Ai-driven cycle time prediction for injection molding with PRC waste
An AI-enhanced model predicts cycle times for injection molded parts using polymer blends, focusing on PET and other resins. It leverages machine learning to optimize industrial processes, aiming to reduce cycle times through accurate predictions and adjustments.
Overview
This innovative solution integrates artificial intelligence with industrial processes to predict and optimize cycle times for injection molded parts using polymer blends. The core of this technology is a model that utilizes machine learning to predict filling and cooling times based on the rheological and thermal properties of polymers like PET and various other resins. By doing so, it aims to enhance efficiency and reduce waste in the manufacturing process.
Technical specifications
- Utilizes coupled flow and heat transfer models to predict cycle times.
- Employs machine learning algorithms trained on literature data sets and experimental data from a bench-top injection molder.
- Initial focus on polymers such as poly(styrene), poly(methyl methacrylate), poly(ethylene), and poly(propylene).
- Designed to adapt to varying polymer compositions and recycling stream inputs, providing robust predictions and optimization strategies.
Technology readiness level
The current development stage is at TRL 2, where the technology concept and application have been formulated. Validation is being pursued through experimental setups using lab-scale injection molding processes.
About McGill University
McGill University is a comprehensive public research university in Montréal, Québec, known for an international community and a research‑intensive culture. Faculty and industry collaborate through shared core facilities and co‑located labs across downtown and hospital sites, with integration into a major hospital system enabling clinical research and translation. Proximity to Montréal’s established industry clusters and a vibrant innovation district give companies access to talent, pilots, and testbeds. Research is supported by Canada’s Tri‑Agency and the Canada Foundation for Innovation, alongside provincial and philanthropic sources. A dedicated technology transfer office streamlines contracting and IP, supports licensing and sponsored research, and connects partners to startups and entrepreneurship resources.
delivered to your inbox.