基于深度学习的陶瓷表面缺陷检测研究综述

doi:10.16731/j.cnki.1671-3133.2025.10.016

摘要/Abstract

摘要： 陶瓷表面缺陷检测对产品质量至关重要,传统检测方法具有局限性,深度学习方法为其带来了新的契机。首先,阐述了提升陶瓷表面小目标缺陷检测精度的方法,包括添加注意力机制、特征改进和网络结构优化等;其次,从轻量化模型的改进和网络模块集成与优化两个方面对提升模型缺陷检测实时性的方法进行了分析;最后,由数据增强、迁移学习和样本分布优化等方法对在陶瓷表面进行缺陷检测时面临的小样本和不平衡样本问题进行了归纳,并总结了陶瓷表面缺陷检测技术实施中可使用的解决方案,展望了未来陶瓷表面缺陷检测的研究方向。

关键词: 陶瓷表面缺陷, 缺陷检测, 深度学习, 注意力机制, 轻量化模型, 网络结构

Abstract: Ceramic surface defect detection is crucial for product quality,and traditional detection methods have limitations. Deep learning methods have brought new opportunities for it. Firstly,methods were presented to improve the accuracy of detecting small target defects on ceramic surfaces,including the use of attention mechanisms,feature enhancement,and network structure optimization. Secondly,an analysis was conducted on improving the real-time defect detection performance of the lightweight model and integrating and optimizing network modules. Finally,methods such as data augmentation,transfer learning,and sample distribution optimization were used to summarize the problems of small and imbalanced samples faced in defect detection on ceramic surfaces. Solutions that can be used in the implementation of ceramic surface defect detection technology were also summarized,and future research directions for ceramic surface defect detection were discussed.

Key words: ceramic surface defects, defect detection, deep learning, attention mechanism, lightweight model, network structure

中图分类号:

TP391

唐冰慧, 杨伟东, 董文益, 张龙. 基于深度学习的陶瓷表面缺陷检测研究综述[J]. 现代制造工程, 2025, 541(10): 148-158.

TANG Binghui, YANG Weidong, DONG Wenyi, ZHANG Long. Review of research on ceramic surface defect detection based on deep learning[J]. Modern Manufacturing Engineering, 2025, 541(10): 148-158.

