本文提出了一种新颖的基于Boosting模糊分类的滚动轴承故障诊断方法。利用小波包对滚动轴承的振动加速度信号进行分解,得到滚动轴承动态信号在不同频带的能量,并以此作为滚动轴承的特征向量,采用模糊分类方法进行故障诊断。该方法利用Boosting方法和遗传算法以迭代形式获取一组模糊规则及规则对应的权值,分类器以加权投票方式进行分类决策。对7类滚动轴承进行了实验,结果表明该方法具有很好的故障诊断效果。 In this paper, a novel fault diagnosis method of rolling bearing based on Boosting fuzzy classification is proposed. The wavelet packet is used to decompose the vibration acceleration signal of the rolling bearing to obtain the energy of dynamic signal of rolling bearing in different frequency bands and use it as the eigenvector of rolling bearing to diagnose the fault with fuzzy classification method. The method uses Boosting method and genetic algorithm to iteratively obtain a set of fuzzy rules and the corresponding weights of the rules. The classifier uses the weighted voting method to make classification decisions. Experiments on seven kinds of rolling bearings show that the method has a good fault diagnosis effect.