{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T10:15:26Z","timestamp":1783332926192,"version":"3.54.6"},"reference-count":29,"publisher":"SAGE Publications","issue":"3","license":[{"start":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T00:00:00Z","timestamp":1774310400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/501100004480","name":"Natural Science Foundation of Shanxi Province","doi-asserted-by":"publisher","award":["202303021211148"],"award-info":[{"award-number":["202303021211148"]}],"id":[{"id":"10.13039\/501100004480","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of X-Ray Science and Technology"],"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Industrial weld defect detection is challenged by the minimal grayscale contrast between defects and the background, as well as by blurred defect edges, which together hinder the performance of detection algorithms. Moreover, practical industrial environments require high detection accuracy, fast inference speed, and flexible deployment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To address these challenges, this study proposes an improved YOLOv8n defect detection method that enables more accurate, faster, and lightweight automated weld defect detection.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The key improvements are as follows. First, in the backbone, the original C2f module is replaced by the C2f_OREPA feature extraction module, constructed with the Online Convolution Parameterization Approach (OREPA), which reduces computational complexity and enhances feature representation. Second, a downsampling module, DCDConv, is introduced to replace the conventional convolution after the first standard convolution layer, allowing better preservation of fine defect features and improving the detection of subtle defects. Additionally, in the neck, a cross-scale feature fusion module (CCFM) is incorporated to improve detection performance across defects of different scales.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Experiments on our self-constructed dataset comprising eight weld defect categories show that the improved model achieves a mean average precision (mAP) of 87.6%, a 4.5% increase over the original YOLOv8n. Meanwhile, the model reduces the number of parameters by 26.9%, decreases computational cost by 35.7%, and achieves an inference speed of 103 frames per second (FPS). On the public NEU-DET dataset, the improved model obtains an mAP of 82.8%, outperforming the original YOLOv8n by 6.7%. Overall, the proposed model surpasses mainstream object detection frameworks, including YOLOv8n, YOLOv12n, Faster R-CNN, and RetinaNet.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>In summary, the proposed method provides an accurate, efficient, and deployment-friendly solution for weld defect detection in industrial applications, demonstrating substantial practical value.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/08953996261433937","type":"journal-article","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T09:32:27Z","timestamp":1774344747000},"page":"225-240","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Weld defect detection based on improved YOLOv8n"],"prefix":"10.1177","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9066-4846","authenticated-orcid":false,"given":"Yongqi","family":"Yan","sequence":"first","affiliation":[{"name":"State key Laboratory of Extreme Environment Optoelectronic Dynamic Testing Technology and Instrument, North University of China, Taiyuan, China"},{"name":"School of Information and Communication Engineering, North University of China, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1967-3048","authenticated-orcid":false,"given":"Yi","family":"Liu","sequence":"additional","affiliation":[{"name":"State key Laboratory of Extreme Environment Optoelectronic Dynamic Testing Technology and Instrument, North University of China, Taiyuan, China"},{"name":"School of Information and Communication Engineering, North University of China, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5586-5839","authenticated-orcid":false,"given":"Lingshuang","family":"Meng","sequence":"additional","affiliation":[{"name":"State key Laboratory of Extreme Environment Optoelectronic Dynamic Testing Technology and Instrument, North University of China, Taiyuan, China"},{"name":"School of Computer Science and Technology, North University of China, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8112-9614","authenticated-orcid":false,"given":"Junjing","family":"Li","sequence":"additional","affiliation":[{"name":"State key Laboratory of Extreme Environment Optoelectronic Dynamic Testing Technology and Instrument, North University of China, Taiyuan, China"},{"name":"School of Computer Science and Technology, North University of China, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8370-9625","authenticated-orcid":false,"given":"Shu","family":"Li","sequence":"additional","affiliation":[{"name":"State key Laboratory of Extreme Environment Optoelectronic Dynamic Testing Technology and Instrument, North University of China, Taiyuan, China"},{"name":"School of Information and Communication Engineering, North University of China, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5771-492X","authenticated-orcid":false,"given":"Niu","family":"Guo","sequence":"additional","affiliation":[{"name":"State key Laboratory of Extreme Environment Optoelectronic Dynamic Testing Technology and Instrument, North University of China, Taiyuan, China"},{"name":"School of Information and Communication Engineering, North University of China, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0656-7254","authenticated-orcid":false,"given":"Pengcheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"State key Laboratory of Extreme Environment Optoelectronic Dynamic Testing Technology and Instrument, North University of