基于GARCH模型MSVM的轴承故障诊断方法

Bearing fault diagnosis with a MSVM based on a garch model

针对振动信号因非平稳性导致自回归(AR)模型无法有效描述信号特征的不足,提出一种基于广义自回归条件异方差(GARCH)模型多类支持向量机(MSVM)的故障诊断方法。该方法首先利用GARCH模型拟合各种故障信号,将所得模型参数作为故障诊断特征,以MSVM作为故障诊断方法。试验结果验证了GARCH模型方法的可行性和有效性,同时将该方法同基于AR模型的方法及其改进方法进行比较,结果表明该方法在诊断率及诊断时间上都有明显提高。

In bearing fault detection application,to solve the problems of difficultly describing signal characteristics using auto-regressive(AR) models due to the signal's non-stationary characteristics,a novel one-class diagnosis model using a multi-class support vector machines(MSVM) based on a generalized autoregressive conditional heteroscedasticity(GARCH) model was presented here.The GARCH model was employed to describe different bearing vibration signals,the parameters of the generated different models was used as the signal' diagnosis characteristics and consequently the classifier based on MSVM was established.The experiments showed that the proposed approach can efficiently overcome the drawback of the conventional methods based on the AR parameters.The proposed diagnosis scheme was compared with the conventional methods based on the AR model's parameters and the other modified methods based on AR model.The results illustrated the effectiveness of the investigated techniques and conclusions in terms of diagnosis time and diagnosis rate.