基于EEMD和PSO-SVM的滚动轴承故障诊断

发布时间：2018-01-13 15:04

本文关键词：基于EEMD和PSO-SVM的滚动轴承故障诊断　出处：《电力科学与工程》2016年10期 　论文类型：期刊论文

【摘要】：为实现滚动轴承故障的精确诊断,提出一种基于集成经验模态分解与粒子群算法优化的支持向量机的故障诊断方法。利用EEMD方法分解振动信号,依据经验选取合适的内禀模态函数进行能量值及包络谱特征幅值比等故障特征参量的计算,构建滚动轴承故障特征向量,然后基于少量不同故障部位及故障程度的样本,利用粒子群算法对支持向量机进行参数优化,进而训练样本并建立故障模型,最后对测试样本进行故障诊断,观察该方法的诊断效果。实验表明,该方法可对多种不同故障状态进行诊断,且分类精度高,证明了振动分析与智能算法结合的方法可有效实现滚动轴承的故障诊断。
[Abstract]:In order to accurately diagnose the rolling bearing fault, a fault diagnosis method of support vector machine based on integrated empirical mode decomposition and particle swarm optimization is proposed. The vibration signal is decomposed by EEMD method. According to the experience, the proper intrinsic mode function is selected to calculate the fault characteristic parameters such as the energy value and the amplitude ratio of the envelope spectrum, and the fault eigenvector of the rolling bearing is constructed. Then based on a small number of samples with different fault locations and degrees of fault, the support vector machine parameters are optimized by particle swarm optimization algorithm, and then the samples are trained and fault models are established. Finally, the fault diagnosis of test samples is carried out. The experimental results show that the method can be used to diagnose many different fault states, and the classification accuracy is high. It is proved that the combination of vibration analysis and intelligent algorithm can effectively realize the fault diagnosis of rolling bearings.
【作者单位】：华北电力大学控制与计算机工程学院;
【分类号】：TH133.33
【正文快照】： 0引言滚动轴承是旋转机械设备中易受损的部件之一,它的寿命随机性大,失效时产生的振动和噪声会直接影响到机械设备的正常工作,使机械运行状态变差,快速定位轴承故障能缩短维修时间,提高机组的经济效益。随着机械设备逐渐向高速化、大型化和自动化方向发展,对滚动轴承的故障进

【相似文献】