Summary

Reducing both raw materials and processing costs — such as curing times and temperatures — remains a key challenge across material classes. For polyurethane (PU) foams, this challenge is compounded by the need to maintain critical mechanical properties and meet stringent flammability regulations. In this webinar, we walk through a case study demonstrating how AI simultaneously optimizes for cost, mechanical performance, and flame retardancy in PU foams by integrating domain knowledge with AI-driven experimentation.

We also talk about a successful project where Huntsman Building Solutions used the Citrine Platform to predict performance in large-scale fire tests, significantly reducing development time frames.

Finally, we conclude with practical guidance on how to accelerate early wins in AI materials projects.

• Product development leaders who want to derisk qualification tests
• Product developers keen to understand how AI can help them understand their chemistry better
• Business leaders who need to cut ingredient costs without harming product performance