基于神经网络的信息融合故障诊断技术

Fault Diagnosis Technology Based on Neural Network Multisensor Data Fusion

利用神经网络技术建立信息融合中心 ,对多传感器数据进行融合处理 ,通过多源互补信息减小故障诊断系统的不确定性。文中讨论了神经网络多传感器信息融合方法中数据预处理与特征提取、特征向量维数压缩与关联、归一化处理方法等 ,同时 ,对神经网络的构造以及学习训练等内容 ,也作了较为详细的讨论。通过对柴油机振动监测数据、燃油压力波动信息、以及两者融合信息的故障诊断性能的比较 。

This paper deals with a multisensor system applied to mechanical fault diagnosis. By using the information fusion pattern based on neural network, the uncertainty of the diagnosis system can be decreased greatly. The methods for data preprocessing, features extraction and construction of the neural network are discussed. The approach is shown to be practical and effective through diagnosing the faults in the fuel injection system of a diesel engine.