Aiming at the safety hidden problem caused by overhead contact wire defects during railway operation, an improved YOLOv7x method for overhead contact wire defect identification was proposed. Firstly, Swin Transformer network is introduced at the end of the backbone feature extraction layer to replace the original extended and efficient layer aggregation network module, so as to improve the ability of the network to grasp global information. Then the SIoU(SCYLLA-IoU) loss function is used to replace the original network loss function, and the direction penalty mechanism is added to the convergence process of the prediction frame. Finally, Coordinate Attention is used to integrate the extended efficient layer in the neck layer to aggregate the network module, enhance the global receptive field of the neck network module. Experimental simulation results show that the accuracy of the model trained by the improved algorithm reaches 95.9%, which is 4.7% higher than that of the original YOLOv7x algorithm, and the detection speed reaches 52 frames per second. The improved algorithm solves the problem of low detection efficiency in the field of hanging strings defect identification, and can improve the efficiency of detection of hanging strings defect in practice.