A machine learning-based fatigue loads and power prediction method for wind turbines under yaw control. (15th November 2022)

• Record Type: Journal Article
• Authors: He, Ruiyang; Yang, Hongxing; Sun, Shilin; Lu, Lin; Sun, Haiying; Gao, Xiaoxia
• Is Part Of: Applied energy. Volume 326(2022)
• Publication Date: 2022-11-15
• Subjects: Wind turbine -- Active yaw control -- Fatigue loads -- Machine learning; Power (Mechanics) -- Periodicals; Energy conservation -- Periodicals; Energy conversion -- Periodicals; 621.042
• DOI: 10.1016/j.apenergy.2022.120013
• Languages: English
• ISSNs: 0306-2619

Abstract

Highlights: An innovative fatigue loads and power prediction method for yaw control is proposed. SVR is used to build relationship between inputs and turbine performance. The combined effects of wake flow and yaw control are considered. The accuracy and robustness of prediction method is verified by a comparative study. Abstract: Yaw control is one of the most promising active wake control strategies to maximize the total power generation of wind farms. Meanwhile, structural performance needs to be considered in yaw misalignment in case the adverse structural performance offsets the benefit of yaw control in power enhancement. However, an efficient and accurate prediction method for fatigue loads under yaw control is still lacking. In this study, a machine learning-based prediction method is proposed to accurately estimate the fatigue loads and power of wind turbines under yaw control. Fatigue loads at critical turbine components and corresponding power yields are selected as outputs to reflect the performance of yawed wind turbines. Since most wind turbines (WTs) are sunk into the wake flow of their upstream counterparts, the wake effects are considered with the combination of active yaw control. Besides, the full range of inflow and yaw conditions are taken into account to ensure the accuracy and practicability of the proposed model. A machine learning algorithm, support vector regression (SVR), is tuned and trained to learn the relationships between outputs and inputs. The superiority of the proposed method is verified by comparing it with another machine learning-based model in several metrics. The results show that the proposed prediction method can return high regression coefficients and low deviation, proving its accuracy and robustness. Large yaw angles and high wind speeds are found to be beneficial for further improving the prediction accuracy. The proposed fatigue loads and power prediction method is expected to make contributions to the yaw optimization and therefore benefit the wind farms.