支持向量数据描述(support vector data description,SVDD)是一种单值分类方法,该方法能够在缺少故障样本的情况下,通过采集到的正常状态数据样本建立起单值分类器,从而区分出机器的运行状态。笔者提出了一种小波变换支持向量数据描述诊断方法,利用正交小波变换(orthogonal wavelet transformation,OWT)方法提取各细节信号的峰峰值作为输入参数,用SVDD方法进行分类。通过滚动轴承的试验数据分类结果显示,该方法比没有提取特征值的SVDD可有效处理复杂机械振动信号,提高了诊断的准确率。
Support vector data description (SVDD) is a kind of one-class classification method. It can build a classifier with collected samples of the normal state data in the shortage of fault samples, and then distinguish the oper- ation of state machine. A machine diagnosis method which uses orthogonal wavelet transform (OWT) technology to extract the details of the peak-to-peak signal as the input parameters of SVDD and use support vector data descrip- tion in classification is presented and then the method is applied to rolling bearing fault diagnosis. The test result shows that this method is superior to traditional SVDD method in dealing with complex machinery vibration signals and it also can identify rolling bearing fault patterns more effectively.