Project Details
Automation and autonomy can enable revolutionary scientific advances by coordinating a diverse array of experimental and computational capabilities more efficiently and more effectively than current hands-on approaches. We propose an INTERSECT Self-Driven Processes, Experiments, Laboratories (SPEL) project to create an autonomous system to plan and adaptively control additive manufacturing (AM) build processes. Because it involves multiple characterization modes, computation across the edge-to-core spectrum, and multiple ORNL user facilities, this project is well suited for co-development of the INTERSECT ecosystem. The objective of the autonomous AM system is to control the residual stress in a part to address a grand challenge laid out in a recent Basic Research Needs report – building parts that are ready and safe to use immediately (“born qualified”). Together with the INTERSECT cross-cut projects we will develop new distributed microservices to enable secure, automated, time-sensitive interactions between experimental and computational components. Using these microservices, we will demonstrate a new method for autonomous AM control. This method combines in-situ observations and thermomechanical simulations for accurate real-time state estimation and uses thermomechanical simulations in the control loop to predict the complex, long-range effects of process parameters on part quality. This autonomous system will enable AM builds with residual stress at least two times closer to the desired distribution than current methods, drastically reducing the time to develop process parameters for new alloys and geometries. Beyond AM, the INTERSECT microservices developed in this project are a diverse set of building blocks that can be applied to automate workflows across ORNL. Additional project in other areas (manufacturing, building equipment, renewable energy generation, energy storage, and electric grid etc.) will be identified through the ongoing open DRD calls.
