LLM-R: A Framework for Domain-Adaptive Maintenance Scheme Generation Combining Hierarchical Agents and RAG

TL;DR

This paper introduces LLM-R, a novel framework combining hierarchical agents and retrieval-augmented generation to improve domain-specific maintenance scheme generation using large language models, with innovations in data adaptation and hallucination mitigation.

Contribution

The paper presents a new LLM-based framework with LORA-KR loss and hierarchical RAG techniques for more accurate, adaptable maintenance scheme generation, addressing hallucination and domain adaptation challenges.

Findings

Achieved 91.59% accuracy in maintenance scheme generation

Enhanced model adaptability and reasoning in maintenance tasks

Reduced hallucination through instruction-level RAG techniques

Abstract

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.