用强化学习加速气动外形优化，降低计算成本并解析关键设计特征。
Reinforcement Learning for Accelerated Aerodynamic Shape Optimisation
- 基于代理模型的演员-评论家强化学习，结合参数冻结策略减少维度
- 在少量CFD仿真下实现全局优化提速，局部邻域需足够大且奖励估计准确
- 可解释优化结果，适用于需要理解设计特征重要性的工程场景
本文提出一种基于强化学习的自适应优化算法，用于气动外形优化，重点在于降维。采用基于代理模型的演员-评论家策略评估方法，结合马尔可夫链蒙特卡洛（MCMC）框架，并允许部分待优化参数在时间上“冻结”。目标是降低计算开销，并利用优化结果解释所发现极值在实现期望流场中的作用。通过一系列以中间CFD模拟为真实值的局部参数调整，若（a）参数局部邻域足够大以超越网格步长及大量仿真数量的限制，且（b）对这些邻域的奖励与成本估计足够精确，则可加速全局优化。文中以一个简单流体力学问题为例，展示了该方法在特征重要性评分方面的可解释性。
原文摘要 · Abstract (English)
We introduce a reinforcement learning (RL) based adaptive optimization algorithm for aerodynamic shape optimization focused on dimensionality reduction. The form in which RL is applied here is that of a surrogate-based, actor-critic policy evaluation MCMC approach allowing for temporal 'freezing' of some of the parameters to be optimized. The goals are to minimize computational effort, and to use the observed optimization results for interpretation of the discovered extrema in terms of their role in achieving the desired flow-field. By a sequence of local optimized parameter changes around intermediate CFD simulations acting as ground truth, it is possible to speed up the global optimization if (a) the local neighbourhoods of the parameters in which the changed parameters must reside are sufficiently large to compete with the grid-sized steps and its large number of simulations, and (b) the estimates of the rewards and costs on these neighbourhoods necessary for a good step-wise parameter adaption are sufficiently accurate. We give an example of a simple fluid-dynamical problem on which the method allows interpretation in the sense of a feature importance scoring.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。