Health Forecast for Aircraft Based on Adaptive MVGFM

A new kind of health state forecast method for the aircraft, based on the adaptive multi-variable grey forecast model (MVGFM), is presented in this paper. The advanced acoustic emission (AE) technique is used to monitor the aircraft stabilizer health state and get the AE information. The original AE signals are decomposed with the wavelet transform, and the maximum of absolute value (MAV), average of absolute value (AAV), standard deviation (SD) and singular value (SV) of the fourth layer wavelet decomposition coefficients are respectively extracted to form eigenvectors. Then the adaptive MVGFM(1,n,beta) is established with the eigenvectors. The parameter beta can be rectified by the errors between the forecast values and the actual ones. So the forecast precision can be adaptively improved. Experiments show that the MVGFM(1,n,beta) can forecast the aircraft stabilizer fatigue crack more accurately than the MGM(1,n). It presents a new method for forecasting the health state of aircraft structure components. And the health forecast method is also applied in other complicated structure systems.