Knowledge graph enhanced retrieval-augmented generation for failure mode and effects analysis

TL;DR

This paper introduces a novel knowledge graph-enhanced retrieval-augmented generation framework to improve failure mode and effects analysis by leveraging semantic question-answering and analytical capabilities.

Contribution

It presents a schema for FMEA data, an algorithm for creating vector embeddings from a knowledge graph, and integrates this into a RAG framework for enhanced reasoning.

Findings

Improved retrieval precision and recall in FMEA data analysis.

Enhanced semantic understanding for failure mode reasoning.

Validated approach through user experience and performance metrics.

Abstract

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.