摘要
支持向量机是建立在结构风险最小原理[1 ] 基础上 ,专门研究小样本情况下的学习规律。本文针对滚动轴承的加速度信号和声音信号的特点 ,选取识别能力好的时域无量纲指标作为支持向量机的特征矢量 ,对滚动轴承的四种典型故障进行模式识别。结果表明 ,支持向量机在滚动轴承故障诊断中有很出色的分类能力。
Support Vector Machine represents a new approach to pattern recognition based on small dataset.It was developed from the theory of Structural Risk Minimization.Vibration and sound signals of the rolling bearing were analyzed in this paper. Some dimensionless factors were selected as the input of Support Vector Machine in order to classify four kinds of fault. The result showed SVM have a good performance in rolling bearing fault diagnosis.
出处
《机床与液压》
北大核心
2003年第4期320-322,共3页
Machine Tool & Hydraulics
