<p>This poster presents a new approach that accurately predicts machining cycle time using machine learning. The machine’s complex motion behavior to generate trajectory from given waypoints causes nonnegligible gaps between nominal and actual cycle time. The proposed approach aims to predict cycle-time in consideration of such acceleration/deceleration behavior by combining a jerk-limited feedrate planner (JLFP) and artificial neural networks (ANNs). For JLFP, corner feedrate and kinematic limits are key parameters to estimate cycle-time. Hence, it first identifies these parameters from recorded kinematic profiles. Then, the identified parameters are provided to ANNs for learning in a self-supervised manner. Based on training, ANNs predict parameters from given geometric information to generate kinematic profiles by JLFP. Experimental results show the accurate cycle-time prediction by the proposed framework.</p>

Machining Cycle-Time Prediction by Machine Learning of Cnc Interpolator Dynamics

Paper Proceedings: https://asmedigitalcollection.asme.org/MSEC/MSEC2021/volume/85062

2021 International Manufacturing Science and Engineering Conference (MSEC2021)

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.