【摘要】 传统旋转机械故障诊断用单通道信号进行诊断,信息量不完整,容易导致误诊;而矢谱融合了多通道的信息,反映的信息更全面。支持向量数据描述是一种单值分类方法,该方法有望解决机械故障诊断中缺少故障样本的问题。基于此,提出矢谱和支持向量数据描述的故障诊断方法,用矢谱作为特征向量,支持向量数据描述方法为分类器,并应用到旋转机械故障诊断中。实验结果表明,该方法是有效的。更多还原

【Abstract】 Traditional rotary machinery fault diagnosis with single channel signal frequentlyresults in faulty judgement.The vector spectrum can fuse the information from different channels,and reflect more comprehensive information.Support vector data description is one class classification method,which can be applied to solve the problem of shortage of fault data in machinery diagnosis. A machinery diagnosis method was proposed, in which vector spectrum was used as feature extraction and support vector data description was used as a classifier. The method was applied to the fault diagnosis of rotary machinery. The experimental result shows that the proposed method is very effective.更多还原