{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:42:39Z","timestamp":1781196159852,"version":"3.54.1"},"reference-count":39,"publisher":"ASME International","issue":"4","license":[{"start":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T00:00:00Z","timestamp":1672099200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52175237"],"award-info":[{"award-number":["52175237"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>In the production of cold-rolled galvanized steel strips used for stamping car body parts, the in-situ and real-time defect detection is crucial for quality control, in which various types of defects inevitably occur. It is challenging to improve the accuracy of defect detection and classification by appropriate means to assist the manual screening process better. Defects under actual production conditions are often not prominent enough in defect characteristics, and there may be a significant similarity between different defect categories. To eliminate this weakness, we propose a data-driven deep learning approach named steel surface faulty detection attention net (SSFDANet) that uses images of the galvanized steel surfaces as input to identify whether the product is qualified and automatic classification of defect types instantaneously. This method can shorten product inspection time and improve the production line automation efficiency. In addition, the attention mechanism is utilized to enhance the performance of SSFDANet. Compared with the baseline ResNet, SSFDANet achieves a noticeable improvement in classification accuracy on test data. The well-trained model can successfully show an improved performance than the baseline models on the multiple types of faulty. Enhanced by SSFDANet with high classification accuracy, the defect rate of products is significantly reduced, and the production speed of the production line is significantly improved. Future prospective studies that are inspired by this article are also discussed.<\/jats:p>","DOI":"10.1115\/1.4055672","type":"journal-article","created":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T08:38:56Z","timestamp":1663576736000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":12,"title":["Intelligent Detection and Classification of Surface Defects on Cold-Rolled Galvanized Steel Strips Using a Data-Driven Faulty Model With Attention Mechanism"],"prefix":"10.1115","volume":"23","author":[{"given":"Hao","family":"Chen","sequence":"first","affiliation":[{"name":"Tsinghua University Department of Automation, , Beijing 100084 , China ;"},{"name":"Shanghai Baosight Software Co., Ltd , Shanghai 201203 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenguo","family":"Nie","sequence":"additional","affiliation":[{"name":"Tsinghua University The State Key Laboratory of Tribology, Department of Mechanical Engineering; Beijing Key Lab of Precision\/Ultra-precision Manufacturing Equipments and Control, , Beijing 100084 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingfeng","family":"Xu","sequence":"additional","affiliation":[{"name":"Tsinghua University The State Key Laboratory of Tribology, Department of Mechanical Engineering; Beijing Key Lab of Precision\/Ultra-precision Manufacturing Equipments and Control, , Beijing 100084 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianghua","family":"Fei","sequence":"additional","affiliation":[{"name":"Shanghai Baosight Software Co., Ltd , Shanghai 201203, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kang","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Baosight Software Co., Ltd , Shanghai 201203, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaguan","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University The State Key Laboratory of Tribology, Department of Mechanical Engineering; Beijing Key Lab of Precision\/Ultra-precision Manufacturing Equipments and Control, , Beijing 100084 , China ;"},{"name":"Taiyuan University of Technology College of Mechanical and Vehicle Engineering, , Taiyuan, Shanxi 030024 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongbin","family":"Lin","sequence":"additional","affiliation":[{"name":"Guangzhou University School of Mathematics and Information Science, , Guangzhou 510006 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhui","family":"Fan","sequence":"additional","affiliation":[{"name":"Tsinghua University Department of Automation, , Beijing 100084 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin-Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University The State Key Laboratory of Tribology, Department of Mechanical Engineering; Beijing Key Lab of Precision\/Ultra-precision Manufacturing Equipments and Control, , Beijing 100084 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"33","published-online":{"date-parts":[[2022,12,27]]},"reference":[{"issue":"2","key":"2022122710510608600_CIT0001","first-page":"3","article-title":"Research on Surface Defect Classification of Strip Steel Based on LVQ","volume":"24","author":"Xu","year":"2004","journal-title":"Chinese Instrumentation"},{"issue":"5","key":"2022122710510608600_CIT0002","first-page":"6","article-title":"Clustering and Optimization of Support Vector Machines for Surface Defect Classification of Cold-Rolled Strip Steel","volume":"23","author":"Hua","year":"2016","journal-title":"J. Plastic Eng."