Optimization of 3D Printed Garment Materials Using Reinforcement Learning and Generative Design
Year: 2025
Type: article
Abstract: The integration of three-dimensional (3D) printing technology with generative design and reinforcement learning (RL) has opened new frontiers in the optimization of garment materials, enabling unprecedented levels of customization, durability, and sustainability in fashion manufacturing. This study proposes an adaptive RL framework to optimize the material properties of 3D-printed textiles, ensuring an ideal balance between flexibility, strength, and comfort. The framework utilizes deep reinforcement learning (DRL) to continuously improve material composition and structural patterns based on real-time performance feedback. Additionally, generative design algorithms facilitate automated fabric structure generation, reducing material waste while enhancing functional adaptability. Experimental evaluations demonstrate that the proposed system significantly improves mechanical performance and wearability compared with traditional material processing methods. The results highlight the potential of combining AI-driven generative modeling and RL to revolutionize the customized and sustainable production of fashion textiles.
Author: Jiayi Wang
Institution: Harbin University
Language: English
Subfield: Visual Arts and Performing Arts
Field: Arts and Humanities
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W4413302491