基于经验模态分解和支持向量机的滚动轴承故障诊断
Rolling bearing fault diagnosis based on empirical mode decomposition and support vector machine

本文针对滚动轴承的故障诊断问题，首先提出一种自适应波形匹配的延拓方法对经验模态分解(Empirical Mode Decomposition, EMD)存在的端点效应进行改进，然后基于改进的EMD和粒子群优化算法(Particle Swarm Optimization, PSO)优化的支持向量机(Support Vector Machine, SVM)设计了一种两阶段的滚动轴承故障诊断方法。离线阶段对典型的正常、故障振动信号进行EMD分解并提取能量信息作为特征，送入PSO-SVM进行训练并保存模型待用，在线阶段对实时的振动信号进行EMD分解并提取特征，利用离线阶段训练好的模型进行诊断并输出诊断结果。使用美国西储大学轴承数据对该方法进行了验证，实验结果证明了该方法的有效性。
In this paper, an adaptive waveform matching method is proposed to improve the end effect of empirical mode decomposition(EMD). Then a two-phase fault diagnosis method for rolling bearing is presented based on improved EMD(IEMD) and Particle Swarm Optimization (PSO) optimized support vector machine (Support Vector Machine, SVM). In the offline phase, the typical normal and fault vibration signals are decomposed by IEMD and energy information is extracted as the feature. A PSO-SVM model is trained and saved as diagnostic model. In the online phase, the real-time vibration signal is decomposed by IEMD and the feature is extracted. The model trained in offline phase executes diagnostic process and output the diagnosis results. The method is verified using Case Western bearing datasets. The experimental results show the effectiveness of the method in fault diagnosis of rolling bearing