Аңдатпа
Digital Twin (DT) offers a structured approach to mitigating 3D printing issues in Additive Manufacturing, today’s widely used manufacturing technique. This study proposes a DT development for a large-scale Construction 3D Printer, supported by a defect-detection method. The implemented system enables activities such as real-time process monitoring and manipulation, vibration analysis, and anomaly detection. Nozzle position, vibration data, and deposited layer quality are measured in real time using sensors and intermediary tools such as Python scripts, text files, and temporary directories. These data-tracking activities aim to detect system issues such as excessive vibration levels, layer misalignment, and pinholes. Wireless motion sensors provide real-time displacement data with a 0.68 mm mean deviation and nozzle synchronization with an average latency of $\approx 299$ ms. An accelerometer produces Fast Fourier Transform (FFT) and time-domain plots during the printing process, while a microscope captures images of the freshly deposited layers, which will later be processed using computer vision. Conducted experiments confirm that this DT for a 1.8-m-high Construction 3D Printer enables practical real-time monitoring and operator-driven intervention based on the defect feedback.