论文部分内容阅读
为进一步提高激波针减阻和降热的效果,在i SIGHT优化平台的基础上,以阻力系数和热流最小为目标,对激波针外形进行了多目标优化设计,实现了整个优化流程的全自动进行。试验采用优化的拉丁超立方采样技术生成样本点,利用i SIGHT软件的集成功能,实现几何建模、网格划分、数值求解的自动化,并采用径向基神经网络建立近似模型。同时,使用NSGA-II算法进行多目标优化,获得了Pareto解集。最后通过对一个典型外形气动性能的数值求解,验证了此优化设计的优越性。
In order to further enhance the effect of shock pin resistance and heat sink, based on the i SIGHT optimization platform, a multi-objective optimization design of the shock pin shape is achieved with the objective of minimizing the drag coefficient and heat flow, and the whole optimization process Fully automatic. The experiment uses the optimized Latin hypercube sampling technique to generate sample points. The integrated functions of iSIGHT software are used to automate geometric modeling, meshing and numerical solution. Radial basis neural networks are used to establish the approximate model. At the same time, using the NSGA-II algorithm for multi-objective optimization, obtained Pareto solution set. Finally, the aerodynamic performance of a typical shape is solved numerically to verify the superiority of this optimized design.