摘要
针对现有输电线路覆冰厚度检测方法存在的泛化能力和适应性差的问题,基于渝东地区采集到的数据,研究了输电线路覆冰图像识别的改进方法。利用自适应开关中值滤波和Otsu阈值分割法对目标图像进行再处理和Canny算子优化,建立了基于边缘检测的导线覆冰厚度识别法。通过识别结果和光纤检测数据对比发现:所使用的方法对输电线路覆冰厚度的检测有效,平均误差为4.10%。
Transmission line icing seriously endangers the safe operation of power system,and the detection of transmission line icing thickness is particularly important.Based on the data collected in Yudong area,this paper studies the improved method of transmission line icing image recognition.The adaptive switching median filter and Otsu threshold segmentation method are used to reprocess the target image and optimize the Canny operator,and a method for identifying the ice thickness of the conductor based on edge detection is established.After comparing the identification results with the optical fiber detection data,it is found that the method used in this paper is effective for the detection of transmission line icing thickness,with an average error of about 4.10%.
作者
韩兴波
王杰
孙鹏
邢镔
蒋兴良
HAN Xingbo;WANG Jie;SUN Peng;XIN Bin;JIANG Xingliang(School of Mechatronics and Vehicle Engineering,Chongqing Jiaotong University,Chongqing 400074,China;Chongqing Innovation Center of Industrial Big-Data Co.,Ltd.,Chongqing 400707,China;State Key Laboratory of Power Transmission Equipment&System Security and New Technology,Chongqing University,Chongqing 400044,China)
出处
《重庆理工大学学报（自然科学）》
北大核心
2023年第8期265-273,共9页
Journal of Chongqing University of Technology：Natural Science
基金
国家自然科学基金重点项目(51637002)
国家自然科学基金项目(52307161)
重庆市教育委员会科学技术研究计划项目(KJQN202000727)。
