Wire rope is an indispensable production machinery in coal mines. It is the main force-bearing equipment of the underground traction system. Accurate detection of wire rope defects and positions plays an extremely important role in safe production. The existing defect detection solutions have some deficiencies in the flexibility, accuracy and real-time performance of wire rope defect detection. In order to solve the above problems, this paper uses the camera to sample the wire rope before the well entry, and proposes an object based on YOLO V5. The surface small defect detection model realizes the accurate detection of small defects outside the wire rope. The transfer learning method is also introduced to improve the model accuracy of small sample training. After a large number of experiments, it is shown that in the task of wire rope defect detection, the average correctness rate and the average accuracy rate of the model are significantly improved compared with those before the modification, and the detection speed can be maintained at a real-time level.