信息融合在飞行器智能健康诊断中的应用

提出了一种基于经验模态分析(Empirical mode decomposition,EMD)和D-S证据相结合的飞行器健康诊断方法.该方法首先对由声发射传感器募集到的飞行器关键结构部件原始声发射信号进行EMD,得到多个内禀模态分量,选取内禀模态能量构建声发射信号的特征向量,并分别采用模糊神经网络、GRNN网络和Elman神经网络对提取出的特征向量进行分类,最后运用D-S证据理论进行决策融合,对飞行器的健康状态进行诊断.实验表明,运用此方法对某型号真实飞行器关键结构部件的健康状态进行诊断,可以得到很好放入诊断结果.与单分类器相比,采用D-S证据理论进行决策融合有效地提高了故障诊断的精度.

Application of Information Fusion in Aircraft Intelligent Health Diagnosis

To effectively diagnose aircraft health states,a new method based on empirical mode decomposition(EMD) and Dempster-Shafer(D-S) evidence theory is proposed.Original acoustic emission(AE) signals of aircraft structural components(stabilizer) are firstly decomposed into several intrinsic mode functions(IMFs) using EMD.The IMFs are used to construct the feature vectors of AE signal.Then,the fuzzy neural network,generalized regression neural network(GRNN) and Elman neural network are adopted to classify these vectors,respectively.Finally,D-S evidence theory is used for decision fusion to determine the aircraft health states.Compared with methods using single classifier,the effectiveness of the proposed method is demonstrated by experimental tests on certain type of aircraft with higher health diagnosis accuracy.