汽车轮毂表面缺陷检测技术分析与装置设计

doi:10.3969/j.issn.1000-1158.2024.06.05

摘要
图/表
参考文献(69)
相关文章 (15)

全文: PDF (797 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要机器视觉作为代替人工检测轮毂表面缺陷的重要手段,是目前该领域的主要研究方向,因此针对汽车轮毂表面缺陷检测技术的研究现状进行了综述与分析。首先,从轮毂表面缺陷的类别和人工检测流程入手,阐述了基于机器视觉的轮毂表面缺陷检测技术的要求和难点。其次,分析了基于机器视觉的智能检测算法的发展历程,包括传统的机器视觉方法在缺陷图像预处理、缺陷定位和特征提取、缺陷分类识别中的应用;卷积神经网络(CNN)等深度学习方法在缺陷检测、分割以及其他方面的应用。最后,介绍了现有轮毂型号识别装置、轮毂缺陷X射线图像采集装置、轮毂表面缺陷图像采集装置,并在分析当前基于机器视觉的智能检测装置在实际应用中的局限性及需要解决的若干关键技术问题的基础上,提出了3种智能检测实验装置设计方案,为全自动快速检测装置的研制与性能提升提供理论与技术支撑。

	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
	刘福才
	张震宇
	徐继龙
	郑宏伟
	刘阳

关键词 ：机器视觉, 汽车轮毂, 表面缺陷检测, 深度学习, 智能检测装置

Abstract：Machine vision, as an important method to replace manual detection of wheel hub surface defects, is currently the main research direction in this field. Therefore, a summary and analysis of the research status of surface defect detection technology for automotive hubs is conducted. Firstly, starting with the categories of wheel surface defects and manual detection process, the requirements and difficulties of machine vision-based wheel surface defect detection technology are expounded. Then, the development of intelligent detection algorithms based on machine vision is analyzed, including the application of traditional machine vision methods in defect image preprocessing, defect location and feature extraction, defect classification and recognition, also including the application of deep learning methods such as convolutional neural networks (CNN) in defect detection, segmentation, and other applications. Finally, the existing hub type recognition device, hub defect X-ray image acquisition device, hub surface defect image acquisition device are introduced. On the basis of analyzing the limitations and key technical issues that need to be solved in practical applications of current machine vision based intelligent detection devices, three kinds of intelligent detection experimental device design schemes are proposed. It provides theoretical and technical support for the development and performance improvement of automatic rapid detection device.

Key words： machine vision;automobile wheel surface defect detection deep learning intelligent detection device

收稿日期: 2023-11-08 发布日期: 2024-06-06

PACS:

TB96

基金资助:河北省自然科学基金(F202220304);河北省高端装备产业技术研究中心学科交叉技术创新重点项目(H20201103)

作者简介: 刘福才(1966-),黑龙江勃利人,燕山大学教授,主要从事空间机构运动特性分析与控制。Email:lfc@ysu.edu.cn

引用本文:

刘福才,张震宇,徐继龙,郑宏伟,刘阳. 汽车轮毂表面缺陷检测技术分析与装置设计[J]. 计量学报, 2024, 45(6): 806-818.
LIU Fucai,ZHANG Zhenyu,XU Jilong,ZHENG Hongwei,LIU Yang. Technology Analysis and Device Design for Automobile Wheel Hub Surface Defect Detection. Acta Metrologica Sinica, 2024, 45(6): 806-818.

链接本文:

http://jlxb.china-csm.org:81/Jwk_jlxb/CN/10.3969/j.issn.1000-1158.2024.06.05 或 http://jlxb.china-csm.org:81/Jwk_jlxb/CN/Y2024/V45/I6/806

