南方科技大学知识苑(SUSTech KC): 基于深度学习方法的PCB材料表面缺陷检测技术

Title	基于深度学习方法的PCB材料表面缺陷检测技术
Alternative Title	A PCB SURFACE DEFECTS INSPECTION TECHNOLOGY BASED ON DEEP LEARNING METHOD
Author	金锦涛
Name pinyin	JIN Jintao
School number	12032320
Degree	硕士
Discipline	0856 材料与化工
Subject category of dissertation	0856 材料与化工
Supervisor	王卫军
Mentor unit	中国科学院深圳理工大学（筹）
Publication Years	2022-05-10
Submission date	2022-06-25
University	南方科技大学
Place of Publication	深圳
Abstract	印刷电路板（printed circuit board，PCB）是电子元器件的支撑体，是电子设备的基本元件之一。PCB 制造工艺中包含开料、钻孔、沉铜等数十个工序，制造工艺较为复杂，其中每一道工序都可能对 PCB 造成损伤，这些损伤可能对 PCB 的电气性能造成影响，进而影响到电子设备可靠性。现有的印刷电路板材料表面缺陷检测方法主要有人工检测、传统机器视觉检测、基于深度学习的视觉检测等。近年来快速发展的深度学习方法具有鲁棒性好、泛化能力强等特点，且随着 Transformer 模型被引入到计算机视觉领域当中，目标检测算法中许多依赖先验知识的结构被去除，以 DETR 为代表的一系列结合了 Transformer 和卷积神经网络的目标检测算法取得了良好的成果。本文以结合了 Transformer 和卷积神经网络的 Deformable DETR 目标检测算法为基础，针对所使用的PCB材料表面缺陷数据集的特点提出了两点优化：其一为使用了Mish激活函数替换了原算法中的ReLU激活函数；其二为基于Focal Loss、GIoU Loss、Smooth L1 Loss设计了新的损失函数，并确定了损失函数中的超参数。最后依托 Pytorch 深度学习框架和分布式并行训练等手段，训练了本文优化后的对 PCB 材料表面缺陷检测的算法。实验结果表明，在本文使用的 PCB 材料表面缺陷数据集上，本文改进后的 Deformable DETR 算法相较于 YOLOv3、RetinaNet、EfficientDet 等主流目标检测算法在 mAP@0.5 指标上提高了 3.8% 到 5.8% 不等，而在消融实验中，对激活函数的优化后的算法相较于原始 Deformable DETR 模型在 mAP@0.5 指标上提高了 1.4%，而同时对激活函数和损失函数优化后的算法相较于原始 Deformable DETR 模型在 mAP@0.5 指标上提高了1.5%。以上实验结果表明本文提出的改进算法相较于主流目标检测算法在 PCB 材料表面缺陷任务上具有一定精度优势，为将来在实际生产制造场景应用中奠定了基础。
Keywords	印刷电路板卷积神经网络深度学习 Transformer Deformable DETR
Language	Chinese
Training classes	独立培养
Enrollment Year	2020
Year of Degree Awarded	2022-06
References List	[1] 中华人民共和国国务院. 国务院关于印发“十三五”国家战略性新兴产业发展规划的通知[EB/OL]. 2016 [2016-12-19]. http://www.gov.cn/zhengce/content/2016-12/19/content_515 0090.htm. [2] 中华人民共和国国家统计局. 《战略性新兴产业分类（2018）》（国家统计局令第 23 号）[EB/OL]. 2018 [2018-11-26]. http://www.stats.gov.cn/tjgz/tzgb/201811/t20181126_1635848. html. [3] 中华人民共和国国家发展和改革委员会. 发展改革委修订发布《产业结构调整指导目录（2019 年本）》[EB/OL]. 2019 [2019-11-06]. http://www.gov.cn/xinwen/2019-11/06/content _5449193.htm. [4] 杨宏强. 势如旭日东升的中国内资 PCB 产业——2017 年全球 PCB 百强企业分析[J]. 印制电路信息, 2018, 26(11): 6-11. [5] 杨宏强. 2018 年全球 PCB 产业分析[J]. 印制电路信息, 2019, 27(10): 1-5. [6] 杨宏强. 2019 年全球 PCB 产业分析[J]. 印制电路信息, 2020, 28(10): 1-4. [7] 龚永林. 看 2020 年度世界顶级 PCB 制造商排名见中国 PCB 产业越来越大[J]. 印制电路信息, 2021, 29(09): 1-6. [8] Institute for Printed Circuits. IPC-A-600J Acceptability of Printed Boards[S]. Bannockburn: Institute for Printed Circuits, 2016. [9] CHANG P C, CHEN L Y, FAN C Y. A case-based evolutionary model for defect classification of printed circuit board images[J]. Journal of Intelligent Manufacturing, 2008, 19(2): 203-214. [10] PUTERA S I, IBRAHIM Z. Printed circuit board defect detection using mathematical morphology and matlab image processing tools[C]//2010 2nd international conference on education technology and computer: volume 5. IEEE, 2010: V5-359. [11] 熊邦书, 熊振姣, 莫燕, 等. 线路板缺陷的图像检测方法[J]. 半导体光电, 2012, 33(02):333-306. [12] RAY S, MUKHERJEE J. A hybrid approach for detection and classification of the defects on printed circuit board[J]. International Journal of Computer Applications, 2015, 121(12). [13] 王栋, 解则晓. 基于形态学的 PCB 缺陷快速检测技术[J]. 计算机科学, 2016, 43(S1): 184-186+225. [14] CE W, et al. Pcb defect detection using opencv with image subtraction method[C]//2017 International Conference on Information Management and Technology (ICIMTech). IEEE, 2017: 204-209. [15] LI Y, LI S. Defect detection of bare printed circuit boards based on gradient direction information entropy and uniform local binary patterns[J]. Circuit World, 2017. [16] GAIDHANE V H, HOTE Y V, SINGH V. An efficient similarity measure approach for pcb surface defect detection[J]. Pattern Analysis and Applications, 2018, 21(1): 277-289. [17] ZHANG Z, WANG X, LIU S, et al. An automatic recognition method for pcb visual defects [C]//2018 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC). IEEE, 2018: 138-142. [18] HASSANIN A A I, ABD EL-SAMIE F E, EL BANBY G M. A real-time approach for automatic defect detection from pcbs based on surf features and morphological operations[J]. Multimedia Tools and Applications, 2019, 78(24): 34437-34457. [19] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2014: 580-587. [20] HE K, ZHANG X, REN S, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE transactions on pattern analysis and machine intelligence, 2015, 37 (9): 1904-1916. [21] GIRSHICK R. Fast r-cnn[C]//Proceedings of the IEEE international conference on computer vision. 