Digital twin of forged part to reduce distortion in machining

Abstract

When long parts are machined in forged blanks, the variability of bulk residual stress (RS) fields leads to uncontrolled deformation after machining, requiring manual reshaping. An original hybrid digital twin of forged part is thus proposed to manage the bulk RS variability and reduce part distortion in machining. The behavior model of parts relies both on reduced models of thermomechanical simulations of the forging process variability, on-line measurements and machine learning from the previous parts deformations. Adaptive machining solutions can then be simulated for a rapid decision-making. The approach was validated on a series of aeronautic forged parts.