［1］	宋春强. 铝合金汽车轮毂的市场需求与发展趋势［J］. 铝加工, 2006(5): 5-8.
	SONG C Q. Market Demand and Development Trend of Aluminum Wheels for Automobile［J］. Aluminum Processing, 2006(5): 5-8
	LIU H B, KANG G W. Surface Defects Inspection of Cold Rolled Strips Based on Neural Network［J］. Journal of Image and Graphics, 2005(10): 1310-1313.
［4］	石敏, 乔昆磊, 王素琴, 等. 基于语义分割的密封圈缺陷检测方法研究［J］. 高技术通讯, 2021, 31(12): 1239-1247.
	SHI M, QIAO K L, WANG S Q, et al. Research on defect detection method of sealing ring based on semantic segmentation［J］. High Technology Letters, 2021, 31(12): 1239-1247.
［5］	STRECKER H. Scatter Imaging of Aluminum Castings Using an X-Ray Fan Beam and A Pinhole Camera［J］. Materials Evaluation, 1982, 40(10): 1050-1056.
［7］	MERY D, JAEGER T, FILBERT D. A review of methods for automated recognition of casting defects［J］. Insight: Non Destructive Testing & Condition Monitoring, 2002, 44(7): 428-436.
［8］	MERY D, FILBERT D. Automated flaw detection in aluminum castings based on the tracking of potential defects in a radioscopic image sequence［J］. IEEE Transactions on Robotics and Automation, 2003, 18(6): 890-901.
［10］	CARRASCO M, MERY D. Automatic multiple view inspection using geometrical tracking and feature analysis in aluminum wheels［J］. Machine Vision and Applications, 2011, 22(1): 157-170.
［12］	张连玉, 孙晓岩. X射线实时成像技术在汽车零件检测中的应用与研究［J］. 汽车工艺与材料, 2004(7): 105-107.
	ZHANG L Y, SUN X Y. Application and Research of X-Ray Real Time Imaging Technology in Automobile Parts Inspection［J］. Automobile Technology & Material, 2004(7): 105-107.
［13］	荆峰. X射线实时成像系统在汽车轮辋检测中的应用［J］. 无损检测, 2004(8): 425-427.
［14］	陆斌. 铝, 镁铸件的X光检测及其接受标准［C］//中国机械工程学会, 中国机械工程学会铸造分会. 2009中国铸造活动周论文集. 中国,威海, 2009:786-795.
［15］	陆斌. 车轮生产的X光检测［J］. 汽车工艺师, 2011(6): 54-57.
［16］	吕金旗. 低压铸造轮毂缺陷X射线检测系统的原理及应用［J］. 特种铸造及有色合金, 2013, 33(2): 155-156.
［18］	谈绍熙, 黄茜. 一种轮毂X光图像的快速区域分割方法［J］. 计算机应用, 2006(S1): 19-20.
	TAN S X, HUANG Q. A fast region segmentation method for hub X-ray images［J］. Computer Applications, 2006(S1): 19-20.
［21］	何再兴. 基于目标提取与匹配的汽车轮毂铸件缺陷检测技术研究［D］. 杭州: 浙江大学, 2008.
［2］	刘红冰, 康戈文. 基于神经网络的冷轧带钢表面缺陷检测［J］. 中国图象图形学报, 2005(10): 1310-1313.
［3］	董正天, 刘斌, 胡春海, 等. 基于机器视觉的丝印样板表面缺陷检测方法研究［J］. 高技术通讯, 2020, 30(12): 1309-1316.
［9］	MERY D. Automated radioscopic testing of aluminum die castings ［J］. Materials Evaluation, 2006, 64(2): 135-143.
［11］	刘明利, 谢晋, 于革刚, 等. 汽车铝合金轮毂的在线无损检测［J］. 无损探伤, 2000(2): 41-43.
	LU B. X-ray inspection of wheel production［J］. Auto Manufacturing Engineer, 2011(6): 54-57.
	L J Q. Application of X-Ray NDT in Casting Aluminum Alloy Wheel［J］. Special Casting & Nonferrous Alloys, 2013, 33(2): 155-156.
	LIU J, TAO W D. Application of X-Ray Digital Radiography in Casting Aluminum Alloy Wheel［J］. Nondestructive Testing Technology, 2017, 41(3): 42-44.
［20］	LI X, TSO S K, GUAN X P, et al. Improving Automatic Detection of Defects in Castings by ApplyingWaveletTechnique［J］. IEEE Transactions on Industrial Electronics, 2006, 53: 1927-1934.
［22］	何再兴, 张树有, 黄长林. 基于缺陷特征与种子填充的轮毂缺陷检测方法［J］. 浙江大学学报(工学版), 2009, 43(7): 1230-1237.
［23］	张淑娴, 程耀瑜. SUSAN算子在汽车铝轮毂缺陷边缘检测中的应用［J］. 信息技术, 2009, 33(4): 74-76.
