Horizontal-axis wind turbines (HAWT) have the constant rotor speed, while the blade tip speed changes continuously. This could reduce power performance of the wind turbine. In this paper, the accuracy of soft-computing technique was employed for aerodynamics performance prediction based on continuously variable-speed horizontal-axis wind turbine with optimal blades. The process, which simulates the $$\varphi$$ φ (relative wind angle), BEP (blade element parameter), SP (solidity parameter), CPtot (total power coefficient), CPl (local power coefficient), and CT (local thrust coefficient), with adaptive neuro-fuzzy inference system (ANFIS) was constructed. The inputs were local speed ratios λr and different values of drag-to-lift ratio ε . The performance of proposed system is confirmed by the simulation results. The ANFIS results are compared with the experimental results using root-mean-square error and coefficient of determination and Pearson’s coefficient. The experimental results show that an improvement in predictive accuracy and capability of generalization can be achieved by the ANFIS approach. The effectiveness of the proposed strategies is verified based on the simulation results.

中文翻译：

---

基于自适应神经模糊方法的连续变速风力机空气动力学性能预测

水平轴风力涡轮机（HAWT）具有恒定的转子速度，而叶尖速度不断变化。这会降低风力涡轮机的功率性能。本文利用软计算技术的精度进行了基于连续变速水平轴风力机优化叶片的空气动力学性能预测。该过程模拟了 $$\varphi$$ φ（相对风角）、BEP（叶片单元参数）、SP（固体参数）、CPtot（总功率系数）、CPl（局部功率系数）和 CT（局部功率系数）推力系数），构建了自适应神经模糊推理系统（ANFIS）。输入是局部速度比 λr 和不同的阻力升力比值 ε 。仿真结果证实了所提出系统的性能。使用均方根误差和决定系数以及 Pearson 系数将 ANFIS 结果与实验结果进行比较。实验结果表明，ANFIS 方法可以提高预测精度和泛化能力。基于仿真结果验证了所提出策略的有效性。