Scholarlink

This study presents an automated defect detection system for smart factories utilizing advanced deep learning models. The approach leverages convolutional neural networks (CNNs) and transfer learning techniques, employing pre-trained architectures such as VGGNet, ResNet, DenseNet, MobileNetV2, and InceptionV3. This system aims to enhance real-time quality assurance by reducing manual effort, improving production efficiency, and achieving high accuracy in defect classification. The proposed framework contributes to advancing Industry 4.0 practices, emphasizing the integration of IoT and AI in manufacturing. Experimental evaluations demonstrate significant improvements in defect detection accuracy, operational cost reduction, and production scalability.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Smart Factory Product Defect Detection Using Deep Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Deo Prakash,
  • Arya Singh,
  • Yash Deep Singh Bais,
  • Vasihnavi Majumdar,
  • Eshani Patel,
  • Om Prakash Sahu

摘要

This study presents an automated defect detection system for smart factories utilizing advanced deep learning models. The approach leverages convolutional neural networks (CNNs) and transfer learning techniques, employing pre-trained architectures such as VGGNet, ResNet, DenseNet, MobileNetV2, and InceptionV3. This system aims to enhance real-time quality assurance by reducing manual effort, improving production efficiency, and achieving high accuracy in defect classification. The proposed framework contributes to advancing Industry 4.0 practices, emphasizing the integration of IoT and AI in manufacturing. Experimental evaluations demonstrate significant improvements in defect detection accuracy, operational cost reduction, and production scalability.