Feeling machines: Prediction of thin-walled workpiece deflection by monitoring variations in tool bending moment pattern during circumferential milling

In circumferential milling, the in-process deflection of thin-walled workpieces induced by feed normal forces results in reduced material removal, leading to geometric errors after machining. With the increasing use of additive manufacturing technologies and the production of near-net-shape structures, this problem is gaining increasing importance. Various strategies attempt to compensate for this geometric errors, for example by modeling the occurring cutting forces and workpiece deflection and then applying countermeasures during machining. However, this requires a high level of process understanding, and multiple parameters need to be considered, including material properties, cutting edge geometry as well as wear state of the tool. This paper examines a novel approach to predict workpiece deflection state by analyzing the bending moment pattern measured by an in-process sensor system located in the tool holder. It could be demonstrated that features extracted and evaluated from the bending moment signal can represent the current deflection state of the workpiece in an offline approach, enabling future in-situ toolpath adaptation to reduce geometric errors without relying on time-consuming simulation of the workpiece stiffness and with minimal signal processing effort.