LLM-3D Print: Large Language Models To Monitor and Control 3D Printing
Yayati Jadhav, Peter Pak, Amir Barati Farimani
2024-08-28
Summary
This paper discusses LLM-3D Print, a system that uses large language models (LLMs) to monitor and control 3D printing processes, improving the quality of printed products.
What's the problem?
3D printing is a popular manufacturing method that creates objects layer by layer, but it can often encounter errors during the printing process. These errors can affect the quality of the final product and usually require expert intervention to fix. Existing automated systems for detecting these errors are limited because they may not work well with different types of printers or setups.
What's the solution?
The authors propose a framework that combines LLMs with 3D printers to detect and correct printing defects in real-time. The LLM analyzes images taken after each layer of printing to assess the quality and identify any issues. It can then communicate with the printer to adjust settings and implement a corrective action plan without needing human help. This system has been tested against a group of engineers and has shown to effectively identify common 3D printing problems, such as inconsistent material flow or warping, and resolve them autonomously.
Why it matters?
This research is significant because it enhances the reliability of 3D printing technology, making it easier to produce high-quality customized products. By reducing the need for expert intervention, this system can save time and resources in manufacturing, leading to more efficient production processes in various industries.
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.