Enhancing 3D Printing Workflows through Multi-Objective Optimization and Reinforcement Learning Techniques
Ahmad Alghamdi
Abstract
Integrating Machine Learning (ML) with optimization algorithms in 3D printing, also known as Additive Manufacturing (AM), has revolutionized the creation and production of complex structures. This integration has significantly boosted material efficiency, print quality, and optimization of the entire process. This paper delves into details on improving 3D printing design and production workflows using advanced ML techniques such as neural networks, Reinforcement Learning (RL), and optimization techniques, such as topology optimization and genetic algorithms. The proposed framework offers a 15-25% reduction in print time and material consumption and a 10-20% improvement in predictive accuracy over existing methods. Additionally, the results of the multiobjective optimization reveal an aligned improvement in cost-effectiveness, structural strength, and mechanical performance. Stress-strain analysis showed that optimized designs can achieve up to a 12% increase in yield strength, while defect rates decrease by up to 30% by applying dynamic RL for parameter adjustments. The results validate the effectiveness of these hybrid models, emphasizing their potential to boost reliability, efficiency, and scalability in additive manufacturing processes.