1
Return

Experimentally validated machine learning surrogates for rapid power coefficient prediction of Darrieus hydrokinetic turbines under canal and river flow conditions

delete2026-08-01
delete0
PRE
AI
D
Dan Singh Pimoli
C
Chandra Shekhar Pant *
DOI：10.1016/j.enconman.2026.121966delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• Darrieus HKT dataset (1830 points) used to train RF, XGBoost, and ANN. • ANN achieved highest accuracy ( R2=0.981 ) and outperformed XGBoost and RF. • SHAP identifies tip speed ratio, solidity, and aspect ratio as key Cp predictors. • ANN validated by flume and CFD benchmarks, enabling rapid turbine screening.

Journal

Energy Conversion and Management cover
Energy Conversion and Management
IF:
10.9
Papers:
2.0W
Citations:
11.3W

Organization

No organization information available
Cited Papers

Cited Papers

Citing Papers

Citing Papers