［24］	张俊生, 王明泉, 郭永亮, 等. 影响X射线数字成像系统分辨率的因素分析［J］. CT理论与应用研究, 2011, 20(2): 227-234.
［25］	张俊生. 基于动态阈值分割的汽车轮毂缺陷检测技术研究［D］. 太原: 中北大学, 2012.
［6］	BOERNER H, STRECKER H. Automated X-ray inspection of aluminum castings［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1988, 10(1): 79-91.
	JIN F. Application of Radiographic Real-time Imaging System to the Inspection of Auto Rims［J］. Nondestructive Testing, 2004(8): 425-427.
［19］	司徒武超. 基于X射线成像的铸件缺陷智能检测系统设计与实现［D］. 广州: 华南理工大学, 2007.
［26］	唐亚健. 基于机器视觉的轮毂精加工面质量在线检测装置研制［D］. 沈阳: 沈阳工业大学, 2018.
［29］	邓耀力. 基于机器视觉的轮毂轴承缺陷检测方法研究［J］. 中国设备工程, 2019(13): 106-108.
［30］	赵娜娜, 陶溢, 李芬, 等. 高铁轮毂表面缺陷的视觉显著性超像素图像检测方法［J］. 科学技术与工程, 2019, 19(32): 230-235.
［33］	MERY D, CHACON M, MUNOZ L, et al. Automated inspection of aluminium castings using classifier fusion strategies. ［J］. Materials Evaluation, 2005, 63(2): 148-153.
［34］	OSMAN A, KAFTAN D JIAN V, HASSLER U. Improvement of X-ray castings inspection reliability by using Dempster-Shafer data fusion theory［J］. Pattern Recognition Letters, 2011, 32(2): 168-180.
［37］	张国胜, 张帆, 邹洵, 等. 基于改进遗传算法的轮毂缺陷检测研究［J］. 农业装备与车辆工程, 2021, 59(2): 100-104.
［38］	李飞, 唐亚健, 苑玮琦. 摩托车轮毂表面缺陷检测研究［J］. 机械设计与制造, 2020(8): 296-299.
	DING J, WANG M Q, ZHANG J S, et al. Defect Enhancement and Character Removal Technology of Defect Detection of Automobile Hub［J］. Science Technology and Engineering, 2017, 17(35): 76-81.
［41］	丁杰. 汽车轮毂缺陷自动分割与识别技术研究［D］. 太原: 中北大学, 2018.
［43］	MERY D, RIFFO V, ZSCHERPEL U, et al. GDXray: The Database of X-ray Images for Nondestructive Testing［J］. Journal of Nondestructive Evaluation, 2015, 34(4): 1-12.
［45］	FERGUSON M, AK R, LEE Y , et al. Automatic localization of casting defects with convolutional neural networks［C］//IEEE. IEEE International Conference on Big Data (Big Data). Boston, USA, 2017: 1726-1735.
［49］	HAN K, SUN M, ZHOU X, et al. A new Method in Wheel Hub Surface Defect Detection: Object Detection Algorithm Based on Deep Learning［C］//IEEE. International Conference on Advanced Mechatronic Systems (ICAMechS). Xiamen, China, 2017: 335-338.
［50］	韩凯. 基于深度学习的汽车轮毂表面缺陷在线检测算法［D］. 北京: 北京邮电大学, 2019.
［52］	SUN X H, GU J N, HUANG R, et al. Surface Defects Recognition of Wheel Hub Based on Improved Faster R-CNN［J］. Electronics. 2019, 8(5): 481.
［56］	郭瑞琦, 王明泉, 张俊生, 等. 基于U-Net卷积神经网络的轮毂缺陷分割［J］. 自动化与仪表, 2020, 35(4): 43-47.
［58］	王陶然. 基于深度学习的轮毂缺陷检测研究［D］. 太原: 中北大学, 2021.
［63］	SUN X H, GU J N, WANG M M, et al. Wheel Hub Defects Image Recognition Base on Zero-Shot Learning［J］. Applied Sciences. 2021, (11): 1529.
	DONG Z T, LIU B, HU C H, et al. Research on surface defect detection method of screen printing template based on machine vision［J］. High Technology Letters, 2020, 30(12): 1309-1316.
	LIU M L, XIE J, YU G G, et al. On-line nondestructive testing of automotive aluminum alloy wheels ［J］. Nondestructive Testing Technology, 2000(2): 41-43.
［17］	刘军, 陶维道. X射线数字成像技术在铸造铝合金轮毂检测中的应用［J］. 无损探伤, 2017, 41(3): 42-44.
	ZHANG S X, CHENG Y Y. Research on defect edge detectionon on auto rims image by using SUSAN operation［J］. Information Technology, 2009, 33(4): 74-76.
