Health Diagnosis for Aircraft Based on EMD and Neural Network

To effectively diagnose the aircraft structure components fatigue damages, a new kind of health diagnosis approach for the aircraft, based on experience modal decomposition (EMD) and probabilistic neural network (PNN), is proposed in this paper. The advanced acoustic emission (AE) technique is used to monitor the aircraft stabilizer health state and get the AE information. And the AE information from the aircraft stabilizer is decomposed into the limited inherent modality function (IMF) by the EMD, which is quite fit for dealing with the non-linear and non-steady signal. The IMF energy is extracted to construct the eigenvectors. Then the health status of the aircraft can be diagnosed with the eigenvectors by PNN health monitor. Experiments show that this method can effectively monitor the fatigue crack of the aircraft stabilizer. It presents a new approach to diagnose effectively health state of aircraft structure components.