2015: 1440-1448. [22] REN S, HE K, GIRSHICK R, et al. Faster r-cnn: Towards real-time object detection with region proposal networks[J]. Advances in neural information processing systems, 2015, 28: 91-99. [23] HE K, GKIOXARI G, DOLLÁR P, et al. Mask r-cnn[C]//Proceedings of the IEEE international conference on computer vision. 2017: 2961-2969. [24] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 779-788. [25] LIU W, ANGUELOV D, ERHAN D, et al. Ssd: Single shot multibox detector[C]//European conference on computer vision. Springer, 2016: 21-37. [26] REDMON J, FARHADI A. Yolo9000: better, faster, stronger[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 7263-7271. [27] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of the IEEE international conference on computer vision. 2017: 2980-2988. [28] REDMON J, FARHADI A. Yolov3: An incremental improvement[J]. arXiv preprint arXiv:1804.02767, 2018. [29] TAN M, PANG R, LE Q V. Efficientdet: Scalable and efficient object detection[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 10781-10790. [30] TAKADA Y, SHIINA T, USAMI H, et al. Defect detection and classification of electronic circuit boards using keypoint extraction and cnn features[C]//The Ninth International Conferences on Pervasive Patterns and Applications Defect: volume 100. 2017: 113-116. [31] GHOSH B, BHUYAN M, SASMAL P, et al. Defect classification of printed circuit boards based on transfer learning[C]//2018 IEEE Applied Signal Processing Conference (ASPCON). IEEE, 2018: 245-248. [32] DENG Y S, LUO A C, DAI M J. Building an automatic defect verification system using deep neural network for pcb defect classification[C]//2018 4th International Conference on Frontiers of Signal Processing (ICFSP). IEEE, 2018: 145-149. [33] LI Y T, GUO J I. A vgg-16 based faster rcnn model for pcb error inspection in industrial aoi applications[C]//2018 IEEE international conference on consumer electronics-Taiwan (ICCETW). IEEE, 2018: 1-2. [34] ZHANG C, SHI W, LI X, et al. Improved bare pcb defect detection approach based on deep feature learning[J]. The Journal of Engineering, 2018, 2018(16): 1415-1420. [35] HU B, WANG J. Detection of pcb surface defects with improved faster-rcnn and feature pyramid network[J]. IEEE Access, 2020, 8: 108335-108345. [36] LAN Z, HONG Y, LI Y. An improved yolov3 method for pcb surface defect detection[C]// 2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA). IEEE, 2021: 1009-1015. [37] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in neural information processing systems. 2017: 5998-6008. [38] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16x16 words: Transformers for image recognition at scale[C]//International Conference on Learning Representations. 2020. [39] CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers [C]//European Conference on Computer Vision. Springer, 2020: 213-229. [40] ZHENG M, GAO P, WANG X, et al. End-to-end object detection with adaptive clustering transformer[J]. arXiv preprint arXiv:2011.09315, 2020. [41] ZHU X, SU W, LU L, et al. Deformable detr: Deformable transformers for end-to-end object detection[J]. arXiv preprint arXiv:2010.04159, 2020. [42] WANG Y, ZHANG X, YANG T, et al. Anchor detr: Query design for transformer-based detector [J]. arXiv preprint arXiv:2109.07107, 2021. [43] BEAL J, KIM