摘要
针对柴油机振动信号的非平稳特性和在现实条件下难以获取大量故障样本的实际情况,提出一种经验模态分解(Empirical Mode Decomposition,EMD)、自回归(Auto Regression,AR)模型和支持向量机(Support Vector Machine,SVM)相结合的柴油机故障诊断方法。运用经验模态分解方法对柴油机失火及气阀机构不同工况下的缸盖振动信号进行分析,计算各个内禀模态函数(Intrinsic ModeFunctions,IMF)的AR模型参数向量以此组成初始特征向量矩阵,再计算此初始特征向量矩阵的奇异值,并将其作为支持向量机的输入特征向量以判断柴油机的工作状态和故障类型。试验结果表明:该方法在小样本情况下也具有较高的精度和较强的泛化能力。
According to the non-stationarity characteristics of the vibration signals from the diesel engine with fault and the situation that it＇s hard to obtain enough fualt samples,a diesel engine fault diagnosis method based on Empirical Mode Decomposition（EMD）,Auto Regression（AR）and Support Sector Machine（SVM）is proposed.Firstly,the vibration signals of three air valve clearances and the vibration signals under the misfire condition are decomposed into a finite number of Intrinsic Mode Functions（IMF）,then the Auto Regressive（AR）model of eachIMFcomponents are established.The auto-regressive parameters and the variance of remnant are regared as the initial feature vector matrixes.Thirdly,by applying the singular value decomposition technique to the initial feature vector matrixes,the singular values are obtained.Finally,the values serve as the fault characteristic vectors to be input to SVM classifier and the working condition and faults of the diesel engine are classified.The results show that this method have high accuracy and good generalization even in the case of small number of samples.
出处
《机械设计与制造》
北大核心
2011年第4期230-232,共3页
Machinery Design & Manufacture
