Operating-regime dependence of turbulence effects on an H-type Darrieus vertical-axis wind turbine using uncertainty-aware surrogate modeling

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.

Authors

Institutions

Publication Details

Journal
Proceedings of the Institution of Mechanical Engineers Part A Journal of Power and Energy
Published
2026-11-20
DOI
https://doi.org/10.1177/09576509261508217
Primary Topic
Wind Energy Research and Development
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Operating-regime dependence of turbulence effects on an H-type Darrieus vertical-axis wind turbine using uncertainty-aware surrogate modeling

İhsan Uluocak, Negar Vakili, Kyosung Choo, Erfan Nasirzadeh Orang et al.
4 links
Proceedings of the Institution of Mechanical Engineers Part A Journal of Power and Energy
Wind Energy Research and Development
article

Operating-regime dependence of turbulence effects on an H-type Darrieus vertical-axis wind turbine using uncertainty-aware surrogate modeling

İhsan Uluocak, Negar Vakili, Kyosung Choo, Erfan Nasirzadeh Orang, Aydin Ulus
article en

Abstract

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.

Proceedings of the Institution of Mechanical Engineers Part A Journal of Power and Energy
Youngstown State University (US), Cukurova University (TR)
Affordable and clean energy
Wind Energy Research and Development
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon