Advancing Industry 4.0 with Cloud-Integrated Cyber-Physical Systems for Optimizing Remote Additive Manufacturing Landscape

Background: The growth of digital technologies, such as IoT and Cyber-Physical Production Systems (CPPS), is driving the Fourth Industrial Revolution. Additive Manufacturing (AM) plays a key role in this revolution but raises concerns regarding intellectual property (IP) theft and quality control due to the lack of physical interaction with printers. Methodology: This paper proposes a cloud-integrated cyber-physical system (CPS) for defect detection in AM using deep learning models. Two models, AlexNet and InceptionV3, were trained on a dataset of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$1,5573 \mathrm{D}$</tex> printer images. The models were deployed in a cloud environment for real-time monitoring and adaptive retraining. Results: Performance evaluation showed that AlexNet achieved 99% classification accuracy, while InceptionV3 achieved 97 %, significantly outperforming baseline models such as ResNet101 (86%), VGG16 (95%), and DNN (82%). The proposed models demonstrated superior defect detection and quality control capabilities in AM. Conclusion: The proposed CPS framework integrates Industry 4.0 technologies for automated and remote defect detection in AM.