Knowledge graph enhanced retrieval-augmented generation for failure mode and effects analysis
Lukas Bahr, Christoph Wehner, Judith Wewerka, José Bittencourt, Ute Schmid, Rüdiger Daub
Technical University of Munich University of Bamberg BMW (Germany) BMW Group (Germany)
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
Failure mode and effects analysis (FMEA) is an essential tool for mitigating potential failures, particularly during the ramp-up phases of new products. However, its effectiveness is often limited by the reasoning capabilities of the FMEA tools, which are usually tabular structured. Meanwhile, large language models (LLMs) offer novel prospects for advanced natural language processing tasks. However, LLMs face challenges in tasks that require factual knowledge, a gap that retrieval-augmented generation (RAG) approaches aim to fill. RAG retrieves information from a non-parametric data store and uses a language model to generate responses. Building on this concept, we propose to enhance the non-parametric data store with a knowledge graph (KG). By integrating a KG into the RAG framework, we aim to leverage analytical and semantic question-answering capabilities for FMEA data. This paper contributes by presenting set-theoretic standardization and a schema for FMEA data, an algorithm for creating vector embeddings from the FMEA-KG, and a KG-enhanced RAG framework. Our approach is validated through a user experience design study, and we measure the precision and performance of the context retrieval recall. • This paper proposes integrating knowledge graphs within a retrieval-augmented generation (KG-RAG) framework, utilizing a query search to deliver user-friendly and analytic question answering on failure mode and effects analysis (FMEA) data. • It builds on a set-theoretic standardization of FMEA, enabling any FMEA to be converted into a KG. An FMEA schema is proposed to facilitate this transposition. Additionally, an algorithm is suggested for traversing the FMEA-KG to generate vector embeddings. • A user experience design study and performance measurements of context recall and precision validate the approach. Initial results indicate that (i) the query search outperforms RAG approaches that rely solely on vector search for retrieving numerical information, and (ii) well-defined vector embeddings of the FMEA-KG are crucial for effective information retrieval in expert domain data.
逐年被引趋势
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
计算机 / AITopic Modeling
Semantic Web and Ontologies · Information Retrieval and Search Behavior
参考文献 62
此处列出前 3 条
引用本文 150
按被引量排序,此处列出前 3 条