{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T16:54:49Z","timestamp":1777913689839,"version":"3.51.4"},"reference-count":54,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2021,9,18]],"date-time":"2021-09-18T00:00:00Z","timestamp":1631923200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Aiming at the problem of the poor robustness of existing methods to deal with diverse industrial weld image data, we collected a series of asymmetric laser weld images in the largest laser equipment workshop in Asia, and studied these data based on an industrial image processing algorithm and deep learning algorithm. The median filter was used to remove the noises in weld images. The image enhancement technique was adopted to increase the image contrast in different areas. The deep convolutional neural network (CNN) was employed for feature extraction; the activation function and the adaptive pooling approach were improved. Transfer Learning (TL) was introduced for defect detection and image classification on the dataset. Finally, a deep learning-based model was constructed for weld defect detection and image recognition. Specific instance datasets verified the model\u2019s performance. The results demonstrate that this model can accurately identify weld defects and eliminate the complexity of manually extracting features, reaching a recognition accuracy of 98.75%. Hence, the reliability and automation of detection and recognition are improved significantly. The research results can provide a theoretical and practical reference for the defect detection of sheet metal laser welding and the development of the industrial laser manufacturing industry.<\/jats:p>","DOI":"10.3390\/sym13091731","type":"journal-article","created":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T22:35:20Z","timestamp":1632263720000},"page":"1731","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":65,"title":["Industrial Laser Welding Defect Detection and Image Defect Recognition Based on Deep Learning Model Developed"],"prefix":"10.3390","volume":"13","author":[{"given":"Honggui","family":"Deng","sequence":"first","affiliation":[{"name":"School of Physics and Electronics, Central South University, Changsha 410012, China"}]},{"given":"Yu","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Physics and Electronics, Central South University, Changsha 410012, China"}]},{"given":"Yuxin","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Physics and Electronics, Central South University, Changsha 410012, China"},{"name":"Shen Zhen Han\u2019s Laser Technology Co., Ltd., Shenzhen 518057, China"}]},{"given":"Junjiang","family":"Xiang","sequence":"additional","affiliation":[{"name":"School of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, China"}]}],"member":"1968","published-online":{"date-parts":[[2021,9,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Qiao, J., Yu, P., Wu, Y., Chen, T., Du, Y., and Yang, J. (2020). A Compact Review of Laser Welding Technologies for Amorphous Alloys. Metals, 12.","DOI":"10.3390\/met10121690"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/j.ndteint.2009.11.002","article-title":"An adaptive-network-based fuzzy inference system for classification of welding defects","volume":"43","author":"Zapata","year":"2010","journal-title":"NDT E Int."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"164369","DOI":"10.1016\/j.nima.2020.164369","article-title":"Application of compact laser-driven accelerator X-ray sources for industrial imaging","volume":"983","author":"Gruse","year":"2020","journal-title":"Nucl. Instrum. Methods Phys. Res. Sect. A Accel. Spectrom. Detect. Assoc. Equip."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"240","DOI":"10.4028\/www.scientific.net\/DDF.405.240","article-title":"Defects of Steel Sheets Joined by Laser Welding","volume":"405","author":"Zubko","year":"2020","journal-title":"Defect Diffus. Forum"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Schmid, M., Bhogaraju, S.K., Liu, E., and Elger, G. (2020). Comparison of Nondestructive Testing Methods for Solder, Sinter, and Adhesive Interconnects in Power and Opto-Electronics. Appl. Sci., 10.","DOI":"10.3390\/app10238516"},{"key":"ref_6","first-page":"234","article-title":"Film-Screen Radiography in Bachelor\u2019s Degree Program Curriculum","volume":"88","author":"Ricketts","year":"2016","journal-title":"Radiol. Technol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1007\/s10921-019-0616-3","article-title":"A Cumulative sums algorithm for segmentation of digital X-ray images","volume":"38","author":"Vorobeychikov","year":"2019","journal-title":"J. Nondestruct. Eval."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1955","DOI":"10.1016\/j.aej.2020.11.043","article-title":"Evaluation of flow pattern recognition and void fraction measurement in two phase flow independent of oil pipeline\u2019s scale layer thickness","volume":"60","author":"Roshani","year":"2021","journal-title":"Alex. Eng. J."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Nisar, M.U., Voghoei, S., and Ramaswamy, L. (2017, January 5\u20138). Caching for pattern matching queries in time evolving graphs: Challenges and approaches. Proceedings of the 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS), Atlanta, GA, USA.","DOI":"10.1109\/ICDCS.2017.57"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1334","DOI":"10.1049\/iet-cta.2019.0651","article-title":"Robust delay-dependent LPV synthesis for blood pressure control with real-time Bayesian parameter estimation","volume":"14","author":"Tasoujian","year":"2020","journal-title":"IET Control. Theory Appl."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Karimi, M., Jahanshahi, A., Mazloumi, A., and Sabzi, H.Z. (2019, January 9\u201312). Border gateway protocol anomaly detection using neural network. Proceedings of the 2019 IEEE International Conference on Big Data (Big Data), Los Angeles, CA, USA.","DOI":"10.1109\/BigData47090.2019.9006201"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1016\/j.isatra.2020.01.011","article-title":"Supervisory predictive control for wheel slip prevention and tracking of desired speed profile in electric trains","volume":"101","author":"Moaveni","year":"2020","journal-title":"ISA Trans."