Design of optimal flow concentrator for vertical-axis wind turbines using computational fluid dynamics, artificial neural networks and genetic algorithm

Abstract

Wind energy extraction is one of the fastest developing engineering branches today. Number of installed wind turbines is constantly increasing. Appropriate solutions for urban environments are quiet, structurally simple and affordable small-scale vertical-axis wind turbines (VAWTs). Due to small efficiency, particularly in low and variable winds, main topic here is development of optimal flow concentrator that locally augments wind velocity, facilitates turbine start and increases generated power. Conceptual design was performed by combining finite volume method and artificial intelligence (AI). Smaller set of computational results (velocity profiles induced by existence of different concentrators in flow field) was used for creation, training and validation of several artificial neural networks. Multi-objective optimization of concentrator geometric parameters was realized through coupling of generated neural networks with genetic algorithm. Final solution from the acquired Pareto set is studied in more detail. Resulting computed velocity field is illustrated. Aerodynamic performances of small-scale VAWT with and without optimal flow concentrator are estimated and compared. The performed research demonstrates that, with use of flow concentrator, average increase in wind speed of 20%–25% can be expected. It also proves that contemporary AI techniques can significantly facilitate and accelerate design processes in the field of wind engineering.