系统仿真学报 ›› 2022, Vol. 34 ›› Issue (5): 1152-1159.doi: 10.16182/j.issn1004731x.joss.20-0984

• 仿真支撑平台/系统技术 • 上一篇    下一篇

线束端子压接后外观缺陷的视觉检测算法研究

袁彬淦(), 钟铭恩(), 倪晶鑫   

  1. 厦门理工学院 福建省客车先进设计与制造重点实验室,福建  厦门  361024
  • 收稿日期:2020-12-08 修回日期:2021-01-05 出版日期:2022-05-18 发布日期:2022-05-25
  • 通讯作者: 钟铭恩 E-mail:1257044697@qq.com;zhongmingen@xmut.edu.cn
  • 作者简介:袁彬淦(1995-),男,硕士,工程师,研究方向为机器视觉技术与应用。E-mail:1257044697@qq.com
  • 基金资助:
    国家自然科学基金(51978592);福建省自然科学基金(2019J01859);厦门市科技计划(3502Z20183065)

Research on Visual Inspection Algorithm of Crimping Appearance Defects for Wiring Harness Terminals

Bingan Yuan(), Mingen Zhong(), Jingxin Ni   

  1. Fujian Key Laboratory of Bus Advanced Design and Manufacturing, Xia Men University of Technology, Xiamen 361024, China
  • Received:2020-12-08 Revised:2021-01-05 Online:2022-05-18 Published:2022-05-25
  • Contact: Mingen Zhong E-mail:1257044697@qq.com;zhongmingen@xmut.edu.cn

摘要:

针对线束端子的缺陷检测效率低、漏检率高等问题,提出一种基于机器视觉的图像检测方法:分析线束端子3个主要部位的5种典型缺陷模式,并定义了缺陷评价参数;设计了定位基准拟合算法、待检部位自适应分割算法和缺陷特征参数计算方法;给出了各类外观缺陷的判断准则。实验结果表明,检测算法适用于各单类多类混合缺陷模式,综合漏检率和误检率较低,准确率和实时性较高,能够满足实际应用要求。

关键词: 机器视觉, 图像处理, 线束, 图像分割, 缺陷检测

Abstract:

Aiming at the low efficiency and high missing rate of wiring harness terminals, an image detection method based on machine vision is proposed. The characteristic parameters of five typical defects in three main parts of wiring harness terminals are analyzed and defined. Tthe algorithms of extracting positioning datum, segmenting inspected-parts adaptively, extracting the defect features and calculating the characteristic parameters are designed respectively, and the defects criterions are given. The experimental results show that the algorithms are suitable for single defect and multi-class defects, both the miss detection rate and the false positiveness rate are low. The accuracy and real-time performance are high, and can meet the practical application requirements.

Key words: machine vision, image processing, wire harness, image segmentation, defect detection

中图分类号: