arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.25099cs.CEcs.AI
收藏

大语言模型作为优化控制器:SIMP拓扑优化的自适应延续

Large Language Models as Optimization Controllers: Adaptive Continuation for SIMP Topology Optimization

Department of Mechanical Engineering, Santa Clara University(圣克拉拉大学机械工程系)

Shaoliang Yang, Jun Wang, Yunsheng Wang

AI总结:

本文提出利用大语言模型作为SIMP拓扑优化的在线自适应控制器,通过实时状态条件参数决策替代传统固定调度延续方法,提升优化效果。

摘要:

我们提出一个框架,其中大语言模型(LLM)作为SIMP拓扑优化的在线自适应控制器,取代传统固定调度延续方法。在每次第k次迭代中,LLM接收结构化观察(当前合规性、灰度指数、停滞计数器、棋盘度量、体积分数和预算消耗),并通过直接数字控制接口输出惩罚指数p、投影锐度β、滤波半径r_min和移动限制δ的数值。硬灰度门防止过早二元化,元优化循环使用第二个LLM迭代来调整代理的调用频率和门阈值。我们对四个基线(固定、标准三场延续、专家启发法、仅调度消融)在三个二维问题(悬臂、MBB梁、L型支架)和两个三维问题(悬臂、MBB梁)上进行基准测试,所有问题均运行300次迭代。标准化的40次锐化尾部从最佳有效快照应用,使得合规性差异仅反映探索阶段。LLM代理在每个基准测试中均达到最低最终合规性:相对于固定基线,-5.7%至-18.1%,所有解决方案均为完全二进制。仅调度消融在三个问题中的两个上表现低于固定基线,确认LLM的实时干预(而非调度几何)驱动了增益。代码和再生产脚本将在发表时发布。

英文摘要:

We present a framework in which a large language model (LLM) acts as an online adaptive controller for SIMP topology optimization, replacing conventional fixed-schedule continuation with real-time, state-conditioned parameter decisions. At every $k$-th iteration, the LLM receives a structured observation$-$current compliance, grayness index, stagnation counter, checkerboard measure, volume fraction, and budget consumption$-$and outputs numerical values for the penalization exponent $p$, projection sharpness $β$, filter radius $r_{\min}$, and move limit $δ$ via a Direct Numeric Control interface. A hard grayness gate prevents premature binarization, and a meta-optimization loop uses a second LLM pass to tune the agent's call frequency and gate threshold across runs. We benchmark the agent against four baselines$-$fixed (no-continuation), standard three-field continuation, an expert heuristic, and a schedule-only ablation$-$on three 2-D problems (cantilever, MBB beam, L-bracket) at $120\!\times\!60$ resolution and two 3-D problems (cantilever, MBB beam) at $40\!\times\!20\!\times\!10$ resolution, all run for 300 iterations. A standardized 40-iteration sharpening tail is applied from the best valid snapshot so that compliance differences reflect only the exploration phase. The LLM agent achieves the lowest final compliance on every benchmark: $-5.7\%$ to $-18.1\%$ relative to the fixed baseline, with all solutions fully binary. The schedule-only ablation underperforms the fixed baseline on two of three problems, confirming that the LLM's real-time intervention$-$not the schedule geometry$-$drives the gain. Code and reproduction scripts will be released upon publication.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