Modeling Aircraft Wing Loads from Flight Data Using Neural Networks

Neural networks were used to model wing bending-moment loads, torsion loads, and control surfacehinge-moments of the Active Aeroelastic Wing (AAW) aircraft. Accurate loads models are required forthe development of control laws designed to increase roll performance through wing twist while notexceeding load limits. Inputs to the model include aircraft rates, accelerations, and control surfacepositions. Neural networks were chosen to model aircraft loads because they can account foruncharacterized nonlinear effects while retaining the capability to generalize. The accuracy of the neuralnetwork models was improved by first developing linear loads models to use as starting points fornetwork training. Neural networks were then trained with flight data for rolls, loaded reversals,wind-up-turns, and individual control surface doublets for load excitation. Generalization was improvedby using gain weighting and early stopping. Results are presented for neural network loads models offour wing loads and four control surface hinge moments at Mach 0.90 and an altitude of 15,000 ft. Anaverage model prediction error reduction of 18.6 percent was calculated for the neural network modelswhen compared to the linear models. This paper documents the input data conditioning, input parameterselection, structure, training, and validation of the neural network models.