{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T04:58:52Z","timestamp":1783659532255,"version":"3.55.0"},"reference-count":22,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T00:00:00Z","timestamp":1683504000000},"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 (NSFC)","doi-asserted-by":"publisher","award":["51975015"],"award-info":[{"award-number":["51975015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Deep learning technology has advanced rapidly and has started to be applied for the detection of welding defects. In the manufacturing process of power batteries for new energy vehicles, welding defects may occur due to the high directivity, convergence, and penetration of the laser beam. The accuracy of deep learning prediction relies heavily on big data, but balanced big data of welding defects is hard to acquire at the battery production site. In this paper, the authors construct a dataset named RIAM, which consists of images captured from an industrial environment for laser welding of power battery modules. RIAM contains four types of images: Normality, Lack of fusion, Surface porosity, and Scaled surface. The characteristics of RIAM are carefully considered in the application scenarios. Moreover, this paper proposes a gradient-based unsupervised model named Grad-MobileNet, which can be trained with only a few normal images and can extract the feature gradients of the input images. Welding defects can then be classified by the gradient distribution. This model is based on MobileNetV3, which is a lightweight convolutional neural network (CNN), and achieves 99% accuracy, which is higher than the accuracy expected from supervised learning.<\/jats:p>","DOI":"10.3390\/s23094563","type":"journal-article","created":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T05:09:19Z","timestamp":1683522559000},"page":"4563","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Grad-MobileNet: A Gradient-Based Unsupervised Learning Method for Laser Welding Surface Defect Classification"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1795-6423","authenticated-orcid":false,"given":"Sizhe","family":"Xiao","sequence":"first","affiliation":[{"name":"Beijing Research Institute of Automation for Machinery Industry, Beijing 100120, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenguo","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing Research Institute of Automation for Machinery Industry, Beijing 100120, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihong","family":"Yan","sequence":"additional","affiliation":[{"name":"Faculty of Materials and Manufacturing, Beijing University of Technology, Beijing 100124, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingquan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Beijing Jiaotong University, Beijing 100044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,5,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1","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. Nondestruct. Eval."},{"key":"ref_2","unstructured":"Liu, B., Zhang, X., Gao, Z., and Chen, L. (2017). International Forum on Digital TV and Wireless Multimedia Communications, Springer."},{"key":"ref_3","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_4","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Hinton","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Khumaidi, A., Yuniarno, E.M., and Purnomo, M.H. (2017, January 28\u201329). Welding defect classification based on convolution neural network (CNN) and Gaussian kernel. Proceedings of the 2017 International Seminar on Intelligent Technology and Its Applications (ISITIA), Surabaya, Indonesia.","DOI":"10.1109\/ISITIA.2017.8124091"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1016\/j.jmapro.2019.07.020","article-title":"Automated defect classification of Aluminium 5083 TIG welding using HDR camera and neural networks","volume":"45","author":"Bacioiu","year":"2019","journal-title":"J. Manuf. Process."},{"key":"ref_7","unstructured":"Huang, X. (2019). Deep Transfer Learning for Online Welding Quality Monitoring. [Master\u2019s Thesis, Guangxi University]."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"531","DOI":"10.5768\/JAO202041.0302007","article-title":"Research on weld defect image classification based on convolutional neural network","volume":"41","author":"Gu","year":"2020","journal-title":"J. Appl. Opt."},{"key":"ref_9","first-page":"79","article-title":"Defect detection of weld X-ray image based on edge AI","volume":"43","author":"Wang","year":"2022","journal-title":"Trans. China Weld. Inst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"102597","DOI":"10.1016\/j.ndteint.2021.102597","article-title":"Approach to weld segmentation and defect classification in radiographic images of pipe welds","volume":"127","author":"Golodov","year":"2022","journal-title":"NDT E Int."},{"key":"ref_11","unstructured":"Smilkov, G., Thorat, N., Kim, B., Vi\u00e9gas, F., and Wattenberg, M. (2017). Smoothgrad: Removing noise by adding noise. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-cam: Visual explanations from deep networks via gradient-based localization. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_13","unstructured":"Omeiza, D., Speakman, S., Cintas, C., and Weldermariam, K. (2019). Smooth grad-cam++: An enhanced inference level visualization technique for deep convolutional neural network models. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1266","DOI":"10.1109\/TIM.2018.2795178","article-title":"An unsupervised-learning-based approach for automated defect inspection on textured surfaces","volume":"67","author":"Mei","year":"2018","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Haselmann, M., Gruber, D.P., and Tabatabai, P. (2018, January 7\u201320). Anomaly detection using deep learning based image completion. Proceedings of the 17th IEEE International Conference on Machine Learning and Applications (ICMLA), Orlando, FL, USA.","DOI":"10.1109\/ICMLA.2018.00201"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"2679","DOI":"10.1109\/TIM.2018.2868490","article-title":"Deep architecture for high-speed railway insulator surface defect detection: Denoising autoencoder with multitask learning","volume":"68","author":"Kang","year":"2018","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_17","unstructured":"Schlegl, T., Seeb\u00f6ck, P., Waldstein, S.M., Schmidt-Erfurth, U., and Langs, G. (2017). International Conference on Information Processing in Medical Imaging, Springer."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Lai, Y.-T.K., and Hu, J.-S. (2018, January 7\u201310). A texture generation approach for detection of novel surface defects. Proceedings of the 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Miyazaki, Japan.","DOI":"10.1109\/SMC.2018.00736"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1177\/0040517519862880","article-title":"Unsupervised fabric defect detection based on a deep convolutional generative adversarial network","volume":"90","author":"Hu","year":"2020","journal-title":"Text. Res. J."},{"key":"ref_20","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L.-C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (November, January 27). Searching for mobilenetv3. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada."},{"key":"ref_21","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017, January 21\u201326). Mobilenets: Efficient convolutional neural networks for mobile vision applications. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018, January 16\u201323). Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00474"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/9\/4563\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:31:13Z","timestamp":1760124673000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/9\/4563"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,8]]},"references-count":22,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2023,5]]}},"alternative-id":["s23094563"],"URL":"https:\/\/doi.org\/10.3390\/s23094563","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,8]]}}}