TPI Composites and WindSTAR have created a digital twin for wind blade manufacturing. Producing wind blades is highly challenging, and current approaches to the use of computers in wind blade production incur a very high computational cost. The digital twin approach developed by TPI and WindSTAR incorporates a machine learning model that provides real-time feedback during fabrication, resulting in reduced defects and more efficient production of wind blades.

Arizona based TPI Composites and WindSTAR, a National Science Foundation (NSF) funded Industry-University Cooperative Research Centre, collaborated to design a composite manufacturing process employing machine learning and big data to serve as the digital twin of the blade manufacturing process.

Stephen Nolet, Senior Director of Innovation & Technology for TPI, worked alongside student researchers and faculty from the University of Texas at Dallas, as well as technical experts from Olin Epoxy and Westlake Epoxy to develop a framework for the digital twin of the vacuum assisted resin infusion molding (VARIM) process. By applying an ML approach, the team achieved predictive accuracy of more than 95% with 100-times faster computation than physics-based simulations.

Mr Nolet said: “The primary value of utilising a ML framework is leveraging historical results and data to inform current manufacturing at a pace that significantly reduces defects from occurring in a real-time production environment. Additionally, this technology allows users to create alternative manufacturing scenarios to increase production velocity in manufacturing operations while simultaneously reducing infusion related problems.”

In the coming year, the WindSTAR research team plans to focus on scaling the technology to larger components with greater manufacturing complexity. The work will apply tools taken from Artificial Intelligence to find patterns in historical data and predict outcomes on full-scale wind blade components including blade shells.