Wind turbine blade airfoils database3/16/2024 ![]() Starting with more accurate inputs means researchers can further narrow the number of designs that need additional high-fidelity modelling. Low-fidelity models are fast to reduce the number of design iterations that require high-fidelity refinement, and researchers know that they only give an indication of how the airfoil will perform. Higher-fidelity means greater confidence in results-there is always some error in modelling. Our work seeks to inject higher fidelity insights (e.g., nonlinear aerodynamic effects) into the design process without affecting their tight timelines.” To achieve all of this, designers use cheap, low-fidelity tools to rapidly create and assess new designs. “Further, design iterations must move extremely quickly to keep pace with the market. “Wind turbine airfoil and blade design is a complex, interdisciplinary process that must balance a wide range of objectives in the shifting landscape of customer demands, policy regulations, and technological innovations,” said Andrew Glaws, an NREL computational science researcher working to pave the way for improved airfoil designs. Researchers at the National Renewable Energy Laboratory (NREL) are building computational tools using artificial intelligence (AI) that can help optimise airfoil design for wind turbine blades, aircraft wings, and fan blades in natural gas turbines.Ī visualisation of 100 distinct airfoil shapes generated from the invertible neural network for a given design criterion: The dotted lines show the range of all shapes used to train the model. / IMAGE: NREL The problem with the current design process The airfoil design problem-where an engineer works to build a shape with desired characteristics, such as maximising lift while minimising drag-presents an opportunity for innovation. ![]() Humans have always developed tools or technologies to help us surmount challenges. Future research will look at improved 2D/3D shape representations, design for blades experiencing erosion or icing, and going well beyond blades and into the design of floating offshore platforms. NREL has made the tools open-source and publicly available. Designers specify target performance characteristics and then rapidly explore the range of shapes that correspond to those design targets. Researchers are exploring deep-learning models using neural networks to deliver high-fidelity modelling within the same tight timeframes. ![]() To keep up with the pace of change in the market (not just customer demands, but policy regulations and technological innovations), the current method uses simplified low-fidelity modelling because it’s quicker to turn around. Justin Daugherty at NREL describes research there on using generative AI to accelerate and improve the wind turbine blade design process. ![]()
0 Comments
Leave a Reply.AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |