Ganufacturing – Revolutionizing Quality Control in 3D Printing with Generative Adversarial Networks

In the realm of 3D printing, ensuring quality assurance remains a significant challenge, particularly due to the limitations of manual inspection methods. This study introduces an approach utilizing Generative Adversarial Networks (GANs) and a specially designed image classifier to detect defects in 3D printed objects. The discriminator component of GANs is employed to effectively distinguish between defective and non-defective items. Furthermore, an image classifier, optimized for low-resource environments, is developed, and implemented on a Raspberry Pi using TensorFlow Lite. This setup offers a practical solution for real-time defect detection in industrial 3D printing applications, potentially revolutionizing quality control processes.