基于CEEMDAN-SVM的高铁轴承故障诊断研究

Research on Bearing Fault Diagnosis of High-speed Railway Based on CEEMDAN-SVM

高铁轴承在高铁运行中起着重要作用,对其进行状态检测和故障诊断有着十分重要的作用和意义。总结出一种基于自适应辅助噪声的完备集合经验模态分解(CEEMDAN)和样本熵(SampEn)相结合的高铁轴承故障诊断方法。振动信号经过分解获得诸多的本征模态分量(IMF),计算其样本熵特征参数来表征不同故障状态下的轴承信号的相关特征,并构造相应的训练和测试样本数据,而后将样本数据录入支持向量机(SVM)并配合灰狼优化算法(GWO)进行训练和测试,完成轴承故障的分类和识别。实验结果表明,此方法能够有效区分不同故障状态下的轴承振动信号。

High speed rail bearing plays an important part in the operation of high-speed railway,so it is very important to carry out state detection and fault diagnosis.In this paper,a bearing fault diagnosis method based on complete ensemble empirical mode decomposition with adaptive noise(CEEMDAN)and Sample Entropy(SampEn)has been proposed.The vibration signal is decomposed into many intrinsic mode functions(IMF),the Sample Entropy parameters are calculated to represent the relevant characteristics of different signals,and the corresponding train and test data samples are constructed.After that,the data samples are input into support vector machine(SVM)and trained and tested with gray wolf optimization algorithm(GWO)to complete the classification and identification of bearing faults.The results show that this method can effectively distinguish the bearing vibration signals under different fault states.