摘要
在D -S证据理论的基础上 ,针对动力机械复合振动识别中在同一征兆域中很难区分多种振动故障的实际状况 ,研究利用其他征兆域的识别信息 ,进行全局信息融合 ,从而达到较为准确的振动故障定位 ;系统地论述了基于证据理论和神经网络的多参数体系识别的数据融合方法 ,在该方法中采用证据理论的组合规则进行局部和全局信息融合 ,结果表明D -S证据理论能有效地识别动力机械复合振动特征 ;
A model of multi-parameter comprehensive recognition system based on D-S evidential theory and neural networks was proposed with respect to the facts that it was difficult to distinguish different faults from one symptom domain during the compound vibration recognition process of a drive machine. More correct diagnosis results can be obtained by fusing part or full range information adopting the combining rules of evidence theory. The results show that the characteristics of compound vibration of a drive machine are diagnosed effectively through D-S evidential theory. At last, an identification example is given.
出处
《中国机械工程》
EI
CAS
CSCD
北大核心
2004年第18期1610-1613,共4页
China Mechanical Engineering
关键词
D—S证据理论
复合振动
信息融合
振动识别
D-S evidential theory
compound vibration
data fusion
vibration recognition