中国机械工程2024，Vol.35Issue(8)：1397-1404,8.DOI:10.3969/j.issn.1004-132X.2024.08.008
基于多智能体深度Q网络交互的板壳加强筋生长式设计
Growth Design of Stiffeners for Shell/Plate Structures Based on MADQN Interaction
摘要
Abstract
Based on the Markov property of the growth steps of shell/plate stiffeners,a reinforce-ment learning driving strategy of the growth design of shell/plate stiffeners was proposed.Aiming at minimizing the overall strain energy of the structures,Markov decision process was used to model the growth processes of the stiffeners.By introducing a multi-agent system to share the states and the re-wards of the stiffeners growth processes,and memorizing specific actions,the learning complexity was reduced.Meanwhile,the convergence of the reward value of the stiffeners growth processes was realized.Therefore,the growth design strategy of shell/plate stiffeners was achieved.Finally,a nu-merical example was given and the results of the smoothed stiffeners layout were compared with those of the classical algorithm,which verifies the validity of the growth design of stiffeners for shell/plate structures based on MADQN interaction.关键词
板壳加强筋/生长式/多智能体深度Q网络/布局设计/强化学习Key words
stiffener for shell/plate structure/growth pattern/multi-agent deep Q network(MADQN)/layout design/reinforcement learning分类
机械制造引用本文复制引用
钟意,杨勇,姜学涛,潘顺洋,朱其新,王磊..基于多智能体深度Q网络交互的板壳加强筋生长式设计[J].中国机械工程,2024,35(8):1397-1404,8.基金项目
国家自然科学基金(51805346) （51805346）
江苏省研究生科研与实践创新计划(KYCX24_3423,KYCX22_3260) （KYCX24_3423,KYCX22_3260）
