电力巡检无人机精准降落方法研究与应用  

Research and Application of Adaptive Landing Method of Electric Patrol UAV

作　　者：王永强 车凯 戴铎 王红星[2] 高超 黄郑 WANG Yong-qiang;CHE Kai;DAI Feng;WANG Hong-xing;Gao Chao;HUANG Zheng(State Grid Jiangsu Electric Power Co.,Ltd.Nanjing,Jiangsu 210024,China;Jiangsu Frontier Electric Power Technology Co.,Ltd.,Nanjing,Jiangsu,211102,China)

机构地区：[1]国网江苏省电力有限公司,江苏南京210024 [2]江苏方天电力技术有限公司,江苏南京211102

出　　处：《计算技术与自动化》2021年第2期41-46,共6页Computing Technology and Automation

基　　金：国家电网有限公司科技项目(2019-4201-13-001179)。

摘　　要：针对现有电力巡检无人机降落方法定位误差较大、机身稳定性较差、易受外部环境干扰等问题,提出一种电力巡检无人机自适应降落方法。构建基于多级视觉标识图像识别的四维定位降落方法,指引无人机进行垂直方向精确降落。开发基于分段式反馈控制的速度矢量的四维控制方法,稳定无人机水平方向的姿态。设计基于视觉标识阵列的自适应抗干扰降落方法,克服降落平台的阴影对无人机定位的影响。开展无人机精准降落现场实验,结果表明所提方法具有非常高的降落定位精度,简单实用。Aiming at the problems of large positioning error,poor fuselage stability and susceptibility to external environment disturbance in the existing landing methods for electric patrol unmanned aircraft vehicle(UAV),a new landing and positioning method is proposed:a four-dimensional landing method based on multi-level visual identification image recognition is proposed to guide the UAV to land vertically;a four-dimensional velocity vector control based on piecewise feedback control is proposed to stabilize the UAV′s horizontal attitude;an adaptive anti-interference landing method based on visual identification array is proposed to overcome the influence of the shadows of landing platform.Field experiments were carried out using the developed UAV.The results show that the proposed method has very high positioning accuracy,high computational efficiency,and it is simple and practical.

关 键 词：电力巡检无人机 四维垂直定位 计算机视觉 四维速度矢量控制 自适应抗干扰 

分 类 号：TM755[电气工程—电力系统及自动化]