应用科学学报 ›› 2024, Vol. 42 ›› Issue (2): 314-322.doi: 10.3969/j.issn.0255-8297.2024.02.012

• 信号与信息处理 • 上一篇    下一篇

复杂背景和光照下双旋翼直升机桨尖间距实时测量方法

曾乐平1, 熊邦书1, 易晖2, 欧巧凤1, 余磊1   

  1. 1. 南昌航空大学 图像处理与模式识别江西省重点实验室, 江西 南昌 330063;
    2. 中国直升机设计研究所 试验试飞部, 江西 景德镇 333000
  • 收稿日期:2021-12-20 出版日期:2024-03-31 发布日期:2024-03-28
  • 通信作者: 熊邦书,教授,研究方向为智能信号处理。E-mail:xiongbs@126.com E-mail:xiongbs@126.com
  • 基金资助:
    国家自然科学基金(No.61866027);江西省重点研发计划基金(No.20212BBE53017)资助

Real-Time Measurement for Tip Clearance of Twin-Rotor Helicopter under Complex Background and Illumination

ZENG Leping1, XIONG Bangshu1, YI Hui2, OU Qiaofeng1, YU Lei1   

  1. 1. Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition, Nanchang Hangkong University, Nanchang 330063, Jiangxi, China;
    2. Test Flight Department, China Helicopter Research and Development Institude, Jingdezhen 333000, Jiangxi, China
  • Received:2021-12-20 Online:2024-03-31 Published:2024-03-28

摘要: 针对现有双旋翼直升机桨尖间距测量方法不适应室外复杂环境的问题,提出一种基于深度网络的桨尖间距实时测量方法。首先,采集桨尖图像制作数据集,搭建并训练YOLOv3-tiny网络;其次,利用训练好的网络定位桨尖区域;再次,采用OTSU分割区域图像并提取桨尖轮廓,定位上下桨尖气动中心,计算桨尖间距;最后,通过在模拟和真实环境分别开展测量实验,模拟实验结果表明本文方法精度高,相机离桨尖20 m时桨尖间距测量的最大误差为1.99 mm;真实实验结果表明本文方法适应能力强和速度快,可以适应不同复杂背景和光照下的桨尖间距测量,帧率达50 fps,已用于现场实验。

关键词: 机器视觉, 复杂环境, 双旋翼直升机, 桨尖间距测量

Abstract: In order to address the limitations of existing tip clearance measurement methods in complex outdoor environments, this paper proposes a real-time measurement method based on deep learning networks. The method utilizes the YOLOv3-tiny network to locate the rotor tip area in collected rotor tip images. The OTSU algorithm is then applied to segment the rotor tip from the background, and the rotor tip contour is extracted to locate the pneumatic center points of the upper and lower rotor tips. The rotor tip clearance is calculated based on the located center points. Experimental results conducted in both simulated and real environments demonstrate the high accuracy of the proposed method. The maximum error in tip clearance measurement is 1.99 mm when the camera is positioned 20 meters away from the tip. The proposed method has been successfully applied in real experiments involving tip clearance measurements under various complex background and illumination conditions, where the method exhibits strong adaptability and fast processing speed with a frame rate of 50 fps.

Key words: machine vision, complex environment, twin-rotor helicopter, measurement of tip clearance

中图分类号: