Intelligent Health Diagnosis Method for Aircraft Based on Multi-Source Information Fusion

In order to diagnose the health status of aircraft effectively, a health diagnosis method based on D-S evidence theory is proposed. Firstly, this method apperceives the healthy information of a real aircraft stabilizer with real time by using AE(Acoustic Emission, AE) detecting system. Secondly, use the wavelet transform to extract feature of the AE signal, including three characteristics of maximum value (MA), singular value (SVD), standard deviation (STD) to set up characteristic vector, then using GRNN and BP neural network to classify the characteristic vector. Finally, D-S evidence theory is used for decision reasoning. Therefore, The Health State of aircraft can be diagnosed. Experiments show that the monitor has good performance to recognize and diagnose the fatigue crack of aircraft structural parts, which is proposed to be effective.