参考文献

[1] BOCH P,NI J C.Ceramic materials:processes,properties,and applications[M].Chichester:John Wiley & Sons,2010.
[2] CHEN Z,LI Z,LI J,et al.3D printing of ceramics:a review[J].Journal of the European Ceramic Society,2019,39(4):661-687.
[3] OTITOJU T A,OKOYE P U,CHEN G,et al.Advanced ceramic components:materials,fabrication,and applications[J].Journal of Industrial and Engineering Chemistry,2020,85:34-65.
[4] SINGER F.Industrial ceramics[M].Dordrecht:Springer,2013.
[5] ZHENG X,ZHENG S,KONG Y,et al.Recent advances in surface defect inspection of industrial products using deep learning techniques[J].The International Journal of Advanced Manufacturing Technology,2021,113:35-58.
[6] ZHAO Z Q,ZHENG P,XU S,et al.Object detection with deep learning:a review[J].IEEE Transactions on Neural Networks and Learning Systems,2019,30(11):3212-3232.
[7] SABERIRONAGHI A,REN J,EL-GINDY M.Defect detection methods for industrial products using deep learning techniques:a review[J].Algorithms,2023,16(2):95.
[8] 杨泽青,张明轩,陈英姝,等.基于机器视觉的表面缺陷检测方法研究进展[J].现代制造工程,2023(4):143-156.
[9] BIRLUTIU A,BURLACU A,KADAR M,et al.Defect detection in porcelain industry based on deep learning techniques[C]//2017 19th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing(SYNA-SC).Piscataway:IEEE,2017:263-270.
[10] MARIYADI B,FITRIYANI N,SAHRONI T R.2D detection model of defect on the surface of ceramic tile by an artificial neural network[J]. Journal of Physics:Conference Series,2021,1764(1):012176.
[11] ALEXANDROPOULOS S A N,KOTSIANTIS S B,VRAHATIS M N.Data preprocessing in predictive data mining[J].The Knowledge Engineering Review,2019,34:e1.
[12] MAHARANA K,MONDAL S,NEMADE B. A review:data pre-processing and data augmentation techniques[J].Global Transitions Proceedings,2022,3(1):91-99.
[13] ZELAYA C V G.Towards explaining the effects of data preprocessing on machine learning[C]//2019 IEEE 35th International Conference on Data Engineering(ICDE). [S.l.]:IEEE,2019:2086-2090.
[14] NIU Z,ZHONG G,YU H.A review on the attention mechanism of deep learning[J].Neurocomputing,2021,452:48-62.
[15] GUO M H,XU T X,LIU J J,et al.Attention mechanisms in computer vision:a survey[J].Computational Visual Media,2022,8(3):331-368.
[16] 安冬,胡荣华,王丽艳,等.基于Transformer的陶瓷轴承表面缺陷检测方法[J].组合机床与自动化加工技术,2024(2):160-163,168.
[17] 雷震霆,朱兴龙,孙进,等.融合坐标注意力和自适应特征的YOLOv5陶瓷膜缺陷检测方法[J].电子测量技术,2023,46(7):133-137.
[18] 丁伟利,张志鹏,雷子琦,等.深度学习陶瓷表面缺陷检测算法研究[J].电子测量与仪器学报,2023,37(11):161-169.
[19] 张志鹏.基于计算机视觉的陶瓷表面缺陷检测关键技术研究[D].秦皇岛:燕山大学,2023.
[20] CHEN W,ZOU B,YANG G X,et al.A real-time detection system for multiscale surface defects of 3D printed ceramic parts based on deep learning[J].Ceramics International,2024,50(8):13101-13112.
[21] GUAN S,WANG X,WANG J,et al.Ceramic ring defect detection based on improved YOLOv5[C]//2022 3rd International Conference on Computer Vision,Image and Deep Learning & International Conference on Computer Engineering and Applications(CVIDL & ICCEA).Piscataway:IEEE,2022:115-118.
[22] 唐世镇.基于机器视觉的陶瓷滤波器表面缺陷检测算法研究[D].武汉:华中科技大学,2022.
[23] 王旭,管声启,刘通,等.基于改进YOLOv5的陶瓷环缺陷检测算法[J].轻工机械,2023,41(3):66-71.
[24] 潘金晶,曾成,张晶,等.基于改进YOLOv5的陶瓷表面缺陷检测算法[J].现代信息科技,2024,8(13):70-75.
[25] PAN H,LI G,FENG H,et al.Surface defect detection of ceramic disc based on improved YOLOv5s[J].Heliyon,2024,10(12):e33016.
[26] 王建国,孙付仲,苑子龙,等.基于改进Faster RCNN的瓷砖表面缺陷检测算法[J].南京工业大学学报(自然科学版),2025,47(1):49-55.
