM binary classifiers were trained for each pair of classes.The IFS-RVM multi-class fault diagnosis model was constructed by combining all RVM binary classifiers and using max-probability-win（MPW） strategy.Vibration data measured under untrained load conditions（1hp and 2hp） were used for testing,which results in very high accuracy of 99.58%.Experimental results demonstrate that the proposed model is very effective and robust for online fault diagnosis under varying load conditions.