The load prediction based on the data used in aircraft plays an important role in the damage analysis and life prediction of aircraft, which can provide technical support for the active on-condition maintenance of aircraft. In this paper, forward neural network is used to establish the load model of shear force, bending moment and torque of the tail wing root of a large transport aircraft. Compared with the load calculated by finite element model, the prediction errors of the neural network model meet the engineering requirements, and compared with the prediction results of the multivariate linear regression model, the results show that the prediction accuracy of the neural network model is better than that of the multivariate linear regression model. The neural network model provides a feasible method for measuring the loads on key structures of a large transport aircraft.