用大模型生成智能维修方案，准确率达91.59%
LLM-R: A Framework for Domain-Adaptive Maintenance Scheme Generation Combining Hierarchical Agents and RAG
- 分层智能体+指令级RAG优化生成流程
- 混合数据微调准确率91.59%，防幻觉
- 适合需要高精度维修方案的工业场景
智能设备普及使维护在生产中愈发关键。交互式电子技术手册（IETMs）虽为重要工具，但面临从图形界面转向自然语言界面的挑战，且难以处理复杂逻辑关系，难以满足智能化需求。本文提出基于大语言模型的维修方案生成方法LLM-R。其核心创新包括：提出低秩适应-知识保留（LORA-KR）损失技术，按比例调整混合维修数据以微调大模型，缓解因数据混合引发的知识冲突，提升模型在特定维修领域的适应性与推理能力；引入分层任务型智能体与指令级检索增强生成（RAG）技术，优化生成步骤，缓解模型因缺乏上下文导致的幻觉现象，增强对已知或未知维修对象及场景的灵活性与准确性。为验证有效性，构建了涵盖多领域设备的维修方案数据集。实验结果表明，该方法生成的维修方案准确率达91.59%，显著提升维修智能化水平，并引入新颖的技术路径用于设备维护。
原文摘要 · Abstract (English)
The increasing use of smart devices has emphasized the critical role of maintenance in production activities. Interactive Electronic Technical Manuals (IETMs) are vital tools that support the maintenance of smart equipment. However, traditional IETMs face challenges such as transitioning from Graphical User Interfaces (GUIs) to natural Language User Interfaces (LUIs) and managing complex logical relationships. Additionally, they must meet the current demands for higher intelligence. This paper proposes a Maintenance Scheme Generation Method based on Large Language Models (LLM-R). The proposed method includes several key innovations: We propose the Low Rank Adaptation-Knowledge Retention (LORA-KR) loss technology to proportionally adjust mixed maintenance data for fine-tuning the LLM. This method prevents knowledge conflicts caused by mixed data, improving the model's adaptability and reasoning ability in specific maintenance domains, Besides, Hierarchical Task-Based Agent and Instruction-level Retrieval-Augmented Generation (RAG) technologies are adopted to optimize the generation steps and mitigate the phenomenon of hallucination caused by the model's Inability to access contextual information. This enhancement improves the model's flexibility and accuracy in handling known or unknown maintenance objects and maintenance scheme scenarios. To validate the proposed method's effectiveness in maintenance tasks, a maintenance scheme dataset was constructed using objects from different fields. The experimental results show that the accuracy of the maintenance schemes generated by the proposed method reached 91.59%, indicating which improvement enhances the intelligence of maintenance schemes and introduces novel technical approaches for equipment maintenance.
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。