{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T04:45:58Z","timestamp":1774932358362,"version":"3.50.1"},"reference-count":25,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2023,9,26]],"date-time":"2023-09-26T00:00:00Z","timestamp":1695686400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>With the development of deep fusion intelligent control technology and the application of low-carbon energy, the number of renewable energy sources connected to the distribution grid has been increasing year by year, gradually replacing traditional distribution grids with active distribution grids. In addition, as an important component of the distribution grid, substations have a complex internal environment and numerous devices. The problems of untimely defect detection and slow response during intelligent inspections are particularly prominent, posing risks and challenges to the safe and stable operation of active distribution grids. To address these issues, this paper proposes a high-performance and lightweight substation defect detection model called YOLO-Substation-large (YOLO-SS-large) based on YOLOv5m. The model improves lightweight performance based upon the FasterNet network structure and obtains the F-YOLOv5m model. Furthermore, in order to enhance the detection performance of the model for small object defects in substations, the normalized Wasserstein distance (NWD) and complete intersection over union (CIoU) loss functions are weighted and fused to design a novel loss function called NWD-CIoU. Lastly, based on the improved model mentioned above, the dynamic head module is introduced to unify the scale-aware, spatial-aware, and task-aware attention of the object detection heads of the model. Compared to the YOLOv5m model, the YOLO-SS-Large model achieves an average precision improvement of 0.3%, FPS enhancement of 43.5%, and parameter reduction of 41.0%. This improved model demonstrates significantly enhanced comprehensive performance, better meeting the requirements of the speed and precision for substation defect detection, and plays an important role in promoting the informatization and intelligent construction of active distribution grids.<\/jats:p>","DOI":"10.3390\/s23198080","type":"journal-article","created":{"date-parts":[[2023,9,26]],"date-time":"2023-09-26T03:45:23Z","timestamp":1695699923000},"page":"8080","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["YOLO-SS-Large: A Lightweight and High-Performance Model for Defect Detection in Substations"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2931-7875","authenticated-orcid":false,"given":"Qian","family":"Wang","sequence":"first","affiliation":[{"name":"Qujiang Campus, School of Electrical Engineering, Xi\u2019an University of Technology, Xi\u2019an 710048, China"}]},{"given":"Lixin","family":"Yang","sequence":"additional","affiliation":[{"name":"Qujiang Campus, School of Electrical Engineering, Xi\u2019an University of Technology, Xi\u2019an 710048, China"}]},{"given":"Bin","family":"Zhou","sequence":"additional","affiliation":[{"name":"North China Electric Power Research Institute Co., Ltd. Xi\u2019an Branch, Xi\u2019an 710000, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8260-0584","authenticated-orcid":false,"given":"Zhirong","family":"Luan","sequence":"additional","affiliation":[{"name":"Qujiang Campus, School of Electrical Engineering, Xi\u2019an University of Technology, Xi\u2019an 710048, China"}]},{"given":"Jiawei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Qujiang Campus, School of Electrical Engineering, Xi\u2019an University of Technology, Xi\u2019an 710048, China"}]}],"member":"1968","published-online":{"date-parts":[[2023,9,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Wang, X., Shrivastava, A., and Gupta, A. (2017, January 21\u201326). A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detection. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.324"},{"key":"ref_2","unstructured":"Purkait, P., Zhao, C., and Zach, C. (2017). SPP-Net: Deep Absolute Pose Regression with Synthetic Views. arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015, January 7\u201313). Fast R-CNN. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"085403","DOI":"10.1088\/1361-6501\/ac68d2","article-title":"CASPPNet: A chained atrous spatial pyramid pooling network for steel defect detection","volume":"33","author":"Zheng","year":"2022","journal-title":"Meas. Sci. Technol."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Pochelu, P., Erard, C., Cordier, P., Petiton, S.G., and Conche, B. (2021). Weakly Supervised Faster-RCNN+FPN to classify small animals in camera trap images. arXiv.","DOI":"10.36227\/techrxiv.17068454"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"560","DOI":"10.1007\/s40544-021-0516-2","article-title":"Morphological residual convolutional neural network (M-RCNN) for intelligent recognition of wear particles from artificial joints","volume":"10","author":"Hu","year":"2022","journal-title":"Friction"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27\u201330). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the Computer Vision & Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zhang, W., Ma, X., Zhang, Y., Ji, M., and Zhen, C. (2022). SMYOLO: Lightweight Pedestrian Target Detection Algorithm in Low-Altitude Scenarios. Future Internet, 14.","DOI":"10.3390\/fi14010021"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"19760","DOI":"10.1109\/TITS.2021.3137253","article-title":"Vehicle and Pedestrian Detection Algorithm Based on Lightweight YOLOv3-Promote and Semi-Precision Acceleration","volume":"23","author":"Xu","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Jiang, S., and Zhou, X. (2022). DWSC-YOLO: A Lightweight Ship Detector of SAR Images Based on Deep Learning. J. Mar. Sci. Eng., 10.","DOI":"10.3390\/jmse10111699"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ji, W., Pan, Y., Xu, B., and Wang, J. (2022). A Real-Time Apple Targets Detection Method for Picking Robot Based on ShufflenetV2-YOLOX. Agriculture, 12.","DOI":"10.3390\/agriculture12060856"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhang, X., Li, N., and Zhang, R. (2021, January 15\u201317). An Improved Lightweight Network MobileNetv3 Based YOLOv3 for Pedestrian Detection. Proceedings of the 2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE), Guangzhou, China.","DOI":"10.1109\/ICCECE51280.2021.9342416"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s00530-022-00982-y","article-title":"A multitask joint framework for real-time person search","volume":"29","author":"Li","year":"2023","journal-title":"Multimed. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., and Savarese, S. (2019, January 15\u201320). Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref_15","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., and Ren, D. (2019, January 7\u201312). Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.neucom.2022.07.042","article-title":"Focal and efficient IOU loss for accurate bounding box regression","volume":"506","author":"Zhang","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_17","first-page":"1","article-title":"YOLOv3 Network Based on Improved Loss Function","volume":"28","author":"Shuo","year":"2019","journal-title":"Comput. Syst. Appl."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1124","DOI":"10.1049\/ipr2.12392","article-title":"A high-performance insulators location scheme based on YOLOv4 deep learning network with GDIoU loss function","volume":"16","author":"Ma","year":"2022","journal-title":"IET Image Process."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"012063","DOI":"10.1088\/1742-6596\/2260\/1\/012063","article-title":"Aircraft Detection in Remote Sensing Imagery Based on Improved YOLOv4","volume":"2260","author":"Liu","year":"2022","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"4746516","DOI":"10.1155\/2021\/4746516","article-title":"DWCA-YOLOv5: An Improve Single Shot Detector for Safety Helmet Detection","volume":"2021","author":"Jin","year":"2021","journal-title":"J. Sens."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zhu, L., Xie, Z., Luo, J., Qi, Y., Liu, L., and Tao, W. (2021). Dynamic Object Detection Algorithm Based on Lightweight Shared Feature Pyramid. Remote Sensing, 13.","DOI":"10.3390\/rs13224610"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Dai, X., Chen, Y., Xiao, B., Chen, D., Liu, M., Yuan, L., and Zhang, L. (2021, January 20\u201325). Dynamic Head: Unifying Object Detection Heads with Attentions. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00729"},{"key":"ref_23","unstructured":"Lin, S., Li, Y., Jiang, Z., Li, Z., Sun, H., Sun, J., and Zheng, N. (2020). Fine-Grained Dynamic Head for Object Detection. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Goindani, A., and Shrivastava, M. (2021). A Dynamic Head Importance Computation Mechanism for Neural Machine Translation. arXiv.","DOI":"10.26615\/978-954-452-072-4_052"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"El-Hag, A., Khalayli, L., and Sagban, H.A. (2013, January 2\u20135). Automatic inspection of outdoor insulators using image processing and intelligent techniques. Proceedings of the 2013 IEEE Electrical Insulation Conference (EIC), Ottawa, ON, Canada.","DOI":"10.1109\/EIC.2013.6554234"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/19\/8080\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:58:08Z","timestamp":1760129888000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/19\/8080"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,26]]},"references-count":25,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2023,10]]}},"alternative-id":["s23198080"],"URL":"https:\/\/doi.org\/10.3390\/s23198080","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,26]]}}}