NEURAL-NETWORK MODELING OF OSCILLATORY LOADS AND FATIGUE DAMAGE ESTIMATION OF HELICOPTER COMPONENTS

A neural network for the prediction of oscillatory loads used for on-l ine health monitoring of flight critical components in an AH-64A helic opter is described. The neural network is used to demonstrate the pote ntial for estimating loads in the rotor system from fixed-system infor mation. Estimates of the range of the pitch link load are determined b y the neural network from roll, pitch, and yaw rates, airspeed, and ot her fixed-system information measured by the flight control computer o n the helicopter. The predicted load range is then used to estimate fa tigue damage to the pitch link. Actual flight loads data from an AH-64 A helicopter are used to demonstrate the process. The predicted load r anges agree well with measured values for both training and test data. A linear model is also used to predict the load ranges, and its accur acy is noticeably worse than that of the neural network, especially at higher load values that cause fatigue damage. This demonstrates the n ecessity of the non-linear modelling capabilities of the neural networ k for this problem. (C) 1998 Academic Press Limited.