让AI从自然语言直接生成可验证的结构设计，无需人工调参。
AutoSiMP: Autonomous Topology Optimization from Natural Language via LLM-Driven Problem Configuration and Adaptive Solver Control
- 用大模型解析中文描述，自动生成几何、载荷等完整设计参数。
- 在17个基准测试中，自动控制器使结构合规性最优，且首次尝试即通过全部质量检查。
- 适合希望快速原型化结构设计的研究者与工程师，尤其关注自动化流程落地。
我们提出AutoSiMP，一个从自然语言描述到可验证二值拓扑结构的全自动流程。该流程包含五个模块：（1）基于大模型的配置器，将纯英文提示解析为有效几何、支撑、载荷、被动区域及网格参数；（2）边界条件生成器，输出求解器可用的自由度数组、力向量和被动单元掩码；（3）带Heaviside投影的三场SIMP求解器，支持可插拔的连续性控制；（4）八项结构评估器（连通性、柔度、灰度、体积分数、收敛性及三项信息质量指标）；（5）闭环重试机制。评估显示：在10个多样化问题中，配置器所有案例均生成有效规范，中位柔度惩罚仅+0.3%；在17个基准上，与六种控制器对比，大模型控制器实现最低中位柔度，但通过率76.5%；确定性调度器通过率达100%，仅额外增加+1.5%柔度。使用调度器时，所有大模型配置的问题首次尝试即通过全部质量检查，无需重试。在所调研系统中，AutoSiMP是首个实现从自然语言描述到验证拓扑的全流程闭环的系统。代码库、所有规范及交互式网页演示将在期刊接收后公开。
原文摘要 · Abstract (English)
We present AutoSiMP, an autonomous pipeline that transforms a natural-language structural problem description into a validated, binary topology without manual configuration. The pipeline comprises five modules: (1) an LLM-based configurator that parses a plain-English prompt into a validated specification of geometry, supports, loads, passive regions, and mesh parameters; (2) a boundary-condition generator producing solver-ready DOF arrays, force vectors, and passive-element masks; (3) a three-field SIMP solver with Heaviside projection and pluggable continuation control; (4) an eight-check structural evaluator (connectivity, compliance, grayness, volume fraction, convergence, plus three informational quality metrics); and (5) a closed-loop retry mechanism. We evaluate on three axes. Configuration accuracy: across 10 diverse problems the configurator produces valid specifications on all cases with a median compliance penalty of $+0.3\%$ versus expert ground truth. Controller comparison: on 17 benchmarks with six controllers sharing an identical sharpening tail, the LLM controller achieves the lowest median compliance but $76.5\%$ pass rate, while the deterministic schedule achieves $100\%$ pass rate at only $+1.5\%$ higher compliance. End-to-end reliability: with the schedule controller, all LLM-configured problems pass every quality check on the first attempt $-$ no retries needed. Among the systems surveyed in this work (Table 1), AutoSiMP is the first to close the full loop from natural-language problem description to validated structural topology. The complete codebase, all specifications, and an interactive web demo will be released upon journal acceptance.
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。