Hybrid physical model and status data-driven approach for quality-reliable digital light processing 3D printing

Existing methods for detecting anomalies in digital light processing (DLP) 3D printing and performing in-situ repairs can reduce most defects and improve success rates. However, since printing control parameters cannot adapt to real-time printing conditions, anomalies may persist across successive layers, and continuous repairs could ultimately lead to printing failure. Therefore, achieving stable printing quality requires integrating anomaly detection with the dynamic adjustment of control parameters. In this paper, we propose a hybrid approach that combines physical models with real-time status data to achieve quality-reliable DLP 3D printing. We developed a status data acquisition scheme to monitor printing status, including the downward force exerted on the printing platform, curing temperatures, resin levels, and surface morphology. Analyzing the collected data provides both status and anomaly information, enabling in-situ repair strategies to address abnormalities with minimal disruption to the printing process. Additionally, an Extended Kalman Filter integrates status data with physical models to dynamically optimise printing parameters. Experimental results show that the proposed scheme effectively addresses typical anomalies, optimises printing times, and significantly improves success rates while preserving the mechanical performance of printed models. Furthermore, the approach adapts to varying printing status, resin materials, and models.