Autonomous Control of Extrusion Bioprinting Using Convolutional Neural Networks
Daniel Kelly, Vasileios Sergis, Léonardo Blanco, Karl Mason, Andrew C. Daly
Abstract
Abstract Extrusion bioprinting technology suffers from reproducibility challenges due to the open‐loop nature of current hardware systems. Here, a novel AI‐powered extrusion bioprinting platform is presented with integrated real‐time quality monitoring and automated error correction capabilities. To achieve this, a custom bioprinting system is engineered with an integrated camera for continuous process monitoring and trained convolutional neural networks (CNNs) to classify the extrusion process in real‐time. The CNN models, including Xception and ResNet, are trained on a combination of real and synthetic data to classify extrusion quality (good, over, or under) across various printing scenarios, including single‐line and infill patterns. Notably, transfer learning, utilizing synthetic data for initial training followed by refinement with real‐world data enhanced classification accuracy, with the Xception model displaying 90% accuracy for single‐line extrusion and 75% for infill extrusion. This intelligent monitoring system is then coupled with a closed‐loop control system that dynamically adjusts extrusion parameters on‐the‐fly to correct errors. The platform successfully corrects both over‐ and under‐extrusion errors for alginate, collagen, and pluronic inks with varying rheological properties, demonstrating adaptability to unseen materials. Importantly, extrusion errors are corrected within ≈10 s. This novel closed‐loop bioprinting platform represents a significant advance over traditional open‐loop systems.