JapanChemicals and materials2023 – ongoingSekisui Chemical
AI prediction for film-material formulation design
Sekisui Chemical shortened film-material design from 5 months to 4 hours with AI
Problem
Researchers faced shorter development deadlines and many possible material formulations. Historical experimental knowledge remained scattered among individual researchers.
Approach
Sekisui collected past experimental methods and results for AI prediction of formulation outcomes. The system helped narrow candidate combinations. Sekisui subsequently worked with Hitachi to organize research data and improve its database.
Results
Takeaway
The reported time reduction applied to material design within film development. Physical experimentation and evaluation remained separate development stages.
Categories
- Size
- Large enterprise
- Industry
- Chemicals and materials
- Business function
- IT and R&D
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and MLOptimization
- Adoption
- Partner co-development
- Evidence
- Vendor case study
Sources
Source summaries
Hitachi reported that AI predictions reduced a film-material design task from 5 months to 4 hours. It described subsequent collaboration on research-data organization and distinguished future experimental automation from completed work.
Full details are in the original sources.
