Knockoff-based deep learning framework for PET container design optimization
A knockoff-based deep learning framework for PET container design that automates variable selection in the two-step stretch blowmolding process. It controls false discovery rates to improve reliability of identified design parameters and reduce spurious correlations. The approach integrates predictive modeling with survival analysis and standard evaluation metrics to streamline design optimization and support manufacturing efficiency improvements.
Overview
The knockoff-based deep learning framework provides a data-driven approach to PET container design by automating the selection of critical variables in the two-step stretch blowmolding process. The method is designed to improve on conventional deep learning strategies by rigorously controlling false discovery rates, helping ensure that selected design parameters correspond to true features that influence product quality. The framework prioritizes variables with high confidence to streamline design optimization.
Technical specifications
Key features:
- Utilizes a knockoff-based deep learning approach for variable selection.
- Controls false discovery rates to reduce spurious correlations and improve reliability of identified causal features.
- Integrates advanced predictive models with industry-standard evaluation metrics and survival analysis techniques.
- Supports integration into design optimization workflows that use CAD-based representations.
Technology readiness level
This technology is currently at TRL 3, indicating it has been demonstrated analytically and experimentally in a laboratory environment. Further validation and development are planned through collaboration with industry experts.
About West Virginia University
West Virginia University is a comprehensive public land‑grant research university headquartered in Morgantown and serving the state through academics, research, and outreach. For industry, a statewide Extension network provides on‑the‑ground access to communities, facilities, and field sites, while an integrated academic medical center and health system enable clinical research and translational partnerships. The university connects corporate R&D with talent through co‑op and internship pipelines and applied engagements. Research is supported by competitive federal funding from agencies such as NIH, NSF, DOE, and USDA. WVU’s Office of Innovation and Commercialization manages IP, licensing, and startup pathways to provide a clear entry point for collaboration.
delivered to your inbox.