Prediction and compensation of force-induced deformation for a dual-machine-based riveting system using FEM and neural network

Abstract

Force-induced deformation of machine tools has a great influence on the workpiece dimension and surface quality. For the dual-machine-based riveting system, the great squeezing force during riveting process not only causes structural deformation of the machine tools but also leads to inaccurate positioning of the riveting bar and dimension deviation of riveted joints. Moreover, the force-induced deformation usually changes with the varying poses of the machine tools, which makes it more difficult to predict precisely. In this paper, an efficient prediction and compensation method of force-induced deformation is developed based on finite element modeling (FEM) and artificial neural network. Firstly, a series of finite element models at selected poses are established to obtain the deformation data. Then, a force-induced deformation prediction model is established through radial basis function neural network with adaptive genetic algorithm optimization (AGA-RBF). Furthermore, a basic strategy is proposed to compensate for the predicted error through the motion commands modification. Finally, a contrast experiment is carried out to verify the feasibility and efficiency of the proposed method.