DT and LLM driven intelligent maintenance system for L-DED and DAG-based LLM fault diagnosis evaluation framework

Abstract

Metal additive manufacturing (AM) has revolutionized industries such as aerospace and automotive manufacturing due to its ability to rapidly prototype complex structures. Laser Directed Energy Deposition (L-DED) is a key AM technique, offering high deposition rates and superior mechanical properties. However, the inherent complexity and high cost of L-DED equipment demand reliable maintenance management to minimize downtime. Traditional maintenance approaches struggle to keep pace with escalating production demands and to cope with growing equipment complexity. To address this, we propose a dual-driven intelligent maintenance system for L-DED, integrating Digital Twins (DT) and Large Language Models (LLMs). The system features a comprehensive DT framework that synchronizes the virtual entity with the physical one in real time, it also incorporates an intelligent maintenance Q&A assistant powered by Retrieval-Augmented Generation (RAG), leveraging L-DED maintenance knowledge bases to provide accurate operational support. Additionally, we propose a Directed Acyclic Graphs (DAG)-based framework to assess LLMs’ ability to guide users through complete fault diagnosis. Our work aims to enhance the reliability and efficiency of L-DED maintenance through advanced digital technologies, ultimately improving productivity and reducing downtime in additive manufacturing.