A Memory-Augmented LLM-Driven Method for Autonomous Merging of 3D Printing Work Orders

2025-04-03

AI Summary

To address the declining work order processing efficiency caused by surging personalized orders in 3D printing production lines, this paper proposes a memory-augmented large language model (LLM)-driven intelligent work order consolidation framework. The method integrates self-memory learning with natural language prompt engineering and synergistically leverages industrial tools—including work order–equipment matching and collision/interference detection—to significantly mitigate LLM hallucination and enhance decision reliability. Evaluated on a real-world production line, the framework improves work order consolidation accuracy and equipment allocation precision by 23.6% and 18.4%, respectively, over conventional rule-based or purely data-driven approaches, while ensuring high robustness and interpretability. Its core innovation lies in the first deep integration of an LLM endowed with persistent memory capability into the closed-loop scheduling of discrete manufacturing—establishing a novel AI-native solution for flexible smart manufacturing.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

With the rapid development of 3D printing, the demand for personalized and customized production on the manufacturing line is steadily increasing. Efficient merging of printing workpieces can significantly enhance the processing efficiency of the production line. Addressing the challenge, a Large Language Model (LLM)-driven method is established in this paper for the autonomous merging of 3D printing work orders, integrated with a memory-augmented learning strategy. In industrial scenarios, both device and order features are modeled into LLM-readable natural language prompt templates, and develop an order-device matching tool along with a merging interference checking module. By incorporating a self-memory learning strategy, an intelligent agent for autonomous order merging is constructed, resulting in improved accuracy and precision in order allocation. The proposed method effectively leverages the strengths of LLMs in industrial applications while reducing hallucination.

Problem

• Autonomous merging of 3D printing work orders
• Enhancing production line efficiency via LLM-driven method
• Reducing hallucination in industrial LLM applications

Innovation

• Memory-augmented LLM for autonomous order merging
• Natural language templates for order-device matching
• Self-memory learning to reduce LLM hallucination