An unsupervised machine learning strategy is developed to automatically cluster the vortex wakes of bio-inspired propulsors into groups of similar propulsive thrust and efficiency metrics. A pitching and heaving foil is simulated via computational fluid dynamics with 121 unique kinematics by varying the frequency, heaving amplitude, and pitching amplitude. A Reynolds averaged Navier-Stokes model is employed to simulate the flow over the oscillating foils at Re = 10 6 , computing the propulsive efficiency, thrust coefficient and the unsteady vorticity wake signature. Using a pairwise Pearson correlation it is found that the Strouhal number most strongly influences the thrust coefficient, whereas the relative angle of attack, defined by both the mid-stroke and maximum have the most significant impact on propulsive efficiency. Next, the various kinematics are automatically clustered into distinct groups exclusively using the vorticity footprint in the wake. A convolutional autoencoder is developed to reduce vortex wake images to their most significant features, and a k-means++ algorithm performs the clustering. The results are assessed by comparing clusters to a thrust versus propulsive efficiency map, which confirms that wakes of similar performance metrics are successfully clustered together. This automated clustering has the potential to identify complex vorticity patterns in the wake and modes of propulsion not easily discerned from traditional classification methods.
This work examines the dynamic stall process and resulting wake features of cross-flow turbines under confined configurations using two computational modeling approaches, Reynolds-averaged Navier-Stokes (RANS) and large-eddy simulation (LES). Cross-flow turbines harvest energy from wind or water currents via rotation about an axis perpendicular to the flow and are a complementary technology to the more common axial-flow turbine. During their 360° rotation cross-flow turbine blades experience a cyclical variation in the angle of attack and velocity relative to the oncoming flow, leading to flow separation and reattachment, otherwise known as dynamic stall. The dynamic stall process causes an instantaneous loss in torque generation and unsteady force fluctuations which pose a challenge to accurate predictions of both the performance and the resulting unsteady flow field. This research compares RANS simulations to higher fidelity LES of a straight-bladed two-blade cross-flow turbine at a moderate Reynolds number (Rec = 45,000) in a confined configuration. The RANS model is shown to be very sensitive to confinement at the simulated tip speed ratio as it over-predicts power generation due to suppression of flow separation, while the flow field from LES matches well with the experimental validation. Results are compared with an unconfined configuration for which the RANS model successfully predicts a power curve; however, it displays significant differences in the evolution of flow structures such as premature shedding of the dynamic stall vortex and a lack of vortex diffusion during convection in the wake.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.