【摘要】 针对旋转机械振动的监测与诊断 ,提出了一种分级自适应的多传感器数据融合方法 .每个测点首先进行传感器级的时间跨度的特征融合 ,然后再进行全局的空间跨度的融合 .融合过程基于自适应模式特征提取 ,提出的方法可以在系统状态未知的情况下 ,自适应地融合不同测点的信息 ,从而较全面、准确、及时地反映系统的振动状态 .对转子试验台上模拟故障数据的融合处理 ,说明了所提出方法的有效性 .更多还原

【Abstract】 A two stage adapting multisensor data fusion is proposed for vibration monitoring and diagnosis of rotating machinery. The feature data from each sensor are preliminarily fused over an extended time period. Then the results are fed into overall fusion center, in which the final fusion is performed spatially. Because the process is based on adapting pattern clustering, the various information sources can be fused adaptively in the situation where priori knowledge is unavailable. The fusion output can give all round, exact and timely description of vibration conditions. The proposing approach is validated by fusing data from a simulative fault on rotor test bed.更多还原