Transfer Learning for Real-Time Surface Defect Detection With Multi-Access Edge-Cloud Computing Networks

The development of deep learning and edge computing provides rapid detection capability for surface defects. However, components produced in actual industrial manufacturing environments often have tiny surface defects and training data for each specific defect type is limited. Meanwhile, network resources at the edge of industrial networks are difficult to guarantee. It is challenging to train a proper surface defect detection model for each specific surface defect type and provide a real-time surface defect detection service. To address the challenge, in this paper, we propose a real-time surface defect detection framework based on transfer learning with multi-access edge-cloud computing (MEC) networks. Furthermore, we improve the original YOLO-v5s framework by introducing the spatial and channel attention mechanism, and adding an additional detection head to enhance the detection ability on tiny surface defects. Evaluation results demonstrate that the proposed framework has superior performance in terms of improving detection accuracy and reducing detection delay in the considered MEC network.

I. Introduction

Recently, with the rapid development of smart manufacturing and industrial automation, component production efficiency has been significantly improved [1], [2]. However, due to differences in technical level and working condition, the quality of manufactured components are easily affected, and surface defects (e.g., surface scratches, oil spot, holes and wrinkles) occur frequently [3], [4], [5]. Surface defects not only affect the aesthetics of component, but also have a significant impact on product performance. At present, manual detection methods are still widely used by various industrial component manufacturers [6]. Training workers to identify these complex and tiny surface defects has many disadvantages such as high workload and low detection accuracy, which cannot meet the requirements for defect detection consistency and high efficiency in industrial networks.