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Voghoei, S., Tonekaboni, N.H., Yazdansepas, D., Soleymani, S., Farahani, A., and Arabnia, H.R. (2020, January 2\u20134). Personalized Feedback Emails: A Case Study on Online Introductory Computer Science Courses. Proceedings of the 2020 ACM Southeast Conference, Tampa, FL, USA.","DOI":"10.1145\/3374135.3385274"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Shih, P.C., Hsu, C.C., and Tien, F.C. (2020). Automatic Reclaimed Wafer Classification Using Deep Learning Neural Networks. Symmetry, 12.","DOI":"10.3390\/sym12050705"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Brachmann, A., and Redies, C. (2016). Using Convolutional Neural Network Filters to Measure Left-Right Mirror Symmetry in Images. Symmetry, 8.","DOI":"10.3390\/sym8120144"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zhang, M., Diao, M., Gao, L., and Liu, L. (2017). Neural Networks for Radar Waveform Recognition. Symmetry, 9.","DOI":"10.3390\/sym9050075"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1016\/j.measurement.2018.09.011","article-title":"Deep features based on a DCNN model for classifying imbalanced weld flaw types","volume":"131","author":"Hou","year":"2019","journal-title":"Measurement"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3389","DOI":"10.1038\/s41598-020-60294-x","article-title":"Supervised deep learning for real-time quality monitoring of laser welding with X-ray radiographic guidance","volume":"10","author":"Shevchik","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1007\/s10921-020-00719-9","article-title":"Using Deep Learning for Defect Classification on a Small Weld X-ray Image Dataset","volume":"39","author":"Ajmi","year":"2020","journal-title":"J. Nondestruct. Eval."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1574350","DOI":"10.1155\/2020\/1574350","article-title":"Deep Learning Technology for Weld Defects Classification Based on Transfer Learning and Activation Features","volume":"2020","author":"Ajmi","year":"2020","journal-title":"Adv. Mater. Sci. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Boikov, A., Payor, V., Savelev, R., and Kolesnikov, A. (2021). Synthetic Data Generation for Steel Defect Detection and Classification Using Deep Learning. Symmetry, 13.","DOI":"10.3390\/sym13071176"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"108981","DOI":"10.1016\/j.matdes.2020.108981","article-title":"In-process calibration of a non-destructive testing system used for in-process inspection of multi-pass welding","volume":"195","author":"Javadi","year":"2020","journal-title":"Mater. Des."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/j.ndteint.2016.11.003","article-title":"Automated detection of welding defects in pipelines from radiographic images DWDI","volume":"86","author":"Boaretto","year":"2017","journal-title":"NDT E Int."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Bestard, G.A., Sampaio, R.C., Vargas, J.A., and Alfaro, S.C.A. (2018). Sensor fusion to estimate the depth and width of the weld bead in real time in GMAW processes. Sensors, 18.","DOI":"10.3390\/s18040962"},{"key":"ref_25","unstructured":"Vasilev, M., MacLeod, C., Galbraith, W., Pierce, G., and Gachagan, A. (2019, January 14\u201319). In-process ultrasonic inspection of thin mild steel plate GMAW butt welds using non-contact guided waves. Proceedings of the 46th Annual Review of Progress in Quantitative Nondestructive Evaluation QNDE2019, Portland, OR, USA."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"101825","DOI":"10.1016\/j.rcim.2019.101825","article-title":"A semi-supervised convolutional neural network-based method for steel surface defect recognition","volume":"61","author":"Gao","year":"2020","journal-title":"Robot. Comput.-Integr. Manuf."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"239s","DOI":"10.29391\/2020.99.022","article-title":"Deep Learning-Based Detection of Penetration from Weld Pool Reflection Images","volume":"99","author":"Li","year":"2020","journal-title":"Weld. J."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"111347","DOI":"10.1016\/j.engstruct.2020.111347","article-title":"A systematic review of convolutional neural network-based structural condition assessment techniques","volume":"226","author":"Sony","year":"2021","journal-title":"Eng. Struct."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"4392","DOI":"10.1109\/TIE.2017.2764844","article-title":"NB-CNN: Deep learning-based crack detection using convolutional neural network and Na\u00efve Bayes data fusion","volume":"65","author":"Chen","year":"2017","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1002\/arp.1730","article-title":"Object-based image analysis: A review of developments and future directions of automated feature detection in landscape archaeology","volume":"26","author":"Davis","year":"2019","journal-title":"Archaeol. Prospect."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1016\/j.jmatprotec.2017.03.031","article-title":"Welding quality monitoring of high frequency straight seam pipe based on image feature","volume":"246","author":"Li","year":"2017","journal-title":"J. Mater. Process. Technol."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1713","DOI":"10.1007\/s00170-019-04401-x","article-title":"Identification of weld defects using magneto-optical imaging","volume":"105","author":"Gao","year":"2019","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_33","first-page":"73","article-title":"Survey on evolving deep learning neural network architectures","volume":"1","author":"Bashar","year":"2019","journal-title":"J. Artif. Intell."