Geometry-aware deep learning for custom PET container design
Innovative NURBS-aware geometric deep learning model to design custom PET containers by predicting container shapes from preform designs and vice versa.
Overview
This solution leverages advanced geometric deep learning techniques to design custom PET containers. By utilizing a NURBS-aware model, the technology predicts the final container shape based on a given preform design and develops a generative model to determine preform shapes for desired container designs. This approach enhances the flexibility and precision in PET container design, potentially transforming manufacturing processes in packaging industries.
Technical specifications
Key features:
- Utilizes Non-uniform Rational B-Splines (NURBS) for accurate geometry representation in CAD software.
- Forward model predicts container shapes from preform designs using geometric deep learning.
- Inverse generative model determines preform designs for desired container shapes.
- Integrates CAD geometry with AI tools for improved design precision and customization.
- Comprehensive MLOps setup for continuous integration and monitoring.
Technology readiness level
The technology is currently at TRL 4, indicating that it has been validated in a laboratory setting. Future steps include data collection, model tuning, deployment, and continuous testing to advance towards commercial deployment.
About Iowa State University
Iowa State University is a large, comprehensive public land‑grant research university based in Ames, known for combining fundamental discovery with translational, industry‑relevant work. Companies collaborate through a research and technology park that co‑locates corporate R&D with faculty labs and startups, creating steady talent pipelines. Pilot‑scale facilities, field test sites, and a statewide extension network support prototyping, validation, and deployment with partners across the region. Research is supported by competitive federal funding, including awards from NSF, USDA, and DOE. A dedicated technology transfer office and affiliated research foundation streamline IP, licensing, and startup formation, with incubator space on site.
delivered to your inbox.