基于图像的高压输电线间隔棒故障诊断方法

Method of Spacer Fault Diagnose on Transmission Line Based on Image Procession

利用无人机巡检高压输电线路故障,可以解决传统人工观测故障巡检方式的成本高、效率低等问题。为此,提出了一种基于可见光图像识别间隔棒框架断裂故障的方法。首先利用图像匹配和形态学运算从图像中提取出间隔棒,校正透视畸变后进行骨架提取,最后用加权的不变矩值进行形状度量,并根据最小风险原则设计了分类方法。对32幅间隔棒图像(其中故障图像10张)进行了计算,数据显示,2类图像的相关值具有良好的区分度,应用该方法能识别出所有故障图片。结果表明,提出的方法可有效对框架断裂故障间隔棒进行检测。

Using unmanned aerial vehicle to complete inspection of transmission lines could effectively solve the problem of high costs and low efficiency in traditional inspections that mainly depends on trained workers.Therefore,a novel fault-detecting method of spacers on transmission line based on images in visible wavelengths is presented.Firstly,by image matching and morphological calculation,spacers are located and extracted from sample images.Then,frames of the spacers are extracted after correction of perspective deformation,and the shapes of the frames are measured using weighted invariant moments.Finally,a method following the principle of minimum risks is proposed to judge whether there is a fault or not.32 images of spacers,ten of which were taken from faulty spacers,were analyzed using the presented method.The results show that the two kinds of images can be distinguished easily,which means the ones of spacers with faults can be figured out effectively.It is concluded that the presented method is effective to detect faulty spacers with frame fractures.