A Knowledge-Driven LLM-Based Decision-Support System for Explainable Defect Analysis and Mitigation Guidance in Laser Powder Bed Fusion

This work introduces a knowledge-driven, LLM-based decision-support system for explainable defect diagnosis and mitigation guidance in manufacturing, using Laser Powder Bed Fusion (LPBF) as a case study. The system integrates an ontological knowledge base of 27 LPBF defect types, supporting natural language queries and literature-backed explanations. It also features a multimodal module for interpreting microscopic defect images.