基于智能算法的高海拔风电机组多参数优化设计

以高海拔地区风电机组为对象，建立了平准化电力成本（LCOE）模型，并采用智能算法对其关键设计参数进行优化。分析了海拔升高对气候环境与风电机组的影响，建立了以转子半径、轮毂高度以及额定功率为设计参数的高海拔风电机组LCOE模型。以LCOE最小化为目标，采用遗传、粒子群、量子遗传3种智能优化算法对3个设计参数进行优化。优化结果表明，一定的海拔高度下存在最佳参数和最优LCOE，3种智能算法皆能得到模型的最优解，而量子遗传算法在收敛时间与收敛精度上均具有较好性能。随着海拔的升高，最优LCOE增大，3个优化参数呈现出不同的变化趋势。本文的相关结论对于高海拔风电机组选型与设计具有一定的参考意义。

Multi-parameter Optimized Design for High-altitude Wind Turbines Based on Intelligent Algorithm

Taking the wind turbines in high-altitude areas as study object， the levelized cost of energy （LCOE） model of high-altitude wind turbines is established and intelligent algorithm is used to optimize the optimal parameters. The impact of elevation increase on climate environment & wind turbine is analyzed. LCOE model of high-altitude wind turbines is established，which takes rotor radius，hub height and rated power as designed parameters. With LCOE minimization as the target， genetic algorithm，particle swarm algorithm and quantum genetic algorithm are used to optimize the LCOE model. The optimization results show that there are optimal parameters and optimal LCOE at certain altitude， optimal solution of the model can be obtained with all three intelligent algorithms，quantum genetic algorithm has good performance in both convergence time and convergence accuracy. As the altitude increases，the optimal LCOE increases，three optimization parameters show different trends. The relevant conclusions are valuable for the development of high-altitude wind turbines.