🤖 AI Summary
Current 3D printing defect detection methods rely heavily on expert intervention or task-specific models requiring extensive labeled data, exhibiting poor generalization across printers and firmware versions. To address this, we propose the first large language model (LLM)-based real-time monitoring and closed-loop control system for additive manufacturing. Our approach integrates multimodal perception of inter-layer images and leverages an LLM for zero-shot fault attribution, policy reasoning, and repair instruction generation—without domain-specific fine-tuning or annotated data. The system interfaces directly with printer APIs to autonomously execute corrective actions. It generalizes across heterogeneous hardware and firmware, accurately identifying common defects—including inconsistent extrusion, stringing, warping, and interlayer adhesion failure—localizing root-cause parameters (e.g., nozzle temperature, print speed, bed leveling), and dynamically adjusting them in real time. Fully automated and human-in-the-loop-free, it achieves diagnostic and corrective performance comparable to that of experienced AM engineers.
📝 Abstract
Industry 4.0 has revolutionized manufacturing by driving digitalization and shifting the paradigm toward additive manufacturing (AM). Fused Deposition Modeling (FDM), a key AM technology, enables the creation of highly customized, cost-effective products with minimal material waste through layer-by-layer extrusion, posing a significant challenge to traditional subtractive methods. However, the susceptibility of material extrusion techniques to errors often requires expert intervention to detect and mitigate defects that can severely compromise product quality. While automated error detection and machine learning models exist, their generalizability across diverse 3D printer setups, firmware, and sensors is limited, and deep learning methods require extensive labeled datasets, hindering scalability and adaptability. To address these challenges, we present a process monitoring and control framework that leverages pre-trained Large Language Models (LLMs) alongside 3D printers to detect and address printing defects. The LLM evaluates print quality by analyzing images captured after each layer or print segment, identifying failure modes and querying the printer for relevant parameters. It then generates and executes a corrective action plan. We validated the effectiveness of the proposed framework in identifying defects by comparing it against a control group of engineers with diverse AM expertise. Our evaluation demonstrated that LLM-based agents not only accurately identify common 3D printing errors, such as inconsistent extrusion, stringing, warping, and layer adhesion, but also effectively determine the parameters causing these failures and autonomously correct them without any need for human intervention.