E, TZENG E, et al. Toward transformer-based object detection[J]. arXiv preprint arXiv:2012.09958, 2020. [44] FANG Y, LIAO B, WANG X, et al. You only look at one sequence: Rethinking transformer in vision through object detection[J]. arXiv preprint arXiv:2106.00666, 2021. [45] WANG W, XIE E, LI X, et al. Pyramid vision transformer: A versatile backbone for dense prediction without convolutions[J]. arXiv preprint arXiv:2102.12122, 2021. [46] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324. [47] HENDRYCKS D, GIMPEL K. Gaussian error linear units (gelus)[J]. arXiv preprint arXiv:1606.08415, 2016. [48] MISRA D. Mish: A self regularized non-monotonic neural activation function[J]. arXiv preprint arXiv:1908.08681, 2019, 4: 2. [49] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778. [50] TAN M, LE Q. Efficientnet: Rethinking model scaling for convolutional neural networks[C]// International Conference on Machine Learning. PMLR, 2019: 6105-6114. [51] SANDLER M, HOWARD A, ZHU M, et al. Mobilenetv2: Inverted residuals and linear bottlenecks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 4510-4520. [52] TAN M, CHEN B, PANG R, et al. Mnasnet: Platform-aware neural architecture search for mobile[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 2820-2828. [53] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132-7141. [54] DEVLIN J, CHANG M W, LEE K, et al. Bert: Pre-training of deep bidirectional transformers for language understanding[J]. arXiv preprint arXiv:1810.04805, 2018. [55] MNIH V, HEESS N, GRAVES A, et al. Recurrent models of visual attention[C]//Advances in neural information processing systems. 2014: 2204-2212. [56] CHO K, VAN MERRIËNBOER B, GULCEHRE C, et al. Learning phrase representations using rnn encoder-decoder for statistical machine translation[J]. arXiv preprint arXiv:1406.1078, 2014. [57] REZATOFIGHI H, TSOI N, GWAK J, et al. Generalized intersection over union: A metric and a loss for bounding box regression[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 658-666. [58] LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection [C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 2117-2125. [59] LIU S, QI L, QIN H, et al. Path aggregation network for instance segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 8759-8768. [60] GHIASI G, LIN T Y, LE Q V. Nas-fpn: Learning scalable feature pyramid architecture for object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 7036-7045. [61] RAMACHANDRAN P, ZOPH B, LE Q V. Searching for activation functions[J]. arXiv preprint arXiv:1710.05941, 2017. [62] SRIVASTAVA N, HINTON G, KRIZHEVSKY A, et al. Dropout: a simple way to prevent neural networks from overfitting[J]. The journal of machine learning research, 2014, 15(1): 1929-1958. [63] HUANG W, WEI P, ZHANG M, et al. Hripcb: a challenging dataset for pcb defects detection and classification[J]. The Journal of Engineering, 2020, 2020(13): 303-309. [64] KINGMA D P, BA J. Adam: A method for stochastic optimization[J]. arXiv preprint arXiv:1412.6980, 2014.
Academic Degree Assessment Sub committee	中国科学院深圳理工大学（筹）联合培养
Domestic book classification number	TB302.6
Data Source	人工提交
Document Type	Thesis
Identifier	http://kc.sustech.edu.cn/handle/2SGJ60CL/342778
Department	Shenzhen Institute of Advanced Technology Chinese Academy of Sciences
Recommended Citation GB/T 7714	金锦涛. 基于深度学习方法的PCB材料表面缺陷检测技术[D]. 深圳. 南方科技大学,2022.

Files in This Item:
File Name/Size	DocType	Version	Access	License
12032320-金锦涛-中国科学院深圳（3554KB）			Restricted Access	--	Fulltext Requests

If you have any objections to this item, please fill out the form below and the administrator will contact you as soon as possible.
Content:
Email：	*
Affiliation Sequential No:
Verification Code:	Refresh

Any comments and suggestions are welcomed.
Title:	*
Content:
Email：	*
Verification Code:	Refresh