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"166342","DOI":"10.1016\/j.ijleo.2021.166342","article-title":"An autonomous technique for weld defects detection and classification using multi-class support vector machine in X-radiography image","volume":"231","author":"Malarvel","year":"2021","journal-title":"Optik"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.chemolab.2017.07.008","article-title":"Multi-class classification for steel surface defects based on machine learning with quantile hyper-spheres","volume":"168","author":"Chu","year":"2017","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_36","first-page":"123","article-title":"Classification of surface defects on steel sheet using convolutional neural networks","volume":"51","author":"Zhou","year":"2017","journal-title":"Mater. Technol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.chemolab.2017.11.018","article-title":"Steel surface defect classification using multiple hyper-spheres support vector machine with additional information","volume":"172","author":"Gong","year":"2018","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.chemolab.2018.03.014","article-title":"Multi-class classification method using twin support vector machines with multi-information for steel surface defects","volume":"176","author":"Chu","year":"2018","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.ifacol.2018.09.412","article-title":"Real-time detection of steel strip surface defects based on improved yolo detection network","volume":"51","author":"Li","year":"2018","journal-title":"IFAC-PapersOnLine"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1177\/0020294018801382","article-title":"Challenges in improving the performance of eddy current testing","volume":"52","author":"AbdAlla","year":"2019","journal-title":"Meas. Control."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"102952","DOI":"10.1016\/j.rinp.2020.102952","article-title":"An infrared perfect absorber based on metal-dielectric-metal multi-layer films with nanocircle holes arrays","volume":"16","author":"Wu","year":"2020","journal-title":"Results Phys."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.ndteint.2017.07.002","article-title":"Composite magnetic flux leakage detection method for pipelines using alternating magnetic field excitation","volume":"91","author":"Wu","year":"2017","journal-title":"NDT E Int."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Yoo, Y., and Baek, J.-G. (2018). A novel image feature for the remaining useful lifetime prediction of bearings based on continuous wavelet transform and convolutional neural network. Appl. Sci., 8.","DOI":"10.3390\/app8071102"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/j.autcon.2019.02.013","article-title":"A vision-based method for crack detection in gusset plate welded joints of steel bridges using deep convolutional neural networks","volume":"102","author":"Dung","year":"2019","journal-title":"Autom. Constr."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Shin, S., Jin, C., Yu, J., and Rhee, S. (2020). Real-time detection of weld defects for automated welding process base on deep neural network. Metals, 10.","DOI":"10.3390\/met10030389"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1002\/prep.201900157","article-title":"Application of Colloid Water Covering on Explosive Welding of AA1060 Foil to Q235 Steel Plate","volume":"45","author":"Yang","year":"2020","journal-title":"Propellants Explos. Pyrotech."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1016\/j.measurement.2019.04.072","article-title":"Optimal bilateral filter and convolutional neural network based denoising method of medical image measurements","volume":"143","author":"Elhoseny","year":"2019","journal-title":"Measurement"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"2798","DOI":"10.1016\/j.neucom.2017.11.057","article-title":"Brightness and contrast controllable image enhancement based on histogram specification","volume":"275","author":"Xiao","year":"2018","journal-title":"Neurocomputing"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1038\/s41586-020-1942-4","article-title":"Fully hardware-implemented memristor convolutional neural network","volume":"577","author":"Yao","year":"2020","journal-title":"Nature"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/j.mineng.2018.12.011","article-title":"Flotation froth image recognition with convolutional neural networks","volume":"132","author":"Fu","year":"2019","journal-title":"Miner. Eng."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"70","DOI":"10.5573\/IEIESPC.2018.7.1.070","article-title":"A Comparative Study of Transfer Learning\u2013based Methods for Inspection of Mobile Camera Modules","volume":"7","author":"Choi","year":"2018","journal-title":"IEIE Trans. Smart Process. Comput."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1520\/SSMS20180033","article-title":"Detection and segmentation of manufacturing defects with convolutional neural networks and transfer learning","volume":"2","author":"Ferguson","year":"2018","journal-title":"Smart Sustain. Manuf. Syst."},{"key":"ref_53","unstructured":"Chrabaszcz, P., Loshchilov, I., and Hutter, F. (2017). A Downsampled Variant of ImageNet as an Alternative to the CIFAR Datasets. arXiv."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.buildenv.2017.01.015","article-title":"Performance evaluation of an agent-based occupancy simulation model","volume":"115","author":"Luo","year":"2017","journal-title":"Build. Environ."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/13\/9\/1731\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:01:43Z","timestamp":1760166103000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/13\/9\/1731"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,18]]},"references-count":54,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2021,9]]}},"alternative-id":["sym13091731"],"URL":"https:\/\/doi.org\/10.3390\/sym13091731","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,18]]}}}