Digital Twin of Intelligent Small Surface Defect Detection with Cyber-manufacturing Systems

Abstract

The rapid advancement in cyber-physical systems has led to the evolution of Industry 4.0, with a key concept being the digital twin (DT). However, linking twin simulations with real-world scenarios remains challenging, especially in tasks like small surface defect detection. This article proposes a cyber-manufacturing system with a DT solution for small surface defect detection. The system uses an Edge-Cloud architecture for efficient data collection and processing, coupled with a deep learning-based detection algorithm utilizing multi-modal data. Experiments demonstrate high accuracy and recall in small defect detection.

Yirui Wu

Young Professor, CCF Senior Member

My research interests include Computer Vision, Artifical Intelligence, Multimedia Computing and Intelligent Water Conservancy.