lightweight structural design

This study addresses the challenge of simultaneously achieving low-carbon design and constructability in truss structure optimization by proposing a mixed-integer linear programming (MILP) model that integrates multi-material selection, cross-sectional size constraints, and connection complexity control. For the first time, constructability constraints—such as node connectivity complexity and multi-material compatibility—are unified with embodied carbon minimization within a single optimization framework, while rigorously accounting for material constitutive relationships. Computational experiments demonstrate that incorporating constructability constraints substantially alters optimal designs; in several cases, judicious material selection reduces embodied carbon by nearly 29%, confirming the method’s effectiveness and scalability in jointly enhancing environmental performance and engineering feasibility.

This study addresses the limitation of existing large language models (LLMs), which support only a single structural analysis software and thus fail to meet engineers’ needs for cross-platform modeling across tools such as ETABS, SAP2000, and OpenSees. To overcome this, the authors propose a two-stage multi-agent architecture: in the first stage, multiple agents collaboratively parse user input and generate a unified JSON representation of structural information; in the second stage, they parallelly produce executable scripts tailored to each target platform. This approach represents the first demonstration of LLM-based universal automated modeling for mainstream structural analysis software. By integrating multi-agent collaborative reasoning, structured information extraction, and code-translation prompt engineering, the method achieves over 90% accuracy across ten repeated trials on 20 representative frame problems, significantly enhancing the generality and reliability of engineering workflows.

This work addresses the lack of quantitative feedback on structural elements that impede robotic disassembly in current product design, which hinders disassembly optimization. The authors propose a CAD-based method that constructs a contact–connection–constraint graph to analyze robotic disassembly sequences and quantify the influence of individual components. For the first time, this influence is mapped onto the geometric model to generate a 3D heatmap, enabling automatic identification and recommendation of key fasteners that can be eliminated without compromising structural integrity. Experiments on seven household appliances demonstrate that the approach successfully identifies redundant fasteners, removes 8–132 structural constraints, reduces tool changes, and shortens robotic travel distance by 165–1675 mm within allowable structural limits.

This work addresses the limitations of black-box optimization in structural design, which often yields suboptimal or physically implausible solutions due to its neglect of problem modeling and domain knowledge. Focusing on the topology optimization of laminated composite structures, the study proposes an explicit decoupling of topological and fiber orientation design variables, combined with a physics-informed sequential optimization strategy. This approach departs from conventional context-agnostic black-box paradigms by leveraging domain-specific insights. Compared to concurrent optimization of all variables, the proposed sequential method significantly improves compliance minimization under volume constraints, yielding superior and physically interpretable designs. The results underscore the critical role of integrating domain knowledge into the optimization process to enhance both performance and solution plausibility.

Traditional mechanical structural optimization relies heavily on expert knowledge and computationally expensive finite element analysis (FEM), while existing machine learning approaches suffer from poor generalizability and dependence on large-scale labeled datasets. Method: We propose the first zero-shot LLM-FEM collaborative framework for autonomous 2D truss generation, multi-objective evaluation, and iterative optimization—requiring no fine-tuning. A general-purpose large language model (GPT-4.1 and its lightweight variant) serves as the natural language reasoning engine, tightly coupled with a physics-based FEM module for structural validation. Convergence is guided via temperature-controlled sampling and multi-objective feedback-driven prompt engineering. Contribution/Results: Compared to NSGA-II, our method drastically reduces FEM evaluations and accelerates convergence. GPT-4.1-mini (temperature=0.5) achieves the highest constraint satisfaction rate and optimization step efficiency. This work establishes, for the first time, the feasibility of LLMs as cross-task general-purpose structural optimizers.

本文提出了一种基于应变能分布优化的系统级轻量化方法，通过均匀分配单位质量应变能并结合多种优化技术，实现服务机器人的轻量化设计与性能提升。

本文提出动态确定所需特征值数量的方法及新的优化公式来准确预测最优设计的屈曲模态，解决了拓扑优化中屈曲约束问题。

本文提出了一种基于灵敏度热点惩罚(SHoSP)的稳健拓扑优化框架，以低成本抑制制造变异和几何不确定性引起的局部脆弱性问题。

This study addresses the challenge of spatial layout optimization for interconnected systems within non-convex design spaces by extending the SPI2 framework. It introduces, for the first time, a geometric representation based on Maximal Disjoint Ball Decomposition (MDBD) combined with differentiable inside-outside tests, enabling component placement under arbitrary non-convex boundaries. The method integrates computations of centroid and moment of inertia and establishes an end-to-end CAD workflow that supports automatic assembly reconstruction. By simultaneously satisfying geometric constraints, routing requirements, and physical performance objectives, the approach guarantees geometric feasibility within numerical precision. The efficacy and practicality of the proposed method are demonstrated through a multi-system co-layout case study of a synthetic aircraft auxiliary unit.

Although topology optimization has matured, its reliance on manual intervention—such as modeling, meshing, and boundary condition specification—hinders accessibility for non-experts. This work proposes the first conversational framework based on a large language model (LLM) agent that enables end-to-end topology optimization through natural language instructions and optional inputs (e.g., images, geometry, or meshes), automatically invoking finite element solvers and optimization tools. The approach integrates multi-load structural and thermal optimization, handles stress constraints, and employs few-shot prompting strategies, successfully reproducing benchmark cases while solving complex engineering problems and autonomously generating optimized structures, field distributions, and convergence curves. Ablation studies confirm that prompt design critically enhances system robustness, substantially lowering the usability barrier without compromising numerical reliability.