The defect of the tire tread of sintering machine trolley sometimes causes the tires of sintering machine trolley to lag, stagnation, derailment and other failures, and then causes stall phenomenon of the sintering machine trolley, which sometimes even leads to production safety accidents. In order to avoid such problems, YOLOv5 detection algorithm is used for defect detection of sintering machine trolley tire tread, and, on this basis, automatic detection system for tire tread defect is designed. When the defect of the tire tread is detected, the system will start the alarm and push the defect of the tire tread through WeChat message, providing technical support for engineers to maintain in time. The results show that the detection system has a recall rate of more than 92% and a precision ratio of 100% for tire tread defect, and the target of tire tread defect missed by the system is quite small, which basically does not affect the normal operation of the sintering machine trolley tires. The system can be applied to the detection of tire tread defect in sintering machine trolley.