A cutting-edge solution leveraging surrogate model accelerated finite-element solvers to optimize packaging design processes, reduce costs, and enhance recyclability by integrating machine learning and computer graphics.
The solution utilizes surrogate model accelerated finite-element (FE) solvers to revolutionize commercial packaging design. By integrating advanced machine learning techniques and computer graphics, such as Neural Operators and B-Splines, this approach enhances traditional FE solvers. It accelerates the design process, reduces design-to-shelf costs, and improves packaging integrity and recyclability. This technology is particularly beneficial in generating synthetic datasets and automating mesh generation, thereby significantly reducing the need for costly real-world validation studies.
Key features:
This technology is currently at Technology Readiness Level 6, indicating that it has been demonstrated in a relevant environment. Future validation plans focus on specification, data acquisition, model development, and testing to further refine the solution for commercial deployment.
The Ohio State University is a comprehensive public land‑grant research university in Columbus, serving one of the nation’s largest student populations and a broad research enterprise. Industry partners engage through an integrated academic medical center for clinical translation, a campus‑adjacent innovation district for co‑located projects, and a statewide extension network that pilots solutions across Ohio. Corporate engagement provides a single front door for sponsored research, talent pipelines, and streamlined agreements. Research is supported by competitive federal funding from agencies such as NIH, NSF, DOE, USDA, DoD, and NASA. A dedicated technology transfer office and venture support help protect IP, license technologies, and launch startups.