	ZHAO N N, TAO Y, LI F, et al. Visual saliency superpixel image detection method for surface defect of high-speed rail hub surface defect of high-speed rail hub［J］. Science Technology and Engineering, 2019, 19(32): 230-235.
	LI F, TANG Y J, YUAN W Q. The research on surface defects detection of motorcycle hub［J］. Machinery Design & Manufacture, 2020(8): 296-299.
［46］	FERGUSON M, LEE Y T, NARAYANAN A, et al. A Standardized PMML Format for Representing Convolutional Neural Networks with Application to Defect Detection［J］. Smart and sustainable manufacturing systems, 2019, 3(1): 79-97.
	WANG C, ZHANG X F, LIU C, et al. Detection method of wheel hub weld defects based on the improved YOLOv3［J］. Optics and Precision Engineering, 2021, 29(8): 1942-1954.
［54］	Yu Y L, Wang M L, Wang Z M, et al. Surface Defect Detection of Hight-speed Railway Hub Based on Improved YOLOv3 Algorithm［C］//IEEE. 2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), Chongqing, China, 2021: 1386-1390.
	GUO R Q, WANG M Q, ZHANG J S, et al. Hub Defect Segmentation Based on U-Net Convolutional Neural Network［J］. Automation & Instrumentation, 2020, 35(4): 43-47.
	Cheng S H, Lu J X, Zhang D F, et al. Wheel Hub Identification of Convolutional Neural Networks Based on Ring Features［J］. Acta Metrologica Sinica, 2022, 43(11): 1404-1411.
［60］	曹富强. 基于卷积神经网络的轮毂缺陷自动检测算法研究［D］. 太原: 中北大学, 2022.
［64］	麻金贺. 轮毂在线识别系统的研究［D］. 秦皇岛: 燕山大学, 2014.
［66］	宋辉, 李钊. 基于工业机器人的汽车轮毂表面缺陷的视觉检测系统设计［J］. 计算机测量与控制, 2018, 26(9): 13-16.
［67］	李钊. 基于机械臂的复杂曲面的视觉检测系统设计［D］. 沈阳: 沈阳工业大学, 2018.
［68］	姚波, 温秀兰, 焦良葆, 等. 改进YOLOv3算法用于铝型材表面缺陷检测［J］. 计量学报, 2022, 43(10): 1256-1261.
	HE Z X, ZHANG S Y, HUANG C L. Approach to detecting defects in wheels based on flaws’ characteristics and seeded region growing method［J］. Journal of Zhejiang University(Engineering Science), 2009, 43(7): 1230-1237.
	ZHANG J S, WANG M Q, GUO Y L, et al. Analysis of X-ray digital imaging system resolution［J］. CT Theory and Applications, 2011, 20(2): 227-234.
	DENG Y L. Research on the Method of Defect Detection of Hub Bearings Based on Machine Vision［J］. China Plant Engineering, 2019(13): 106-108.
［32］	HERNNDEZ S, SAEZ D, MERY D. Neuro-Fuzzy Method for Automated Defect Detection in Aluminium Castings［C］// Association for Image and Machine Intelligence. International Conference on Image Analysis and Recognition(ICIAR). Porto, Portugal, 2004: 826-833.
	ZHANG G S, ZHANG F, ZOU X, et al. Research on Wheel Hub Defect Detection Based on Improved Genetic Algorithm［J］. Agricultural Equipment & Vehicle Engineering, 2021, 59(2): 100-104.
［40］	丁杰, 王明泉, 张俊生, 等. 汽车轮毂缺陷检测中的缺陷增强与字符去除技术［J］. 科学技术与工程, 2017, 17(35): 76-81.
［44］	MERY D, ARTETA C. Automatic Defect Recognition in X-Ray Testing Using Computer Vision［C］//IEEE. 2017 IEEE Winter Conference on Applications of Computer Vision (WACV). Santa Rosa, USA, 2017: 1026-1035.
［48］	MERY D. Aluminum Casting Inspection using Deep Object Detection Methods and Simulated Ellipsoidal Defects［J］. Machine Vision and Applications, 2021, 32(3): 1-16.
［53］	王宸, 张秀峰, 刘超, 等. 改进YOLOv3的轮毂焊缝缺陷检测［J］. 光学精密工程, 2021, 29(8): 1942-1954.
