A new study led by researcher Sébastien Le Fouest from the School of Engineering Unsteady Flow Diagnostics Lab has shed light on the potential commercialization of vertical-axis wind turbines (VAWTs) through the application of machine learning technology. Vertical-axis wind turbines, which spin perpendicular to the wind as opposed to the traditional horizontal-axis design, offer several advantages such as reduced noise levels, increased wind energy density, and improved wildlife-friendliness.
Despite these benefits, VAWTs have not been widely adopted in the wind energy market due to engineering challenges related to air flow control. However, Le Fouest and his team have developed two optimal pitch profiles for VAWT blades using a genetic learning algorithm, resulting in a 200% increase in turbine efficiency and a 77% reduction in vibrations that threaten the structure.
The study’s findings hold significant promise for addressing the global need to increase wind energy capacity in order to meet carbon emissions objectives. With Europe’s wind energy capacity growing at a rate below the necessary levels, innovative solutions such as the optimization of VAWTs could play a crucial role in accelerating the transition to renewable energy sources.
By harnessing the power of machine learning and sensor technology, researchers were able to overcome the limitations of VAWTs in handling gusts and dynamic stall phenomena. The development of efficient and robust pitch profiles has transformed the traditional weaknesses of VAWTs into strengths, paving the way for increased adoption and utilization of this sustainable energy technology.
In conclusion, the intersection of engineering expertise, machine learning algorithms, and sensor technology offers a promising pathway towards commercializing vertical-axis wind turbines and advancing the global renewable energy agenda. Le Fouest’s groundbreaking research marks a significant step forward in overcoming the technical challenges that have hindered the widespread use of VAWTs, signaling a new era of innovation in the wind energy sector.