[27] CHEN W,ZOU B,HUANG C,et al.The defect detection of 3D-printed ceramic curved surface parts with low contrast based on deep learning[J].Ceramics International,2023,49(2):2881-2893.
[28] 唐雨欣.基于机器视觉的陶瓷填孔缺陷检测技术研究[D].哈尔滨:哈尔滨工业大学,2023.
[29] CAO C,WANG B,ZHANG W,et al.An improved faster R-CNN for small object detection[J].IEEE Access,2019,7:106838-106846.
[30] 叶旭芳,陈梅,李晖,等.基于联合注意力的复杂纹理瓷砖缺陷检测方法[J].计算机应用研究,2024,41(3):944-950.
[31] ZHU Y,SONG H. Improved small defect detection on ceramic surfaces with YOLOv8[C]//2024 39th Youth Academic Annual Conference of Chinese Association of Automation(YAC).Piscataway:IEEE,2024:1879-1884.
[32] 满英杰,王宪,孙冬悦,等.目标检测与图像分类网络融合的金属化陶瓷环缺陷检测[J].激光与光电子学进展,2023,60(20):167-175.
[33] 韩磊.基于深度学习的陶瓷表面缺陷检测[D].沈阳:沈阳航空航天大学,2022.
[34] CHEN W,ZOU B,ZHENG Q,et al.Research on anti-interference detection of 3D-printed ceramics surface defects based on deep learning[J].Ceramics International,2023,49(13):22479-22491.
[35] 李泽辉,陈新度,练洋奇.基于卷积自编码网络的瓷砖表面缺陷检测[J].现代计算机,2021,27(24):109-114.
[36] JIA X,LI S,WANG T,et al. High-performance defect detection methods for real-time monitoring of ceramic additive manufacturing process based on small-scale datasets[J].Processes,2024,12(4):633.
[37] HANG J,SUN H,YU X,et al.Surface defect detection in sanitary ceramics based on lightweight object detection network[J].IEEE Open Journal of the Industrial Electronics Society,2022,3:473-483.
[38] 滕博文.基于深度学习的卫浴陶瓷缺陷检测[D].北京:机械科学研究总院,2021.
[39] 李泽辉,陈新度,黄佳生,等.基于改进YOLOv3的纹理瓷砖缺陷检测[J].激光与光电子学进展,2022,59(10):294-302.
[40] CAO T,SONG K,XU L,et al.Balanced multi-scale target score network for ceramic tile surface defect detection[J].Measurement,2024,224:113914.
[41] 吴连雨.基于YOLOv8的日用陶瓷杯表面缺陷检测算法应用[D].景德镇:景德镇陶瓷大学,2024.
[42] CUMBAJIN E,RODRIGUES N,COSTA P,et al.A real-time automated defect detection system for ceramic pieces manufacturing process based on computer vision with deep learning[J].Sensors,2023,24(1):232.
[43] ZHOU Y,CHEN S,WANG Y,et al.Review of research on lightweight convolutional neural networks[C]//2020 IEEE 5th Information Technology and Mechatronics Engineering Conference(ITOEC).[S.l.]:IEEE,2020:1713-1720.
[44] 马晨凯,吴毅慧,傅华奇,等.基于深度学习的先进陶瓷零件实时缺陷检测系统[J].南京航空航天大学学报,2021,53(5):726-734.
[45] 杨梦瑶.陶瓷药瓶缺陷检测及尺寸测量技术的研究[D].天津:河北工业大学,2022.
[46] HUANG C Y,LIN I C,LIU Y L.Applying deep learning to construct a defect detection system for ceramic substrates[J].Applied Sciences,2022,12(5):2269.
[47] 王淑青,顿伟超,黄剑锋,等.基于YOLOv5的瓷砖表面缺陷检测[J].包装工程,2022,43(9):217-224.
[48] 汪震.基于Faster R-CNN的陶瓷覆铜板缺陷检测研究[D].湘潭:湘潭大学,2020.
[49] BANSAL M A,SHARMA D R,KATHURIA D M.A systematic review on data scarcity problem in deep learning:solution and applications[J].ACM Computing Surveys(Csur),2022,54(10s):1-29.
[50] NIU J,CHEN Y,YU X,et al.Data augmentation on defect detection of sanitary ceramics[C]//IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society.Piscataway:IEEE,2020:5317-5322.
[51] GHOSH K,BELLINGER C,CORIZZO R,et al.The class imbalance problem in deep learning[J].Machine Learning,2024,113(7):4845-4901.
[52] HUANG Y P,SU C M,BASANTA H,et al.Imbalance modelling for defect detection in ceramic substrate by using convolutional neural network[J].Processes,2021,9(9):1678.
[53] CARVALHO R,MORGADO A C,GONCALVES J,et al.Computer-aided visual inspection of glass-coated table-ware ceramics for multi-class defect detection[J].Applied Sciences,2023,13(21):11708.