Abstract
Conventional mechanical design paradigms rely on experts systematically refining concepts through experience-guided modification and FEA to meet specific requirements. However, this approach can be time-consuming and heavily dependent on prior knowledge and experience. While numerous machine learning models have been developed to streamline this intensive and expert-driven iterative process, these methods typically demand extensive training data and considerable computational resources. Furthermore, methods based on deep learning are usually restricted to the specific domains and tasks for which they were trained, limiting their applicability across different tasks. This creates a trade-off between the efficiency of automation and the demand for resources. In this study, we present a novel approach that integrates pre-trained LLMs with a FEM module. The FEM module evaluates each design and provides essential feedback, guiding the LLMs to continuously learn, plan, generate, and optimize designs without the need for domain-specific training. We demonstrate the effectiveness of our proposed framework in managing the iterative optimization of truss structures, showcasing its capability to reason about and refine designs according to structured feedback and criteria. Our results reveal that these LLM-based agents can successfully generate truss designs that comply with natural language specifications with a success rate of up to 90%, which varies according to the applied constraints. By employing prompt-based optimization techniques we show that LLM based agents exhibit optimization behavior when provided with solution-score pairs to iteratively refine designs to meet specifications. This ability of LLM agents to produce viable designs and optimize them based on their inherent reasoning capabilities highlights their potential to develop and implement effective design strategies autonomously.
Abstract (translated)
传统机械设计范式依赖于专家通过经验指导的修改和有限元分析（FEA）来系统地优化概念以满足具体需求。然而，这种方法耗时且高度依赖于先验知识和经验。虽然已经开发了许多机器学习模型来简化这一密集和专家驱动的迭代过程，但这些方法通常需要大量的训练数据和相当大的计算资源。此外，基于深度学习的方法通常仅限于所训练的具体领域和任务，限制了它们在不同任务上的应用。这导致自动化效率与资源需求之间存在平衡。在这项研究中，我们提出了一个新方法，将预训练的LLM与有限元分析（FEM）模块相结合。FEM模块评估每个设计并提供关键反馈，指导LLM持续学习、规划、生成和优化设计，而无需进行领域特定训练。我们证明了所提出的框架在管理悬索结构迭代优化方面的有效性，展示了其根据结构化反馈和标准评估进行推理和优化设计的能力。我们的研究结果表明，基于LLM的代理商可以成功生成符合自然语言规范的悬索结构设计，成功率高达90%，具体取决于应用的限制条件。通过采用提示式优化技术，我们证明了LLM代理商在获得解决方案评分对迭代优化设计以满足规范具有优化行为。这种基于LLM代理商产生可行设计和优化它们的能力，突出表明了它们可以自主开发和实施有效设计策略的潜力。
URL
https://arxiv.org/abs/2404.17525