	GUO R Q, WANG M Q, ZHANG J S, et al. Automatic segmentation Technology of Automobile Wheel Hub Defects Based on Deep Learning［J］.Science Technology and Engineering, 2020, 20(24): 9976-9981.
［59］	程淑红, 芦嘉鑫,张典范, 等. 基于环形特征的卷积神经网络轮毂识别［J］. 计量学报, 2022, 43(6): 730-736.
［62］	SHEN Z Z, DANG H, SUN M Y, et al. Application of Generating Adversarial Networks in High-light Removal of Wheel Hub Surface［C］//2019 International Conference on Advanced Mechatronic Systems (ICAMechS). 2019: 12-15.
	SONG H, LI Z. Design of visual inspection system for automobile hub surface defect based on industrial robot［J］. Computer Measurement and Control, 2018, 26(9): 13-16.
［69］	吴凤和, 崔健新, 张宁, 等. 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.
［27］	王一妍. 基于机器视觉的轮毂铸造面质量检测研究［D］. 沈阳: 沈阳工业大学, 2019.
［28］	王文丽. 基于机器视觉的轮毂轴承法兰检测系统研究［D］. 杭州: 浙江科技学院, 2019.
［35］	李高亮. 基于X射线图像的汽车轮毂缺陷自动检测与识别技术研究［D］. 太原: 中北大学, 2013.
［36］	焦腾云. 基于X射线图像的轮毂铸件缺陷检测技术研究［D］. 太原: 中北大学, 2020.
［42］	焦腾云, 王明泉, 张俊生, 等. 基于小波分析和伪彩色处理的轮毂图像增强［J］. 自动化与仪表, 2020, 35(1): 47-51.
	JIAO T Y, WANG M Q, ZHANG J S, et al. Hub X-ray image enhancement based on wavelet analysis and pseudo color processing［J］. Automation & Instrumentation, 2020, 35(1): 47-51.
［51］	赵海文, 赵亚川, 齐兴悦, 等. 基于深度学习的汽车轮毂表面缺陷检测算法研究［J］. 组合机床与自动化加工技术, 2019(11): 112-115.
	ZHAO H W, ZHAO Y C, QI X Y, et al. Research on surface defect inspection algorithms of automobile hub based on deep learning［J］. Modular Machine Tool & Automatic Manufacturing Technique, 2019(11): 112-115.
［57］	王陶然, 王明泉, 张俊生, 等. 基于Mask R-CNN的轮毂缺陷分割技术［J］. 国外电子测量技术, 2021, 40(2): 1-5.
	WANG T R, WANG M Q, ZHANG J S, et al. Automatic instance segmentation technology of automobile wheel hub defects based on Mask R-CNN［J］. Foreign Electronic Measurement Technology, 2021, 40(2): 1-5.
［65］	郭智杰, 王明泉, 张俊生, 等. 基于机器视觉的轮毂在线识别分类技术研究［J］. 测试技术学报, 2019, 33(3): 233-237.
	GUO Z J, WANG M Q, ZHANG J S, et al. The Research on Online Recognition and Classification Technology of Wheel Hub Based on Machine Vision［J］. Journal of Test and Measurement Technology, 2019, 33(3): 233-237.
［31］	MERY D, SILVA R R D, CALOBA L P, et al. Pattern recognition in the automatic inspection of aluminium castings［J］. Insight-Non-Destructive Testing and Condition Monitoring, 2003, 45(7): 475-483.
［39］	徐道磊. 基于X射线成像的铸件缺陷检测系统及噪声干扰去除［D］. 广州: 华南理工大学, 2013.
［47］	MERY D. Aluminum casting inspection using deep learning: a method based on convolutional neural networks［J］. Journal of Nondestructive Evaluation, 2020, 39(1): 1-12.
［55］	郭瑞琦, 王明泉, 张俊生, 等. 基于深度学习的汽车轮毂缺陷自动分割技术［J］. 科学技术与工程, 2020, 20(24): 9976-9981.
［61］	TANG C W, FENG X X, WEN H T, et al. Semantic Segmentation Network for Surface Defect Detection of Automobile Wheel Hub Fusing High-Resolution Feature and Multi-Scale Feature［J］. Applied Sciences. 2021, 11(22): 10508.
	YAO B, WEN X L, JIAO L B, et al. Improved YOLOv3 Algorithm for Surface Defect Detection of Aluminum Profile［J］. Acta Metrologica Sinica, 2022, 43(10): 1256-1261.
	WU F H, CUI J X, ZHANG N, et al. Surface Defect Detection of Wheel Hub Based on Improved YOLOv4 Algorithm［J］. Acta Metrologica Sinica, 2022, 43(11): 1404-1411.