},{"issue":"12","key":"2022122710510608600_CIT0003","first-page":"6","article-title":"Classification of Surface Defects of Strip Steel Based on Weighted Coding of Local Features","volume":"25","author":"Liu","year":"2018","journal-title":"Control Eng."},{"key":"2022122710510608600_CIT0004","first-page":"770","article-title":"Deep Residual Learning for Image Recognition","author":"He","year":"2015"},{"key":"2022122710510608600_CIT0005","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2015.338","article-title":"Look and Think Twice: Capturing Top-Down Visual Attention With Feedback Convolutional Neural Networks","author":"Cao","year":"2015"},{"key":"2022122710510608600_CIT0006","first-page":"9215","article-title":"Tell Me Where to Look: Guided Attention Inference Network","author":"Li","year":"2018"},{"issue":"10","key":"2022122710510608600_CIT0007","first-page":"1","article-title":"Textspamdetector: Textual Content Based Deep Learning Framework for Social Spam Detection Using Conjoint Attention Mechanism","volume":"12","author":"Elakkiya","year":"2020","journal-title":"J. Ambient Intell. Humanized Comput."},{"issue":"8","key":"2022122710510608600_CIT0008","doi-asserted-by":"publisher","first-page":"825","DOI":"10.3390\/electronics8080825","article-title":"A Rapid Recognition Method for Electronic Components Based on the Improved YOLO-V3 Network","volume":"8","author":"Huang","year":"2019","journal-title":"Electronics"},{"key":"2022122710510608600_CIT0009","article-title":"YOLOV3: An Incremental Improvement","author":"Redmon","year":"2018"},{"key":"2022122710510608600_CIT0010","article-title":"Mobilenets: Efficient Convolutional Neural Networks for Mobile Vision Applications","author":"Howard","year":"2017"},{"key":"2022122710510608600_CIT0011","article-title":"SSD: Single Shot Multibox Detector","author":"Liu","year":"2015"},{"key":"2022122710510608600_CIT0012","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2015.169","article-title":"Fast R-CNN","author":"Girshick","year":"2015"},{"issue":"4","key":"2022122710510608600_CIT0013","doi-asserted-by":"publisher","first-page":"040801","DOI":"10.1115\/1.4049535","article-title":"Image-Based Surface Defect Detection Using Deep Learning: A Review","volume":"21","author":"Bhatt","year":"2021","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"key":"2022122710510608600_CIT0014","first-page":"1","article-title":"Unsupervised Image Anomaly Detection and Segmentation Based on Pre-Trained Feature Mapping","volume-title":"IEEE Trans. Ind. Inf.","author":"Wan","year":"2022"},{"key":"2022122710510608600_CIT0015","first-page":"9584","article-title":"MVTec AD \u2013 A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection","author":"Bergmann","year":"2019"},{"issue":"1","key":"2022122710510608600_CIT0016","doi-asserted-by":"publisher","first-page":"209","DOI":"10.3390\/s18010209","article-title":"Anomaly Detection in Nanofibrous Materials by CNN-Based Self-Similarity","volume":"18","author":"Napoletano","year":"2018","journal-title":"Sensors"},{"issue":"4","key":"2022122710510608600_CIT0017","doi-asserted-by":"publisher","first-page":"044502","DOI":"10.1115\/1.4049030","article-title":"A Simple and Fast Hole Detection Algorithm for Triangulated Surfaces","volume":"21","author":"Vijai Kumar","year":"2021","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"3","key":"2022122710510608600_CIT0018","first-page":"031005","article-title":"Segmentation of Additive Manufacturing Defects Using U-Net","volume":"22","author":"Wong","year":"2021","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"2","key":"2022122710510608600_CIT0019","doi-asserted-by":"publisher","first-page":"021009","DOI":"10.1115\/1.4045663","article-title":"An Integrative Machine Learning Method to Improve Fault Detection and Productivity Performance in a Cyber-Physical System","volume":"20","author":"Chiu","year":"2020","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"5","key":"2022122710510608600_CIT0020","doi-asserted-by":"publisher","first-page":"051005","DOI":"10.1115\/1.4053520","article-title":"A Surface Defect Detection Method Via Fusing Multi-Level Features","volume":"22","author":"Ren","year":"2022","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"1","key":"2022122710510608600_CIT0021","doi-asserted-by":"publisher","first-page":"014501","DOI":"10.1115\/1.4051435","article-title":"Steel Surface Defect Detection Using an Ensemble of Deep Residual Neural Networks","volume":"22","author":"Konovalenko","year":"2021","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"key":"2022122710510608600_CIT0022","first-page":"770","article-title":"Deep Residual Learning for Image Recognition","author":"He","year":"2016"},{"issue":"1","key":"2022122710510608600_CIT0023","doi-asserted-by":"publisher","first-page":"011002","DOI":"10.1115\/1.4044097","article-title":"Stress Field Prediction in Cantilevered Structures Using Convolutional Neural Networks","volume":"20","author":"Nie","year":"2020","journal-title":"ASME J. Comput. Inf. Sci. Eng."