{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T06:57:04Z","timestamp":1775113024125,"version":"3.50.1"},"reference-count":35,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T00:00:00Z","timestamp":1749081600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52075261"],"award-info":[{"award-number":["52075261"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>In industrial inspection, X-ray detection methods are the mainstream approach for non-destructive testing (NDT) of weld defects. In response to the issues of insufficient detection accuracy and slow detection speed in existing X-ray weld defect detection (WDD) methods, a lightweight X-ray WDD model, AFD-YOLOv10, based on an improved YOLOv10n, is proposed. First, by introducing variable kernel convolution (AKConv) to replace traditional convolution in the backbone network, the model better adapts to the multi-scale variations in weld defects while maintaining its lightweight nature. Second, a lightweight C2f-Faster module is incorporated into both the backbone and neck networks to achieve a more symmetrical and efficient feature flow, reducing the model\u2019s computational complexity and achieving lightweight design. Finally, dynamic upsampling (DySample) is added to the neck network to enhance the model\u2019s detection accuracy for targets of different scales. This combination of innovations strikes an effective symmetry between model complexity, inference speed, and detection performance. Experimental results show that the improved AFD-YOLOv10 model achieves accuracies, recall rates, and mean average precision values of 90.7%, 88.8%, and 93.8%, respectively, on five typical X-ray weld defects, representing improvements of 4.9%, 4.1%, and 5.3% over the YOLOv10n baseline model, with a 10.1% reduction in model parameters and a 13.3% increase in detection speed. Compared with other existing mainstream detection methods, the AFD-YOLOv10 model not only improves the accuracy of X-ray WDD but also achieves model lightweighting, demonstrating overall detection performance superior to other mainstream algorithms, thus meeting the industrial production requirements for X-ray WDD. Additionally, generalization experiments conducted using a public dataset of surface defects in steel validate the good generalization performance of the AFD-YOLOv10 model.<\/jats:p>","DOI":"10.3390\/sym17060886","type":"journal-article","created":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T08:34:32Z","timestamp":1749112472000},"page":"886","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["AFD-YOLOv10: A Lightweight Method for Non-Destructive Testing of Fusion Weld Seam Defects"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6936-6313","authenticated-orcid":false,"given":"Ranran","family":"Geng","sequence":"first","affiliation":[{"name":"School of Applied Technology, Nanjing Institute of Technology, Nanjing 211167, China"},{"name":"Jiangsu Province Bionic Control Technology and Equipment Engineering Research Center, Nanjing 211167, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5318-8541","authenticated-orcid":false,"given":"Haibin","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Applied Technology, Nanjing Institute of Technology, Nanjing 211167, China"},{"name":"Jiangsu Province Bionic Control Technology and Equipment Engineering Research Center, Nanjing 211167, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5444-9558","authenticated-orcid":false,"given":"Haoyan","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Applied Technology, Nanjing Institute of Technology, Nanjing 211167, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Teng","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Applied Technology, Nanjing Institute of Technology, Nanjing 211167, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,6,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"110484","DOI":"10.1016\/j.ymssp.2023.110484","article-title":"Defect detection method for high-resolution weld based on wandering Gaussian and multi-feature enhancement fusion","volume":"199","author":"Li","year":"2023","journal-title":"Mech. Syst. Sig. Process."},{"key":"ref_2","first-page":"4503612","article-title":"DGICR-Net: Dual-Graph Interactive Consistency Reasoning Network for Weld Defect Recognition with Limited Labeled Samples","volume":"73","author":"Liu","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2241","DOI":"10.1109\/TMECH.2023.3327713","article-title":"An X-ray-based automatic welding defect detection method for special equipment system","volume":"29","author":"Zuo","year":"2023","journal-title":"IEEE-ASME Trans. Mechatron."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1237","DOI":"10.1080\/08839514.2021.1975391","article-title":"Deep learning based steel pipe weld defect detection","volume":"35","author":"Yang","year":"2021","journal-title":"Appl. Artif. Intell."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"107295","DOI":"10.1016\/j.engappai.2023.107295","article-title":"Intelligent identification of girth welds defects in pipelines using neural networks with attention modules","volume":"127","author":"Xu","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"143024","DOI":"10.1016\/j.msea.2022.143024","article-title":"Effects of increasing the strain rate on mechanical twinning and dynamic strain aging in Fe-12.5Mn-1.1C and Fe\u201324Mn-0.45C\u20132Al austenitic steels","volume":"842","author":"Khedr","year":"2022","journal-title":"Mat. Sci. Eng. A-Struct."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Mohandas, R., Mongan, P., and Hayes, M. (2024). Ultrasonic Weld Quality Inspection Involving Strength Prediction and Defect Detection in Data-Constrained Training Environments. Sensors, 24.","DOI":"10.3390\/s24206553"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"108045","DOI":"10.1016\/j.engappai.2024.108045","article-title":"Research on X-ray weld seam defect detection and size measurement method based on neural network self-optimization","volume":"133","author":"Zhang","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1080\/10589759.2023.2197287","article-title":"Non-destructive evaluation of weld defect with coating using electromagnetic induction thermography","volume":"39","author":"Tang","year":"2024","journal-title":"Nondestruct. Test. Eval."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"102176","DOI":"10.1016\/j.ndteint.2019.102176","article-title":"A spectroscopic method based on support vector machine and artificial neural network for fiber laser welding defects detection and classification","volume":"108","author":"Chen","year":"2019","journal-title":"NDT E Int."