用多智能体LLM框架实现从图纸到制造计划的全流程自动规划
Design-to-Plan: A Large Language Model-Based Multi-Agent Framework for Manufacturing Process Planning from 3D CAD Models and 2D Engineering Drawings
- 设计多智能体系统，分工协作处理3D模型与2D图纸
- 端到端规划成功率达100%，工具识别F1超95%
- 适合智能制造、工业自动化领域研究者使用
制造工艺规划需将异构设计信息转化为连贯的制造决策。现有方法多聚焦于孤立子任务，如特征识别、图纸解析或刀具选择，难以支撑从设计文档到工艺计划的完整推理链条。尤其在需解析3D CAD模型、2D工程图、材料属性及领域规则时尤为困难。本文提出Design-to-Plan，一种基于大语言模型（LLM）的多智能体框架，实现端到端制造工艺规划。由协调器管理多个专用智能体：3D特征识别、2D图纸分析、2D-3D上下文融合、知识检索、工序排序、刀具选择与报告生成。不将LLM作为独立文本生成器，而是作为与确定性模块和知识源交互的推理智能体，确保决策一致且可追溯。在300个基准案例中，该并行架构在三个下游ReAct增强智能体上均达100%成功率，工具识别F1值95.9%-97.6%，冲突分析源检测准确率90%，关键任务令牌使用量降低60%-68%。结果表明，结构化LLM多智能体协同可有效衔接设计表示与制造知识，实现可扩展、高效、可追溯的设计到制造自动化。
原文摘要 · Abstract (English)
Manufacturing process planning transforms heterogeneous design information into coherent manufacturing decisions. However, existing approaches focus on isolated subtasks, such as feature recognition, drawing interpretation, or tool selection, and struggle to support the full reasoning chain from design artifacts to process plans. This is critical when planning must interpret 3D CAD models, 2D engineering drawings, materials, and domain-specific rules. To address this gap, this paper presents Design-to-Plan, a large language model (LLM)-based multi-agent framework for end-to-end manufacturing process planning. An orchestrator coordinates specialized agents for 3D feature recognition, 2D drawing analysis, 2D-3D context fusion, knowledge retrieval, process sequencing, tool selection, and report generation. Rather than using LLMs as standalone text generators, the framework deploys them as reasoning agents that interact with deterministic modules and knowledge sources to produce consistent and traceable decisions. In this hybrid design, deterministic modules and specialized agents extract structured information from CAD and drawing inputs, while LLM agents perform context-aware reasoning, retrieve manufacturing rules, resolve conflicts, and generate planning outputs. The framework is evaluated using 300 benchmark cases across three downstream ReAct-enabled agents, plus separate evaluations of CAD feature recognition, drawing analysis, and 2D-3D context fusion. The parallel architecture achieves 100% success across downstream agents, Tool F1 scores of 95.9%-97.6%, 90% source detection accuracy in conflict analysis, and a 60%-68% reduction in token usage for key planning tasks. Results show that structured LLM-based multi-agent coordination can bridge design representations and manufacturing knowledge, enabling scalable, efficient, and traceable design-to-plan automation.
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。