A Digital-Twin-Based and RAG-Based LLM Agent Framework for Intelligent Bearing Diagnosis and Maintenance

Intelligent bearing diagnosis and maintenance require question-answering systems that combine asset-specific condition evidence with engineering knowledge. However, existing bearing diagnosis studies mainly predict fault labels or health states, while document-based RAG systems generally lack access to the condition of a specific asset. Digital twin-based systems provide structured condition data but offer limited support for manual-grounded diagnostic interpretation. Consequently, there is still no unified route-aware framework and benchmark for determining the evidence that is required by different diagnostic questions and evaluating route selection, DT querying, document retrieval, and answer grounding separately. To address this gap, this paper proposes a route-aware digital twin (DT) and retrieval-augmented generation (RAG) large language model (LLM) agent framework for bearing diagnosis question answering (QA). The framework routes questions to four paths: unrelated, DT-only, RAG-only, and DT+RAG. A route-specific 140-question benchmark is constructed from run-to-failure bearing data and a technical maintenance manual corpus to evaluate the router and the four processing paths. The hybrid router achieves an accuracy of 0.979, while the DT-only module obtains 0.967 query accuracy and 0.900 joint accuracy. Hybrid + reranker performs best for RAG-only Hit@5, mean reciprocal rank (MRR), and context precision, whereas hybrid performs best for DT+RAG Hit@1, MRR, faithfulness, and context precision. These results demonstrate that route-aware evidence selection provides a transparent and evaluable approach to LLM-based bearing diagnosis QA.