北京航空航天大学学报 ›› 2021, Vol. 47 ›› Issue (4): 682-689.doi: 10.13700/j.bh.1001-5965.2020.0321

• 论文 • 上一篇    下一篇

基于R-D SSD模型航空发动机安装工位检测算法

陈科山1,2, 郝宇1, 何泓波1, 李坤龙1   

  1. 1. 北京交通大学 机械与电子控制工程学院, 北京 100044;
    2. 北京交通大学 载运工具先进制造与测控技术教育部重点实验室, 北京 100044
  • 收稿日期:2020-07-06 发布日期:2021-04-30
  • 通讯作者: 陈科山 E-mail:kshchen@bjtu.edu.cn
  • 作者简介:陈科山,男,博士,教授,硕士生导师。主要研究方向:机器人设计与控制技术、计算机视觉与图像识别技术、智能交通与新能源技术等;郝宇,男,硕士研究生。主要研究方向:计算机视觉与图像识别技术。
  • 基金资助:
    国家自然科学基金(51735009)

Detection algorithm of aeroengine installation station based on R-D SSD model

CHEN Keshan1,2, HAO Yu1, HE Hongbo1, LI Kunlong1   

  1. 1. School of Mechanical, Electronic and Control Engineering, Beijing Jiaotong University, Beijing 100044, China;
    2. Key Laboratory of Advanced Manufacturing and Measurement and Control Technology of Transport Tools, Ministry of Education, Beijing Jiaotong University, Beijing 100044, China
  • Received:2020-07-06 Published:2021-04-30
  • Supported by:
    National Natural Science Foundation of China (51735009)

摘要: 为解决航空发动机在安装过程中大多实行人工安装、定位不精确等问题,在研究其自动化安装方法中,针对航空发动机安装工位的检测需求,提出了一种残差网络与膨胀卷积相融合的SSD改进算法(R-D SSD)。将经典SSD模型的主干网络VGG16替换为残差网络ResNet-101,并增加其输出特征图上的预选框数量,解决了原始算法对底层特征抓取能力不足的问题,进而弥补了对小目标检测效果较差的缺陷;利用膨胀卷积扩大网络的感受野,获取足够的安装工位边缘特征细节信息,在不改变网络结构的同时,保证了模型良好的实时性和对目标的检测精度。实验表明:对于小目标数据集和整个数据集,R-D SSD算法的平均检测精度较原始算法分别提高了8.6%和4.0%,可以满足航空发动机安装时平均检测精度不低于85%的要求。

关键词: 安装工位, 残差网络, 膨胀卷积, SSD模型, 小目标检测, 预选框数量

Abstract: In order to solve the problems of manual installation and inaccurate positioning in the process of aeroengine installation, an improved SSD algorithm (ResNet-Dilated SSD, R-D SSD) is proposed to meet the detection requirements of aeroengine installation station in the research of its automatic installation method. The VGG16, the backbone network of classical SSD model, is replaced by the residual network ResNet-101 and the number of preselected boxes on output feature map is increased, which solves the problem that original algorithm has insufficient ability to grasp the underlying features, and thus results in poor detection effect of small target. The dilation convolution is used to expand the network’s receptive field to obtain enough edge feature information of installation station, which ensures the good real-time performance of the model and the detection accuracy of the target without changing the network structure. The experimental results show that the average detection accuracy of the R-D SSD detection algorithm is 8.6% and 4.0% higher than that of original algorithm for the small target dataset and the whole dataset. It can meet the requirement that the average detection accuracy is not less than 85% when the aeroengine is installed.

Key words: installation station, residual network, dilation convolution, SSD model, small target detection, number of preselected boxes

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发