Researchers have developed an IoT-enhanced deep learning system for detecting cracks in additive manufacturing. The framework integrates real-time monitoring, edge computing, and convolutional neural networks (CNNs) to achieve high accuracy in defect classification. It supports supervised and semi-supervised learning, demonstrating 99.54% accuracy on a large dataset and improving generalization through data balancing and augmentation. The system also links manufacturing parameters to defect formation and incorporates Digital Twin technology for predictive analytics and process control. AI
影响 Enhances quality control in additive manufacturing with high-accuracy, real-time defect detection and predictive analytics.
排序理由 This is a research paper detailing a novel framework for crack detection using IoT and CNNs.
AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →
