AI 中文总结
本文提出The AI Engineer智能体框架，通过LLMs与工程后端闭环耦合实现工程设计自动化，其设计经CCS验证达标，性能优于人工优化的TuQiang基准。
AI 中文摘要
智能体AI已实现部分科学发现的自动化，包括论文生成、专家级编码、治疗方案提出及自主实验，但复杂的物理工程设计仍是空白，因为设计候选方案必须同时满足流体动力学、固体力学和结构稳定性的多重约束。本文提出The AI Engineer，这一智能体框架将大语言模型（LLMs）与确定性工程后端耦合形成闭环：将自然语言需求转换为设计领域的几何与网格；采用双向进化结构优化（BESO）结合CalculiX求解器进行拓扑优化；在海上空气-水-伺服-弹性载荷工况下，采用粒子群优化（PSO）结合Zwind细化构件尺寸。为在无需逐候选方案验证成本的前提下探索大量设计，Automated Reviewer依据11个实际浮式风电项目校准的分段线性函数，从容量、钢材强度、单位成本、可建造性、疲劳寿命五个维度对每个候选方案评分。搜索仅在候选方案达到综合评分S≥85（A级）且无单项评分低于60时终止。我们通过将得分最高的设计提交至中国船级社（CCS）申请原则性认可（AIP）验证该机制，其获得通过；AIP因此成为外部校验，确保Automated Reviewer追踪专业判断而非仅日常目标。该经验证的设计优于人工优化的TuQiang基准，在满足所有AIP标准的同时，钢材质量和单位资本成本各降低8.1%。这种每个方案均由确定性物理和编码极限状态评判的闭环验证机制，使The AI Engineer区别于开放式生成系统。剩余局限包括详细设计和制造硬约束。
英文摘要
Agentic AI has automated parts of scientific discovery, including paper generation, expert-level coding, therapeutic proposal, and autonomous experimentation. Complex physical engineering design remains a gap, because candidates must satisfy simultaneous constraints in fluid dynamics, solid mechanics, and structural stability. We introduce The AI Engineer, an agentic framework that couples large language models (LLMs) to deterministic engineering backends in a closed loop: natural-language requirements are converted into design-domain geometry and mesh; topology is optimized with bi-directional evolutionary structural optimization (BESO) coupled to the CalculiX solver; and member sizes are refined with particle swarm optimization (PSO) coupled to Zwind under offshore aero-hydro-servo-elastic load cases. To explore many designs without per-candidate certification cost, an Automated Reviewer scores each candidate on five dimensions (capacity, steel intensity, unit cost, constructability, and fatigue life) using piecewise-linear functions calibrated on 11 real floating-wind projects. Search terminates only when a candidate reaches a composite score $S \ge 85$ (grade A) with no subscore below 60. We validated this gate by submitting the top-scoring design to the China Classification Society (CCS) for Approval in Principle (AIP), which it passed; AIP is thus an external check that the reviewer tracks professional judgment, not the daily objective. The certified design outperforms the human-optimized TuQiang baseline, reducing steel mass and unit capital cost by 8.1% each while meeting all AIP criteria. This verification-closed regime, in which every proposal is judged by deterministic physics and codified limit states, distinguishes The AI Engineer from open-ended generative systems. Remaining limits include detailed design and fabrication-hard constraints.
Comments24 pages,3 figures
