基于学习矢量量化网络的智能BIT故障诊断方法

Method of Fault Diagnosis of Intelligent BIT Based on LVQ Neural Network

将一种经过修正的基于学习矢量量化算法的竞争网络应用在多电飞机电气系统智能BIT故障诊 断中,该网络在竞争层实现故障模式的自组织聚类,在输出层给出了具体的故障模式,通过与原算法进 行比较,修正后的算法达到了很好的故障识别和分类效果。

A self-organizing neural network based on the modified learning vector quantization（LVQ） which is applied in the fault diagnosis of intelligent BIT of more-electric aircraft（MEA） is studied. This neural network completes the self-organizing clustering of the faults in the competitive layer and outputs the diagnostic results in the output layer. The results show that the modified algorithm is more effective than the standard algorithm.