Study of the Flow Mechanism of Wind Turbine Blades in the Yawed Condition

The computational fluid dynamics method was used to simulate the flow field around a wind turbine at the yaw angles of 0°,15°,30°,and 45°.The angle of attack and the relative velocity of the spanwise sections of the blade were extracted with the reference points method.By analyzing the pressure distribution and the flow characteristics of the blade surface,the flow mechanism of the blade surface in the yawed condition was discussed.The results showed that the variations of the angle of attack and the relative velocity were related to the azimuth angle and the radius in the yawed condition.The larger the yaw angle was,the larger the variation was.The pressure distribution in the spanwise sections was affected by both the angle of attack and the relative velocity.The angle of attack was more influential than the relative velocity.At the same yaw angle,when the angle of attack decreased,the c_(p)∼x/c curve shrunk inward and the lift force decreased.The larger the yaw angle was,the more obvious the shrink was.The effect of the yaw on the blade root region was higher than its effect on the blade tip region.

Machine Learning Methods in Solving the Boolean Satisfiability Problem

This paper reviews the recent literature on solving the Boolean satisfiability problem(SAT),an archetypal N P-complete problem,with the aid of machine learning(ML)techniques.Over the last decade,the machine learning society advances rapidly and surpasses human performance on several tasks.This trend also inspires a number of works that apply machine learning methods for SAT solving.In this survey,we examine the evolving ML SAT solvers from naive classifiers with handcrafted features to emerging end-to-end SAT solvers,as well as recent progress on combinations of existing conflict-driven clause learning(CDCL)and local search solvers with machine learning methods.Overall,solving SAT with machine learning is a promising yet challenging research topic.We conclude the limitations of current works and suggest possible future directions.The collected paper list is available at https://github.com/ThinklabSJTU/awesome-ml4co.Keywords:Machine learning(ML),Boolean satisfiability(SAT),deep learning,graph neural networks(GNNs),combinatorial optimization.