论文部分内容阅读
提出了基于AR模型和支持向量机的转子系统故障诊断方法.该方法对转子系统的振动信号建立AR模型,以AR模型主要的自回归参数和残差的方差作为特征向量,然后建立支持向量机分类器,进而判断转子系统的工作状态和故障类型.实验结果分析表明,该方法能有效地应用于转子系统的故障诊断.并通过支持向量机与BP神经网络的性能比较,说明了支持向量机的优点.
A rotor system fault diagnosis method based on AR model and support vector machine is proposed.The AR model is established for the vibration signal of the rotor system and the main autoregressive parameters and variance of the residuals of the AR model are taken as eigenvectors and then a support vector machine Classifier to judge the working status and fault types of the rotor system.Experimental results show that this method can be effectively applied to the fault diagnosis of the rotor system.By comparing the performance of support vector machine and BP neural network, The advantages.