基于YOLOv3-spp的汽车轮毂表面缺陷检测算法研究与分析

doi:10.3969/j.issn.1000-1158.2023.09.09

Abstract
Figure/Table
References (21)
Related Citation (15)

Download: PDF (725 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract According to the requirements of surface defect detection environment and detection index in the production process of automobile hub, aiming at the problems of low efficiency and low accuracy of traditional manual detection methods, an automatic defect detection method based on YOLOv3-spp (You Only Look Once v3-Spatial Pyramid Pooling Network) network is proposed. In this method, firstly, the defect area is extracted by image slicing, and then the extracted defect image is enhanced to form a data set to train the YOLOv3-spp deep learning network, what's more the hub defects are detected and compared by using different neural networks and data set screening methods. The experimental results show that: On the dataset collected from the industrial site, the trained YOLOv3-spp neural network can accurately locate and identify four types of defects: point-like, linear, oily sludge and pinhole, with an average accuracy of 84.5%, 93.4%, 95.4% and 89.5% respectively. The detection speed of a single image can reach 35ms, meeting the real-time requirements of detection. Furthermore, the detection accuracy is better than two common neural networks: Faster R-CNN(Faster Region-Convolutional Neural Networks) and SSD(Single Shot MultiBox Detector).

Received: 04 August 2022 Published: 21 September 2023

PACS:

TB96

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	ZHANG Zhen-yu
	LIU Yang
	LIU Fu-cai

Cite this article:

ZHANG Zhen-yu,LIU Yang,LIU Fu-cai. Research and Analysis of Automobile Wheel Hub Surface Defect Detection Algorithm based on YOLOv3-spp[J]. Acta Metrologica Sinica, 2023, 44(9): 1375-1382.

URL:

http://jlxb.china-csm.org:81/Jwk_jlxb/EN/10.3969/j.issn.1000-1158.2023.09.09 OR http://jlxb.china-csm.org:81/Jwk_jlxb/EN/Y2023/V44/I9/1375

	Tan S X, Huang Q. A fast region segmentation method for hub X-ray images［J］. Computer Applications, 2006(S1): 19-20, 23.
［11］	Sun X, Gu J, Huang R, et al. Surface Defects Recognition of Wheel Hub Based on Improved Faster R-CNN［J］. Electronics. 2019, 8(5): 481.
［15］	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.
［1］	张玉燕, 任腾飞, 温银堂. 一种基于YOLOv3算法的3D打印点阵结构缺陷识别方法［J］. 计量学报, 2022, 43(1): 7-13.
［6］	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.
	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.
	Wang Z W, Guo B, Hu X F, et al. Internal Groove Defect Detection Method of Brake Master Cylinder Based on FCOS Neural Network［J］. Acta Metrologica Sinica, 2021, 42(9): 1225-1231.
	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, 22.
	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.
［5］	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, 23.
［12］	朱超平, 杨永斌. 基于改进的Faster-RCNN模型的汽车轮毂表面缺陷在线检测算法研究［J］. 表面技术, 2020, 49(6): 359-365.
［17］	Redmon J, Farhadi A. Yolov3: An Incremental Improvement［C］//IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City, USA, 2018.
［19］	吴喆. 基于深度学习的动态背景下航道船舶检测识别与跟踪研究［D］. 宜昌: 三峡大学, 2019.
［4］	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.
［9］	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.
［10］	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.
	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.
	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.
	Zhang Y Y, Ren T F, Wen Y T. A Method for Detecting Internal Defects of Metal Lattice Structure Based on YOLOv3 Algorithm［J］. Acta Metrologica Sinica, 2022, 43(1): 7-13.
［3］	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, 22.
	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.
［8］	郭保苏, 吴文文, 付强, 等. 基于支持向量机分类策略的多晶硅电池片色差检测［J］. 计量学报, 2019, 40(6): 1013-1019.
	Zhu C P, Yang Y B. Online Detection Algorithm of Automobile Wheel Surface Defects Based on Improved Faster-RCNN Model［J］. Surface Technology, 2020, 49(6): 359-365.
［14］	Yu Y, Wang M, Wang Z, et al. Surface Defect Detection of Hight-speed Railway Hub Based on Improved YOLOv3 Algorithm［C］//2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC). Chongqing, China, 2021: 1386-1390.
［20］	Ren S, He K, Girshick R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks［C］//Advances in Neural Information Processing Systems (NIPS). Montreal, Canada, 2015.
［2］	王芷薇, 郭斌, 胡晓峰, 等. 基于FCOS神经网络的制动主缸内槽缺陷检测方法［J］. 计量学报, 2021, 42(9): 1225-1231.
［7］	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.
［13］	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.
［21］	Liu W, Anguelov D, Erhan D, et al. SSD: Single shot multibox detector［C］//In European Conference on Computer Vision (ECCV). Amsterdam, Netherlands, 2016.
	Guo B S, Wu W W, Fu Q, et al. Color Difference Detection of Polycrystalline Silicon Cells Based on Support Vector Machine Classification Strategy［J］. Acta Metrologica Sinica, 2019, 40(6): 1013-1019.
	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.
［16］	Tang C, Feng X, Wen H, 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.
［18］	Zhang P, Zhong Y, Li X. SlimYOLOv3: Narrower, Faster and Better for Real-Time UAV Applications［C］//2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). Seoul, Korea, 2019: 37-45.