},{"issue":"10","key":"2022122710510608600_CIT0024","doi-asserted-by":"publisher","first-page":"15017","DOI":"10.1007\/s11042-021-10515-w","article-title":"Medical Image Segmentation Algorithm Based on Multilayer Boundary Perception-Self Attention Deep Learning Model","volume":"80","author":"An","year":"2021","journal-title":"Multim. Tool. Appl.: Int. J."},{"key":"2022122710510608600_CIT0025","first-page":"1150","article-title":"A Deep Convolutional Neural Network With Selection Units for Super-Resolution","author":"Choi","year":"2017"},{"key":"2022122710510608600_CIT0026","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01234-2_18","article-title":"Image Super-Resolution Using Very Deep Residual Channel Attention Networks","author":"Zhang","year":"2018"},{"key":"2022122710510608600_CIT0027","article-title":"Squeezenet: Alexnet-Level Accuracy With 50x Fewer Parameters and &lt;0.5 mb Model Size","author":"Iandola","year":"2016"},{"issue":"6","key":"2022122710510608600_CIT0028","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TPAMI.1986.4767851","article-title":"A Computational Approach to Edge Detection","volume":"PAMI-8","author":"Canny","year":"1986","journal-title":"IEEE. Trans. Pattern. Anal. Mach. Intell."},{"key":"2022122710510608600_CIT0029","first-page":"694","article-title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","author":"Johnson","year":"2016"},{"key":"2022122710510608600_CIT0030","first-page":"7974","article-title":"Image Super-Resolution by Neural Texture Transfer","author":"Zhang","year":"2019"},{"key":"2022122710510608600_CIT0031","article-title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","author":"Ledig","year":"2016"},{"issue":"1","key":"2022122710510608600_CIT0032","doi-asserted-by":"publisher","first-page":"011002","DOI":"10.1115\/1.4052195","article-title":"SuperMeshing: A New Deep Learning Architecture for Increasing the Mesh Density of Physical Fields in Metal Forming Numerical Simulation","volume":"89","author":"Xu","year":"2021","journal-title":"ASME J. Appl. Mech."},{"key":"2022122710510608600_CIT0033","article-title":"Bam: Bottleneck Attention Module","author":"Park","year":"2018"},{"key":"2022122710510608600_CIT0034","doi-asserted-by":"crossref","DOI":"10.4467\/20838476SI.16.004.6185","article-title":"On Loss Functions for Deep Neural Networks in Classification","author":"Janocha","year":"2017"},{"issue":"12","key":"2022122710510608600_CIT0035","doi-asserted-by":"publisher","first-page":"7787","DOI":"10.1109\/TIT.2020.3009923","article-title":"Minimax Optimal Estimation of KL Divergence for Continuous Distributions","volume":"66","author":"Zhao","year":"2020","journal-title":"IEEE Trans. Inform. Theory"},{"key":"2022122710510608600_CIT0036","article-title":"Adam: A Method for Stochastic Optimization","author":"Kingma","year":"2014"},{"key":"2022122710510608600_CIT0037","article-title":"Attention Is All You Need","volume-title":"Neural Information Processing Systems.","author":"Vaswani","year":"2017"},{"key":"2022122710510608600_CIT0038","first-page":"5790","article-title":"Learning Texture Transformer Network for Image Super-Resolution","author":"Yang","year":"2020"},{"key":"2022122710510608600_CIT0039","doi-asserted-by":"publisher","first-page":"182993","DOI":"10.1109\/ACCESS.2019.2959940","article-title":"Spatial Transformer Generative Adversarial Network for Robust Image Super-resolution","volume":"7","author":"Kasem","year":"2019","journal-title":"IEEE Access"}],"container-title":["Journal of Computing and Information Science in Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/23\/4\/041001\/6969868\/jcise_23_4_041001.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/23\/4\/041001\/6969868\/jcise_23_4_041001.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T10:51:46Z","timestamp":1672138306000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article\/23\/4\/041001\/1146311\/Intelligent-Detection-and-Classification-of"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,27]]},"references-count":39,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2023,8,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4055672","relation":{},"ISSN":["1530-9827","1944-7078"],"issn-type":[{"value":"1530-9827","type":"print"},{"value":"1944-7078","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,27]]},"article-number":"041001"}}