Large-Scale Customized Production Scheduling of Multiagent-Based Medical 3D Printing

Area of Science:

• Medical Engineering
• Manufacturing Technology
• Artificial Intelligence

Background:

• Three-dimensional (3D) printing, or additive manufacturing, offers advantages over traditional methods, gaining traction in medicine.
• The demand for large-scale, customized medical 3D printing (M-3DP) has surged, especially during public health events.
• Traditional scheduling methods struggle with M-3DP's complexity, particularly multimaterial printing and job-to-device matching.

Purpose of the Study:

• To address the challenges in large-scale customized M-3DP production scheduling.
• To propose an intelligent collaborative scheduling method using a multiagent system.
• To optimize M-3DP production for reduced completion time and balanced device load.

Main Methods:

• Development of a multiagent-based optimization model for M-3DP scheduling.
• Implementation of an improved genetic algorithm incorporating product mix strategy and intelligent matching.
• Evaluation of the method's effectiveness through numerical simulation.

Main Results:

• The improved genetic algorithm significantly reduced M-3DP mass customization production scheduling time.
• The proposed method achieved better load balancing between devices compared to other algorithms.
• The approach demonstrated enhanced intelligent collaboration for M-3DP mass customization.

Conclusions:

• The intelligent multiagent-based method effectively optimizes M-3DP production scheduling.
• The improved genetic algorithm offers superior performance in reducing lead times and balancing workloads.
• This advancement promotes the intelligent manufacturing of customized medical 3D printed products.