减轻技术人员的检索负担：面向赛斯纳172维护手册的多模态检索增强生成
Reducing Technician Search Burden: A Multimodal RAG for Cessna 172 Maintenance Manual
浏览论文内容
中文总结 AI 辅助
本研究针对赛斯纳172维护手册，开发多模态检索增强生成流程，其多模态手册检索器召回率达93.37%，生成响应与基准答案语义相似度87.20%，可减轻技术人员检索负担。
中文摘要 AI 辅助
正确使用飞机维护手册对于开展规范的维护工作至关重要，这类手册提供了操作流程、图表、注意事项及规格参数。然而，技术人员往往因手册难以导航且在紧张日程下耗时过多而不愿查阅。检索增强生成（RAG）模型近期已应用于飞机维护领域，但现有模型仅聚焦文本检索。本研究针对通用航空中广泛使用的赛斯纳172维护手册（C172-MM），开发了一种能够检索多模态手册页面的多模态手册检索器（MMR）。使用涵盖操作流程、图表、注意事项/安全信息及规格参数的合成查询对检索性能进行评估，MMR在召回率@5指标上达到93.37%。除检索外，还对多模态检索增强生成（MRAG）流程进行了检验，将检索到的页面输入视觉语言模型以生成针对合成查询的响应，该响应与基准答案的语义相似度达到87.20%。此外，还评估了三项实际可行性指标：推理时间、运营成本和可解释性。检索5页的平均时间为11.93秒，响应生成耗时4.95秒，每次查询成本为0.0091美元，同时通过热力图可视化验证了可解释性。这些结果表明，面向C172-MM的MRAG流程能够减少技术人员在检索手册及多模态信息上的时间投入。
英文摘要
Proper use of the aircraft maintenance manual is essential for correct maintenance, providing procedures, diagrams, cautions, and specifications. However, technicians often avoid consulting it because it is difficult to navigate and time-consuming under strict schedules. Retrieval augmented generation (RAG) models have recently been introduced in aircraft maintenance, yet existing models focus solely on textual retrieval. This research therefore targeted the Cessna 172 Maintenance Manual (C172-MM), widely used in general aviation, and developed a multimodal manual retriever (MMR) capable of retrieving multimodal manual pages. Retrieval performance was evaluated using synthetic queries covering procedures, diagrams, caution/safety information, and specifications; the MMR achieved 93.37% recall@5. Beyond retrieval, a multimodal RAG (MRAG) pipeline was examined, in which retrieved pages were input to a vision-language model that generated responses to the synthetic queries, achieving 87.20% semantic similarity to ground-truth answers. Three practical feasibilities were also assessed: inference time, operational cost, and interpretability. Average retrieval time for five pages was 11.93 seconds and response generation took 4.95 seconds, at $0.0091 per query, while interpretability was validated through heatmap visualizations. These results indicate that the MRAG pipeline for the C172-MM can reduce the time technicians spend searching manuals and retrieving multimodal information.
