| Abstract Scope |
Current research efforts at my manufacturing group aim to advance the capability to co-design materials and manufacturing processes using hybrid physics-based and data-driven approaches. In this talk, I will share my journey in metal additive manufacturing research and thoughts on future directions. Specifically, I will demonstrate how integrating process simulations, sensing, process control, and techniques including machine learning can achieve effective and efficient predictions of a material’s mechanical behavior. Furthermore, I will show how we use machine learning for active sensing with the goal of effective in-situ local process control. Our solutions particularly target three notoriously challenging aspects of the process, i.e., long history-dependent properties, complex geometric features, and the high dimensionality of their design space. |