Answers are grounded in this paper and cite their sources.
The aerodynamic response of an H-type Darrieus vertical-axis wind turbine to inflow turbulence depends on the rotor operating regime and cannot be represented by a single turbulence correction. This study examines the coupled effects of free-stream velocity, tip speed ratio, and turbulence intensity for a fixed-geometry, three-bladed rotor using an 85-case two-dimensional unsteady Reynolds-averaged Navier-Stokes database. The retained cases span free-stream velocities of 6, 9, and 12 m/s, tip speed ratios of 1.5–3.5, and turbulence intensities of 1%–25%. Gaussian process regression, random forest, and extreme gradient boosting are used as surrogate tools to interpolate the computed operating map and are evaluated using nested five-fold cross-validation. Across the sampled conditions, the highest power coefficient occurs at a tip speed ratio of 2.5. Increasing turbulence from 1% to 25% reduces the peak power coefficient by approximately 3%–6%, whereas the reduction reaches 17% at a tip speed ratio of 1.5 and 9 m/s. A local non-monotonic response also appears near a tip speed ratio of 2.0 and turbulence intensities of 10%–15%. SHapley Additive exPlanations identify tip speed ratio as the dominant input, while turbulence intensity has a smaller global contribution but a strongly operating-regime-dependent effect. The three nonlinear surrogates are statistically comparable; Gaussian process regression gives a root-mean-square error of 0.0047 and provides predictive variance for interpolation within the sampled domain. The results show that the surrogate is most useful as an uncertainty-aware representation of operating-condition interactions within the adopted two-dimensional numerical framework.
No takes yet. Share an insight, caveat, or question.
Ulus et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: