A reinforcement learning based blade twist angle distribution searching method for optimizing wind turbine energy power

Jia, Lin; Hao, Jia; Hall, John F.; Nejadkhaki, Hamid Khakpour; Wang, Guoxin; Yan, Yan; Sun, Mengyuan

doi:10.1016/j.energy.2020.119148

Cited by 26 publications

(6 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural networks have shown promising results in solving nonlinear problems and have been increasingly used in wind power research [15,16,17,18,19,20]. In this study, we used a 3D-CNN architecture based on the model proposed in Higashiyama et al [11].…”

Section: Neural Network Modelmentioning

confidence: 99%

How Regional Wind Characteristics Affect Cnn-Based Wind Predictions: Insights from Spatiotemporal Correlation Analysis

Shin

Rüttgers

Lee

2023

Preprint

View full text Add to dashboard Cite

Section: Neural Network Modelmentioning

confidence: 99%

How Regional Wind Characteristics Affect Cnn-Based Wind Predictions: Insights from Spatiotemporal Correlation Analysis

Shin

Rüttgers

Lee

2023

Preprint

View full text Add to dashboard Cite

“…Since wind blades are usually used in dynamic wind environments where the wind speed varies greatly, it is important to find the optimal TAD for different wind speeds. In their work, Jia et al [12] present a learning-based method for finding the optimal TAD, which they call RL-TAD. A case study was conducted to validate the proposed method.…”

Section: Wind Turbine Bladesmentioning

confidence: 99%

Wind Turbine Technology Trends

et al. 2022

View full text Add to dashboard Cite

The rise in prices of traditional energy sources, the high dependence of many countries on their import, and the associated need for security of supply have led to large investments in new capacity of wind power plants. Although wind power generation is a mature technology and levelized cost of electricity low, there is still room for its improvement. A review of available literature has indicated that wind turbine development in the coming decade will be based on upscaling wind turbines and minor design improvements. These include further improvements in rotor blade aerodynamics, active control of the rotor blade rotation system, and aerodynamic brakes that will lead to increased power generation efficiency. Improvements in system maintenance and early diagnosis of transmission and power-related faults and blade surface damage will reduce wind turbine downtime and increase system reliability and availability. The manufacture of wind turbines with larger dimensions presents problems of transportation and assembly, which are being addressed by manufacturing the blades from segments. Numerical analysis is increasingly being used both in wind turbine efficiency analysis and in stress and vibration analysis. Direct drive is becoming more competitive with traditional power transmission through a gearbox. The trend in offshore wind farms is to increase the size of wind turbines and to place them farther from the coast and in deeper water, which requires new forms of floating foundations. Due to the different work requirements and more difficult conditions of the marine environment, optimization methods for the construction of offshore substructures are currently being developed. There are plans to use 66-kV cables for power transmission from offshore wind farms instead of the current 33-kV cables. Offshore wind farms can play an important role in the transition to a hydrogen economy. In this context, significant capacity is planned for the production of “green” hydrogen by electrolysis from water. First-generation wind turbines are nearing the end of their service life, so strategies are being developed to repower them, extend their life or dismantle and recycle them.

show abstract

“…Jia et al [57] demonstrated a tunable WT blade using RL. The twist angle distribution of the turbine blades was tuned using RL to maximize aerodynamic performances.…”

Section: Nn-based Turbine Blade Designmentioning

confidence: 99%

Neural Networks for Improving Wind Power Efficiency: A Review

Shin

Rüttgers

Lee

2022

Fluids

View full text Add to dashboard Cite

The demand for wind energy harvesting has grown significantly to mitigate the global challenges of climate change, energy security, and zero carbon emissions. Various methods to maximize wind power efficiency have been proposed. Notably, neural networks have shown large potential in improving wind power efficiency. In this paper, we provide a review of attempts to maximize wind power efficiency using neural networks. A total of three neural-network-based strategies are covered: (i) neural-network-based turbine control, (ii) neural-network-based wind farm control, and (iii) neural-network-based wind turbine blade design. In the first topic, we introduce neural networks that control the yaw of wind turbines based on wind prediction. Second, we discuss neural networks for improving the energy efficiency of wind farms. Last, we review neural networks to design turbine blades with superior aerodynamic performances.

show abstract

A reinforcement learning based blade twist angle distribution searching method for optimizing wind turbine energy power

Cited by 26 publications

References 14 publications

How Regional Wind Characteristics Affect Cnn-Based Wind Predictions: Insights from Spatiotemporal Correlation Analysis

How Regional Wind Characteristics Affect Cnn-Based Wind Predictions: Insights from Spatiotemporal Correlation Analysis

Wind Turbine Technology Trends

Neural Networks for Improving Wind Power Efficiency: A Review

Contact Info

Product

Resources

About