基于级联网络的螺栓锈蚀检测方法研究  

Research on bolt corrosion detection method based on cascade network

在线阅读下载全文

作  者:邓伟 王洪亮[2] DENG Wei;WANG Hongliang(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650031,China;Faculty of Civil Aviation and Aeronautics,Kunming University of Science and Technology,Kunming 650500,China)

机构地区:[1]昆明理工大学信息工程与自动化学院,云南昆明650031 [2]昆明理工大学民航与航空学院,云南昆明650500

出  处:《现代电子技术》2023年第19期111-115,共5页Modern Electronics Technique

基  金:国家自然科学基金资助项目(62163021)。

摘  要:螺栓作为输电线路中连接各金具的重要紧固件,长期处于恶劣环境中容易产生锈蚀,导致金具间连接不稳定,对输电线路的安全运行造成威胁。针对螺栓在巡检图像中占比较小,且背景复杂,难以检测出螺栓锈蚀故障,文中提出一种基于级联网络的螺栓锈蚀检测方法。首先利用改进YOLOX算法定位输电线路图像中螺栓的位置,通过位置信息裁剪螺栓目标,增大其在图片中的占比率;其次将螺栓图像转换为HSV图像,确定锈蚀区域各分量的阈值;然后,对图像进行二值化处理,实现对螺栓锈蚀的检测;最后,采用建立的螺栓数据集进行仿真实验,结果表明文中提出方法能够有效、精确地实现输电线路图像中螺栓锈蚀故障的检测。As important fasteners connecting various fittings in power transmission lines,bolts are prone to rust due to long⁃time exposure to hush environments,which results in unstable connections between fittings and poses a threat to the safe operation of power transmission lines.It is difficult to detect bolt corrosion faults because bolts'small proportions in the inspection images and the complex image backgrounds.Therefore,a bolt corrosion detection method based on cascade network is proposed.Firstly,the improved YOLOX algorithm is used to locate the bolt position in the image of the power transmission lines,and the bolt(the object)is cut out according to the position information,so as to increase its proportion in the image.And then,the bolt image is converted into an HSV image to determine the threshold of each component of the corrosion area.The image is binarized to realize the detection of bolt corrosion.Finally,the established bolt data set is used for simulation experiments.The results show that the proposed method can effectively and accurately detect bolt corrosion faults in the images of power transmission lines.

关 键 词:螺栓锈蚀检测 YOLOX 二值化 HSV颜色模型 CBAM 检测准确率 

分 类 号:TN911.73-34[电子电信—通信与信息系统] TM391.41[电子电信—信息与通信工程] TM75[电气工程—电机]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象