【摘要】 针对港口起重机人工巡检效率低、安全性差的问题，给出一种基于无人机的智能巡检方案。方案结合RTK定位与三维建模技术，实现精确建模；采用改进的A*算法完成航迹规划，并引入Resnet18网络结构对锈蚀、裂纹、油漆脱落等缺陷进行自动识别。经工程验证，该方案在路径执行稳定性、图像采集质量和缺陷识别准确率方面均表现优异，可显著提升港口设备的巡检效率与安全水平，为智慧港口建设提供有效的技术支撑。更多还原

【Abstract】 To address the problems of low efficiency and poor safety associated with manual inspection of port cranes, this paper proposes an intelligent inspection system based on an unmanned aerial vehicle(UAV).The system integrates RTK positioning and 3D modeling technology to achieve precise modeling.An improved A* algorithm is used for flight path planning, and the ResNet18 network architecture is introduced to automatically identify defects such as rust, cracks, and paint peeling.Engineering validation has demonstrated that the system performs excellently in terms of path execution stability, image acquisition quality, and defect recognition accuracy, significantly improving the inspection efficiency and safety level of port equipment, thereby providing effective technical support for the development of smart ports.更多还原