A paper entitled “multi-task learning for data-efficient spatiotemporal modeling of tool surface progression in ultrasonic welding” is recently published in the Journal of Manufacturing Systems. The paper was co-authored by Haotian Chen, Yuhang Yang, and Chenhui Shao.
This paper developed a multi-task learning method to enable data-efficient spatiotemporal modeling. The method was evaluated using tool surface measurement data collected from ultrasonic metal welding and superior modeling accuracy, robustness, and efficiency were demonstrated. See the full paper here.