Towards scalable intelligence at the edge: a multi-agent framework for quality assurance in additive manufacturing
Key Points
This work aims to develop a framework for real-time quality assurance in additive manufacturing by leveraging a multi-agent system.
Developed the Additive Edge Multi-Agent framework consisting of Specialist Agents, a Transformer-based Historian, and an Orchestrator.
Utilized acoustic monitoring and embedded computing to analyze print process dynamics.
Conducted experiments with six print classes to evaluate the framework's effectiveness.
Achieved an accuracy improvement from 87.76% to 98.37% with the new multi-agent architecture.
Average inference time was approximately 105 ms for each 1-second audio segment.
Validated the system's capability for real-time defect detection in additive manufacturing processes.
Abstract
Abstract Real-time quality assurance in Additive Manufacturing remains challenging, as most monitoring frameworks do not directly account for process dynamics on the printer. This work presents the Additive Edge Multi-Agent (AEMA) framework, an acoustic monitoring system that runs entirely on an embedded single-board computer connected directly to a fused deposition modeling printer. AEMA separates the task into three parts: Specialist Agents that analyze short, phase-specific windows of spectral audio features, a Transformer-based Historian that models the full print history, and an Orchestrator that combines their outputs using an attention mechanism to predict the current print condition. Experiments on six print classes (normal print, over-extrusion, under-extrusion, no extrusion, poor layer adhesion, and toolhead failure) show an improvement in accuracy from 87.76% for the baseline multi-agent model to 98.37% for the final AEMA architecture, with an average inference time of about 105 ms per 1-s segment on an ODROID-XU4Q board. Findings indicate that a multi-agent, edge-deployed design can support practical real-time defect monitoring in AM.