基于 U-Net 网络和椭圆度量学习的防震锤锈蚀识别-《计算机技术与发展》

文章信息/Info

Title:: Identification of Anti-vibration Hammer Corrosion of High-voltage Transmission Lines Based on U-Net Network and Elliptic Metric Learning

作者:: 刘军¹; 孙庆²; 刘玮³; 康伟东³; 秦浩¹; 郭成英¹; 1. 国网安徽省电力有限公司,安徽合肥 230601; 2. 安徽大学,安徽合肥 230601; 3. 安徽南瑞继远电网技术有限公司,安徽合肥 230088

Author(s):: LIU Jun1; SUN Qing2; LIU Wei3; KANG Wei-dong3; QIN Hao1; GUO Cheng-ying1; 1. State Grid Anhui Electric Power Co. ,Ltd. ,Hefei 230601,China; 2. Anhui University,Hefei 230601,China; 3. Anhui Nanrui Jiyuan Electricity Grid Technical Co. ,Ltd. ,Hefei 230088,China

Keywords:: corrosion detection; high-voltage transmission line anti-vibration hammer; U-Net network; HSV color features; LBP texture features; metric learning

摘要:: 高压输电线路中金属锈蚀会严重危害输电线路的安全运行。针对高压输电线背景复杂、缺乏有效锈蚀检测手段以及锈蚀检测准确率低等问题,提出了一种基于 U-Net 网络和度量学习的高压输电线防震锤锈蚀检测方法。相比其他深度网络,U-Net 网络的参数量较少且直观,在小样本下具有较优的性能,利用 U-Net 网络可以将复杂背景条件下的高压输电线路中的防震锤完整分割出来。对分割后的防震锤图像提取 HSV 颜色特征和 LBP 纹理特征,并引入能够反映样本空间结构信息或语义信息的椭圆度量,通过椭圆度量学习实现高压输电线防震锤锈蚀的识别。实验结果表明,相比于支持向量机、BP 神经网络、决策树等检测方法,该方法能够高效、准确地识别复杂背景环境下的高压输电线防震锤锈蚀。

Abstract:: Metal corrosion in high-voltage transmission lines can seriously endanger the safe operation of transmission lines. Aiming at the problems of complex background of high-voltage transmission lines,lack of effective corrosion detection methods,and low accuracy of corrosion detection,we propose a method for detecting corrosion of anti-vibration hammers of high-voltage transmission lines based on U-Net network and metric learning. Compared with other deep networks,the U-Net network has fewer parameters and is intuitive with better performance in a small sample. U-Net networks can be used to completely isolate the seismic hammers in high-voltage transmission lines under complex background conditions. The HSV color features and LBP texture featu-res are extracted from the segmented seismic image,and an ellipse metric that reflects the spatial structure information or semantic information of the sample is introduced. The ellipse metric learning is used to identify the anticorrosive hammer corrosion of high - voltage power lines. Experiment shows that compared with support vector machine,BP neural network,decision tree and other detection methods,the proposed method can efficiently and accurately identify the anti-vibration hammer corrosion of high-voltage transmission lines in complex background environments.