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1080\/02564602.2014.892739","article-title":"Weld defect detection of X-ray images based on support vector machine","volume":"31","author":"Wang","year":"2014","journal-title":"IETE Technol. Rev."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1007\/s10921-023-01032-x","article-title":"Advanced faster-RCNN model for automated recognition and detection of weld defects on limited X-ray image dataset","volume":"43","author":"Ajmi","year":"2024","journal-title":"J. Nondestr. Eval."},{"key":"ref_13","first-page":"1137","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., and Cheng, Y.F. (2016, January 11\u201314). Ssd: Single shot multibox detector. Proceedings of the Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Li, K.N., Jiao, P.G., Ding, J.M., and Du, W.B. (2024). Bearing defect detection based on the improved YOLOv5 algorithm. PLoS ONE, 19.","DOI":"10.1371\/journal.pone.0310007"},{"key":"ref_16","first-page":"e70005","article-title":"Welding defect detection with image processing on a custom small dataset: A comparative study","volume":"6","author":"Szolosi","year":"2024","journal-title":"IET CIM."},{"key":"ref_17","first-page":"61","article-title":"Weld defect detection by X-ray images method based on Fourier fitting surface","volume":"35","author":"Li","year":"2014","journal-title":"Trans. China Weld. Inst."},{"key":"ref_18","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_19","doi-asserted-by":"crossref","first-page":"6322","DOI":"10.1109\/TII.2019.2896357","article-title":"An effective method of weld defect detection and classification based on machine vision","volume":"15","author":"Sun","year":"2019","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"9235","DOI":"10.1080\/03772063.2022.2040387","article-title":"Intelligent Welding Defect Detection Model on Improved R-CNN","volume":"69","author":"Chen","year":"2022","journal-title":"IETE J. Res."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1016\/j.jmapro.2023.05.058","article-title":"Defect signal intelligent recognition of weld radiographs based on YOLO V5-IMPROVEMENT","volume":"99","author":"Xu","year":"2023","journal-title":"J. Manuf. Processes."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1295","DOI":"10.1080\/10589759.2023.2253494","article-title":"A welding defect detection method based on multiscale feature enhancement and aggregation","volume":"39","author":"Shi","year":"2024","journal-title":"Nondestr. Test. Eval."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2516","DOI":"10.1080\/10589759.2024.2382915","article-title":"DFW-YOLO: YOLOv5-based algorithm using phased array ultrasonic testing for weld defect recognition","volume":"40","author":"Han","year":"2024","journal-title":"Nondestr. Test. Eval."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/10589759.2024.2421941","article-title":"Data enhanced YOLOv8s algorithm for X-ray weld defect detection. Nondestructive","volume":"41","author":"Ding","year":"2024","journal-title":"Nondestr. Test. Eval."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Yang, J., Fu, B., Zeng, J.Q., and Wu, S.X. (2022, January 18\u201323). Yolo-xweld: Efficiently detecting pipeline welding defects in x-ray images for constrained environments. Proceedings of the International Joint Conference on Neural Networks (IJCNN), Padua, Italy.","DOI":"10.1109\/IJCNN55064.2022.9892765"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"7430","DOI":"10.1109\/JSEN.2023.3247006","article-title":"LF-YOLO: A lighter and faster yolo for weld defect detection of X-ray image","volume":"23","author":"Liu","year":"2023","journal-title":"IEEE Sens. J."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zhang, Y., and Ni, Q.J. (2023). A novel weld-seam defect detection algorithm based on the s-yolo model. Axioms, 12.","DOI":"10.3390\/axioms12070697"},{"key":"ref_28","first-page":"107984","article-title":"Yolov10: Real-time end-to-end object detection","volume":"37","author":"Wang","year":"2024","journal-title":"Adv. Neural Inf. Process Syst."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"147942","DOI":"10.1109\/ACCESS.2024.3475629","article-title":"Bird and UAVs Recognition Detection and Tracking Based on Improved YOLOv9-DeepSORT","volume":"12","author":"Zhu","year":"2024","journal-title":"IEEE Access."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"55370","DOI":"10.1109\/ACCESS.2025.3551727","article-title":"Research on long-distance snow depth measurement Method based on improved YOLOv8","volume":"13","author":"Wang","year":"2025","journal-title":"IEEE Access."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Chen, J., Kao, S.H., He, H., Zhuo, W., Wen, S., Lee, C.H., and Chan, S.H.G. (2023, January 17\u201324). Run, Don\u2019t Walk: Chasing Higher FLOPS for Faster Neural Networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Fu, R.G., Hu, Q.Y., Dong, X.H., Gao, Y.H., Li, B., and Zhong, P. (2024, January 1\u20135). Lighten CARAFE: Dynamic Lightweight Upsampling with Guided Reassemble Kernels. Proceedings of the International Conference on Pattern Recognition, Kolkata, India.","DOI":"10.2139\/ssrn.4671723"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1007\/s10921-015-0315-7","article-title":"GDXray: The database of X-ray images for nondestructive testing","volume":"34","author":"Mery","year":"2015","journal-title":"J. Nondestr. Eval."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"55382","DOI":"10.1109\/ACCESS.2025.3552683","article-title":"EAD-YOLOv10: Lightweight Steel Surface Defect Detection Algorithm Research Based on YOLOv10 Improvement","volume":"13","author":"Hu","year":"2025","journal-title":"IEEE Access."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1338","DOI":"10.1007\/s11837-019-03329-7","article-title":"Evolution of Fracture Mode in Nano-twinned Fe-1.1C-12.5Mn Steel","volume":"71","author":"Khedr","year":"2019","journal-title":"Jom"}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/6\/886\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:47:04Z","timestamp":1760032024000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/6\/886"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,5]]},"references-count":35,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["sym17060886"],"URL":"https:\/\/doi.org\/10.3390\/sym17060886","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,5]]}}}