|
| Abstract: |
| In this paper, a new algorithm combining the features of bi-direction evolutionary structural optimization (BESO) and reinforcement learning (RL) is proposed for continuum structural topology optimization (STO). In contrast to conventional approaches which only generate a certain quasi-optimal solution, the goal of the combined method is to provide more quasi-optimal solutions for designers such as the idea of generative design. Two key components were adopted. First, besides sensitivity, value function updated by Monte-Carlo reinforcement learning was utilized to measure the importance of each element, which made the solving process convergent and closer to the optimum. Second, ε-greedy policy added a random perturbation to the main search direction so as to extend the search ability. Finally, the quality and diversity of solutions could be guaranteed by controlling the value of compliance as well as Intersection-over-Union (IoU). Results of several 2D and 3D compliance minimization problems, including a geometrically nonlinear case, show that the combined method is capable of generating a group of good and different solutions that satisfy various possible requirements in engineering design within acceptable computation cost. |
| Key words: structural topology optimization bi-direction evolutionary structural optimization reinforcement learning first-visit Monte-Carlo method ε-greedy policy generative design |
| DOI：10.11916/j.issn.1005-9113.19078 |
| Clc Number:TU311 |
| Fund: |
|
| Descriptions in Chinese: |
| 结合BESO与强化学习的结构拓扑优化 孙鸿博, 马岭 （深海载人装备国家重点实验室，中国船舶科学研究中心，江苏 无锡 214033） 摘要：本文将双向进化结构优化法(Bi-direction evolutionary structural optimization, BESO)与强化学习(Reinforcement learning, RL)结合，提出一种新算法，用于求解结构拓扑优化问题。与传统算法仅生成一个确定的近优解不同，该算法的目标是向设计者提供若干个近优解，类似于生成式设计(generative design)。该算法主要包含两部分：1） 除灵敏度外，根据蒙特卡洛强化学习更新的值函数也被用于衡量各结构单元的重要性，以使结果更加收敛并向最优值靠近；2） -贪心策略在主搜索方向上添加了一个随机扰动，以扩展算法的搜索能力。最后，通过控制结构柔度值以及交并比(Intersection-over-Union, IoU)，来保证解的质量及多样性。本文将该算法用于一些二维和三维结构最小应变能问题，包括一个几何非线性算例，结果表明，该算法在可接受的时间内，能够生成一组“好而不同”的解，以满足实际工程中可能存在的多种需求。 关键词：结构拓扑优化；双向进化结构优化法；强化学习；首次访问蒙特卡洛法；-贪心策略；生成式设计 |
