Simulation and Optimization of an Aluminum Extrusion Process Using FEM and Artificial Intelligence

A non-linear, three-dim finite element model of the extrusion process has been created by using QForm software to simulate an aluminum extrusion and investigate the impact of various parameters on the extrusion process outcomes. The model has been used to examine the effects of inputs such as ram speed, billet temperature, and tool temperature on outputs including effective stress, tool and workpiece temperature, contact pressure, and power consumption. Additionally, an Artificial Neural Network (ANN) model has been developed to depict accurately the relationship between inputs and outputs of the extrusion process. The results have showed that the effective stress is highly affected by the temperature of both the workpiece and the tool, while the ram speed has a high impact on the tool temperature during the extrusion as well as on the contact pressure. This will lead to an increase in power consumption during the process and accelerate the wear on the dies.