特征级融合模块采用RBF神经网络，其功能是提取数据特征进而特征信息融合。
The feature level module adopts RBF neural network to extract feature of data and to make feature fusion.
数据级融合模块主要对多传感器的测量信号进行处理，提取出故障诊断的特征信息。
The data fusion level module mainly handles the metrical data of multi-sensors and extracts the feature of faults.
也可以根据信息抽象程度的不同，从低到高分为像素级、特征级和决策级融合三个层次。
According to the different abstract extent of information, from low to high, it can also be divided into three levels: pixel-level, feature-level and decision-making level.
应用推荐