AI and Machine Learning in 3D Printing: Advancing Design, Efficiency, and Sustainability in the Digital Age

Artificial intelligence (AI) and machine learning (ML) are no longer futuristic add-ons to additive manufacturing (AM)—they are fundamentally changing how we design, produce, and sustain manufacturing. In my work, I’ve seen firsthand how AI-driven generative design and topology optimization can produce parts that are not only lighter and stronger but also more resource-efficient. For instance, one of our aerospace projects achieved a 45% weight reduction in a critical component, resulting in significant fuel savings. At the same time, ML-based process controls have proven invaluable for preemptively detecting defects, thereby reducing waste and energy consumption. However, these innovations come with challenges. While Rojek et al. (2019 ) emphasize the promise of AI in optimizing material efficiency, my own experiments have revealed limitations when it comes to generalizing models across diverse materials. Moreover, issues such as overly complex designs and biased training datasets remain. Ultimately, the factories of the future won’t just manufacture—they will think, adapt, and evolve, positioning AI-driven AM as the architect of a smarter, more sustainable, and self-optimizing manufacturing revolution.