2025年04月05日 星期六 首页   |    期刊介绍   |    编 委 会   |    投稿指南   |    期刊订阅   |    统合信息   |    联系我们
计量学报  2022, Vol. 43 Issue (11): 1404-1411    DOI: 10.3969/j.issn.1000-1158.2022.11.03
  光学计量 本期目录 | 过刊浏览 | 高级检索 |
基于改进YOLOv4算法的轮毂表面缺陷检测
吴凤和1,崔健新1,张宁1,张志良2,张会龙1,郭保苏1
1.燕山大学机械工程学院,河北 秦皇岛 066004
2.中信戴卡股份有限公司, 河北 秦皇岛 066004
Surface Defect Detection of Wheel Hub Based on Improved YOLOv4 Algorithm
WU Feng-he1,CUI Jian-xin1,ZHANG Ning1,ZHANG Zhi-liang2,ZHANG Hui-long1,GUO Bao-su1
1. College of Mechanical Engineering, Yanshan University, Qinhuangdao, Hebei 066004, China
2. CITIC Dicastal Co. Ltd, Qinhuangdao, Hebei 066004, China
全文: PDF (3246 KB)   HTML (1 KB) 
输出: BibTeX | EndNote (RIS)      
摘要 汽车轮毂加工过程中产生的表面缺陷严重影响整车的美观性及服役性能,针对人工检测效率低、漏检率高的问题,提出一种基于改进YOLOv4算法的轮毂表面缺陷检测方法。构建了轮毂缺陷数据集,其包含6种表面缺陷,由2346张4928×3264pixel的图像组成;采用K-means方法进行先验框聚类,并针对YOLOv4算法在纤维、粘铝等小尺度缺陷上检测精度不足问题,在原网络Neck部分引入细化U型网络模块(TUM)和注意力机制,用于增强有效特征并抑制无效特征,强化多尺度特征提取与融合,改善特征处理过程中可能存在的小目标信息丢失问题;基于该数据集,训练并测试不同算法的缺陷检测性能并验证改进模块的有效性。结果表明,该方法大幅提升了粘铝等小尺寸缺陷的检测能力,缺陷检测平均精度达到85.8%,与多种算法相比较检测精度最高。
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
E-mail Alert
RSS
作者相关文章
吴凤和
崔健新
张宁
张志良
张会龙
郭保苏
关键词 计量学轮毂缺陷检测改进YOLOv4算法细化U型网络    
Abstract:The surface defects produced during the processing of automobile wheels seriously affect the aesthetics and service performance of the whole vehicle. Aiming at the problems of low manual defect detection efficiency and high missed detection rate at this stage, a method for detecting wheel surface defects based on the improved YOLOv4 algorithm is proposed. Constructed a wheel defect data set, including six types of surface defects, composed of 2346 images of 4928×3264pixel, using K-means method for priori box clustering, and focusing on YOLOv4 algorithm on small-scale defects such as fiber and sticky aluminum insufficient detection accuracy. In the Neck part of the original network, a thinned U-shaped network module (TUM) and attention mechanism are introduced to enhance effective features and suppress invalid features, strengthen multi-scale feature extraction and fusion, and improve the possibility of feature processing small target information loss problem; based on self-built data sets, training and testing the defect detection performance of different algorithms and verify the effectiveness of the improved modules, the results show that the average defect detection accuracy of the method reaches 85.8%, and it greatly improves small-size defects such as aluminum sticking. The detection ability of, the detection accuracy is the highest among many comparison algorithms.
Key wordsmetrology    wheel hub    defect detection    improved YOLOv4 algorithm    TUM
收稿日期: 2021-07-19      发布日期: 2022-11-14
PACS:  TP92  
基金资助:国家重点研发计划(2020YFB1700803);河北省高等学校科学技术研究重点项目(ZD2020156)
通讯作者: 郭保苏(1986-),男,燕山大学副教授,硕士生导师,主要从事数字化设计制造方向研究工作。Email:guobaosu@ysu.edu.cn      E-mail: guobaosu@ysu.edu.cn
作者简介: 吴凤和(1968-),男,燕山大学教授,博士生导师,主要从事智能感知与数字孪生、智能制造方向研究工作。Email:risingwu@ysu.edu.cn
引用本文:   
吴凤和,崔健新,张宁,张志良,张会龙,郭保苏. 基于改进YOLOv4算法的轮毂表面缺陷检测[J]. 计量学报, 2022, 43(11): 1404-1411.
WU Feng-he,CUI Jian-xin,ZHANG Ning,ZHANG Zhi-liang,ZHANG Hui-long,GUO Bao-su. Surface Defect Detection of Wheel Hub Based on Improved YOLOv4 Algorithm. Acta Metrologica Sinica, 2022, 43(11): 1404-1411.
链接本文:  
http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2022.11.03     或     http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2022/V43/I11/1404
京ICP备:14006989号-1
版权所有 © 《计量学报》编辑部
地址:北三环东路18号(北京1413信箱)  邮编:100029 电话:(010)64271480
本系统由北京玛格泰克科技发展有限公司设计开发  技术支持:support@magtech.com.cn