Acceleration-based spindle monitoring based on geometric error motions

The development of intelligent machine tools requires integrating sensors that allow the machine to monitor, diagnose, and control the machining process. However, existing sensors for monitoring tool vibrations are intrusive and difficult to integrate in a production machining system. This paper describes how spindle-mounted accelerometers can be used to model spindle-speed dependent error motions in situ . It extends on previous work by applying a geometric model for interpreting tool holder displacements and spindle error motions from the motion of a laser that is coaxially mounted in a tool holder, providing an accurate and interpretable basis for training models that output geometric error motions via acceleration inputs. Trained data-driven models show the potential for use of spindle-mounted accelerometers to accurately estimate geometric error motions, even during spindle rotation with radial loads.