Porosity Prediction of 3D Printed Components Using U-Net and Its Variants

Additive manufacturing (AM) or 3D printing (3DP) technologies witnessed revolutionary growth in the manufacturing sector. Parts produced with metal AM techniques, especially Laser Powder Bed Fusion (LPBF), are often prone to porosity issues. The presence of pores leads to harmful effects such as crack formation and, eventually, premature failure of the component. Consequently, research in defect detection and pore prediction attracted substantial attention. Utilizing image-based porosity detection in preexisting systems is a simple, effective, and cost-efficient approach for final part inspection. This paper investigates the possibility of predicting porosity using U-Net and its novel network architectures RU-Net and RAU-Net, on an X-ray computed tomography (XCT) image dataset. RAU-Net outperforms RU-Net and U-Net in detecting more than 90 % of actual pores while retaining $95 \%$ precision. While RU-Net and U-Net required additional training, RAU-Net achieved high performance in only 50 epochs, demonstrating its data efficiency and convergence. Due to its shorter training period also leading to lower computational overhead, RAU-Net is suited for practical high throughput, low latency applications. Particularly in timesensitive applications, RAU-Net can enable more widespread adoption of dense prediction networks.