China, Taiyuan, China"},{"name":"School of Information and Communication Engineering, North University of China, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8991-9907","authenticated-orcid":false,"given":"Zhiguo","family":"Gui","sequence":"additional","affiliation":[{"name":"State key Laboratory of Extreme Environment Optoelectronic Dynamic Testing Technology and Instrument, North University of China, Taiyuan, China"},{"name":"School of Information and Communication Engineering, North University of China, Taiyuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,3,24]]},"reference":[{"key":"e_1_3_3_2_2","first-page":"1","article-title":"Research progress on visual perception of welding robots and key technologies for intelligent welding","volume":"45","author":"Chen HB","year":"2024","unstructured":"Chen HB, Xiao RQ, Chen SB. Research progress on visual perception of welding robots and key technologies for intelligent welding. Trans China Weld Inst 2024; 45: 1\u20139.","journal-title":"Trans China Weld Inst"},{"key":"e_1_3_3_3_2","first-page":"10","article-title":"Research status and prospects of intelligent monitoring technology for welding","volume":"45","author":"Zhang ZF","year":"2024","unstructured":"Zhang ZF, Chen SB, Zhang YM, et al. Research status and prospects of intelligent monitoring technology for welding. Trans China Weld Inst 2024; 45: 10\u201320.","journal-title":"Trans China Weld Inst"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10438-y"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.3390\/s25103038"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.3390\/plants14162475"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1912.02424"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","unstructured":"Bochkovskiy A Wang C Liao H-M. YOLOv4: Optimal speed and accuracy of object detection. arXiv preprint 2020: 10934. doi: 10.48550\/arXiv.2004.10934.","DOI":"10.48550\/arXiv.2004.10934"},{"key":"e_1_3_3_9_2","first-page":"30","article-title":"Lightweight YOLO network-based real-time X-ray welding defect detection","volume":"12","author":"Long L","year":"2023","unstructured":"Long L, Chen H, Liang H, et al. Lightweight YOLO network-based real-time X-ray welding defect detection. Network New Media Technol 2023; 12: 30\u201338.","journal-title":"Network New Media Technol"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00065"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1080\/03772063.2022.2040387"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1177\/00202940221092030"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10921-023-01032-x"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ndteint.2024.103059"},{"key":"e_1_3_3_16_2","first-page":"24","article-title":"Defect identification algorithm for weld X-ray images based on CCBFE-RCNN model","volume":"46","author":"Dai Z","year":"2025","unstructured":"Dai Z, Liu XJ, Pan Q. Defect identification algorithm for weld X-ray images based on CCBFE-RCNN model. Trans China Weld Inst 2025; 46: 24\u201333.","journal-title":"Trans China Weld Inst"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.3390\/app10238629"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1080\/13621718.2022.2061691"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2023.3247006"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1080\/08839514.2021.1975391"},{"key":"e_1_3_3_21_2","first-page":"29","article-title":"Sim-YOLOv8 target detection model for aluminum alloy weld DR image defects","volume":"51","author":"Wu L","year":"2024","unstructured":"Wu L, Chu YK, Yang HG, et al. Sim-YOLOv8 target detection model for aluminum alloy weld DR image defects. Chin J Lasers 2024; 51: 29\u201338.","journal-title":"Chin J Lasers"},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ndteint.2023.102919"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.3390\/s23218677"},{"key":"e_1_3_3_24_2","first-page":"766","article-title":"Improved X-ray pipe weld detection algorithm for YOLO","volume":"45","author":"Wang HJ","year":"2024","unstructured":"Wang HJ, Lin N, Lin ZC, et al. Improved X-ray pipe weld detection algorithm for YOLO. Huaqiao Univ (Nat Sci Ed) 2024; 45: 766\u2013775.","journal-title":"Huaqiao Univ (Nat Sci Ed)"},{"key":"e_1_3_3_25_2","first-page":"60","article-title":"RetinaNet-based wheel weld detection and localization method","volume":"09","author":"Li X","year":"2022","unstructured":"Li X, Ren DJ, Ren QL, et al. RetinaNet-based wheel weld detection and localization method. Comput Modern 2022; 09: 60\u201367.","journal-title":"Comput Modern"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-024-03738-5"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1088\/2631-8695\/ae040d"},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3151138"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","unstructured":"Li H Zhang Y Zhang Y et al. DCNv3: Towards next generation deep cross network for CTR prediction. 2024. doi: 10.48550\/arXiv.2407.13349","DOI":"10.48550\/arXiv.2407.13349"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.07947"}],"container-title":["Journal of X-Ray Science and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/08953996261433937","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/08953996261433937","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/08953996261433937","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T09:32:33Z","timestamp":1783330353000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/08953996261433937"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,24]]},"references-count":29,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["10.1177\/08953996261433937"],"URL":"https:\/\/doi.org\/10.1177\/08953996261433937","relation":{},"ISSN":["0895-3996","1095-9114"],"issn-type":[{"value":"0895-3996","type":"print"},{"value":"1095-9114","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,24]]}}}