摘要
针对驱动桥异响检测缺乏故障样本的问题,提出了异响检测的单值分类法———支持向量数据描述法(SVDD)。这种方法只需要正常运行状态的数据样本,就可以建立单值分类器,区分出正常和异常状态。试验中,提取驱动桥振动信号频谱的二维谱熵作为特征指标,输入到SVDD分类器。结果表明SVDD算法计算效率高,分类效果好,可以满足在线检测的要求。
in view of the lack of fault samples, the technique of one-class classification-support vector data description （SVDD） is adopted for abnormal sound detection, in which the normal and abnormal conditions can be distinguished by one-class classifier, set up only on the base of samples in normal conditions. In the test on driving axle, the 2D spectrum entropy of vibration signals is extracted as the feature indicator and is input into the SVDD classifier. The test result shows that the SVDD algorithm has high computing efficiency and good effects of classification, meeting the requirements of online detection.
出处
《汽车工程》
EI
CSCD
北大核心
2006年第2期203-206,175,共5页
Automotive Engineering
