Find in Library

Hot-rolled steel strip is widely used in production life and surface defects inevitably occur during its production process. In order to solve this problem, this paper proposes a method for classifying and locating surface defects in hot-rolled strip steel based on the YOLOV7 target detection model, which takes into account both accuracy and real-time performance. The method is capable of distinguishing seven common surface defects with an average accuracy of 84,3 % and a maximum accuracy of 99,6 % in a single category of defects.