CelSian Glass & Solar has been awarded an MIT Grant for a collaborative research project on using Artificial Intelligence (AI) to enhance the efficiency of glass production.
The ‘Quality prediction and simulation optimisation for glass production’ project will explore the use of AI in predicting glass quality.
CelSian Glass & Solar will collaborate on this research with Ignition Computing, a company that specialises in complex numerical solvers for fusion energy and multiphysics problems.
The project's goal is the development of an AI-accelerated CFD application and integration with an AI-based quality prediction model for industrial glass manufacturing.
The glass-melting process can take up to multiple days. Temperature and material fluctuations have implications for the final product. Product quality issues, such as bubbles in glass, may arise. This can lead to the loss of large batches of glass, totalling multiple days of production.
Developments in machine learning and simulation can provide more accurate predictions of glass quality.
By accelerating simulation software in the glass industry, the project will reduce product losses, thereby substantially reducing costs as well as CO2, NOx, and SOx emissions into the atmosphere.
The project also includes GTM-X and PreconNet integration, GTM-X performance optimisation, integration in a quality prediction model, pilot testing, and validation.
The application project placed first out of 57 submissions in the national MIT R&D AI tender.
The MIT-R&D encourages SMEs within the top sectors in the Netherlands to develop creative initiatives.
These sectors are the ones that have the potential to solve global problems and help boost the country’s economy and competitiveness.
The MIT Grant will boost CelSian’s R&D capabilities.
Furthermore, the project contributes to the development of ‘Engineering and fabrication technologies’ by developing digital twins for processes with the help of new machine learning technologies.
