| 常潇丹,冯浩,殷晨波,陈鸣隽,王军.基于无人机图像的建筑起重机械表面缺陷视觉智能诊断方法[J].电子测量与仪器学报,2025,39(8):54-64 |
| 基于无人机图像的建筑起重机械表面缺陷视觉智能诊断方法 |
| Visual intelligent diagnosis method for surface defects of constructionhoisting machinery based on UAV images |
| |
| DOI： |
| 中文关键词: 表面缺陷检测 无人机图像 改进YOLOv8 建筑起重机械 EMA模块 |
| 英文关键词:surface defect detection drone images improved YOLOv8 construction crane machinery EMA module |
| 基金项目:江苏省自然科学基金（BK20221342）、国家自然科学基金（52105064）、国家重点研发计划（2021YFB2011904）、中国博士后科学基金特别资助项目（2025T180363）、江苏省研究生科研创新计划（KYCX24_1503）项目资助 |
|
|
| Author | Institution |
| Chang Xiaodan | School of Artificial Intelligence, Nanjing University of Information Science & Technology, Nanjing 210044, China |
| Feng Hao | School of Artificial Intelligence, Nanjing University of Information Science & Technology, Nanjing 210044, China |
| Yin Chenbo | School of Mechanical and Power Engineering, Nanjing Tech University, Nanjing 211816, China |
| Chen Mingjun | School of Mechanical and Power Engineering, Nanjing Tech University, Nanjing 211816, China |
| Wang Jun | Jiangsu Tianzhou Testing Co., Ltd., Nanjing 210035, China |
|
| 摘要点击次数: 806 |
| 全文下载次数: 651 |
| 中文摘要: |
| 建筑起重机械是现代工程的核心装备，其高空作业的高风险性易引发重大事故及经济损失，严重威胁安全。为了提升缺陷识别的效率和精度，降低操作人员登高巡查的风险，提出了一种基于无人机图像的表面缺陷智能检测方法FRE。建筑起重机械表面缺陷种类多样、尺度微小且背景复杂，传统YOLOv8网络因多尺度特征融合能力不足及环境适应性局限，难以实现高精度缺陷检测。利用无人机巡检施工设备，建立了钢丝绳缺陷、金属结构锈蚀两个典型的起重机械缺陷图像数据集。将YOLOv8骨干网络中的C2F模块替换为RepViT Block模块，提升模型在图像理解和处理中的性能和效率，显著降低了计算复杂度和延迟，训练速度分别提高了46.4%、2.6%；将FasterNet Block模块替换颈部网络的C2F模块，提高对缺陷的定位性能，提高了检测小目标的能力；将高效多尺度注意力（EMA）模块嵌入到骨干网络中，抑制背景信息的干扰，使模型更加关注缺陷特征。与现有的缺陷检测相比，该模型的检测精度分别达到了88.0%、94.1%。同时，模型参数量相较于YOLOv8模型下降了23.26%。结果表明，该方法可以快速、准确的检测出建筑起重机械表面缺陷，具有一定的社会应用价值。 |
| 英文摘要: |
| Construction cranes are the core equipment of modern engineering, and their high-risk operation at height is prone to cause major accidents and economic losses, seriously threatening safety. In order to improve the efficiency and accuracy of defect recognition and reduce the risk of operators climbing up to inspect, a surface defect intelligent detection method FRE based on UAV images is proposed. The surface defects of construction cranes are diverse, tiny in scale and complex in background, and the traditional YOLOv8 network is difficult to realize high-precision defect detection due to the lack of multi-scale feature fusion capability and the limitation of environmental adaptability. Utilizing the UAV inspection construction equipment, two typical lifting machine defect image datasets of wire rope defects and metal structure corrosion are established. The C2F module in the YOLOv8 backbone network is replaced with the RepViT Block module to improve the performance and efficiency of the model in image understanding and processing, which significantly reduces the computational complexity and latency, and the training speed is increased by 46.4% and 2.6%, respectively; the C2F module in the neck network is replaced by the FasterNet Block module, which improves the performance of the localization of defects and improves the ability of detecting small targets; the EMA module is embedded into the backbone network to suppress the interference of background information and make the model more focused on defect features. Compared with the existing defect detection, the detection accuracy of the model reaches 88.0% and 94.1%, respectively. Meanwhile, the number of model parameters decreased by 23.26% compared with the YOLOv8 model. The results show that the method can quickly and accurately detect the surface defects of construction cranes, which has certain social application value. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
