{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T13:28:14Z","timestamp":1767619694134,"version":"3.48.0"},"reference-count":54,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T00:00:00Z","timestamp":1767312000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"State Grid Corporation of China Headquarters Technology Project","award":["5700-202416334A-2-1-ZX"],"award-info":[{"award-number":["5700-202416334A-2-1-ZX"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>As power systems expand and grow smarter, the safe and steady operation of substation equipment has become a prerequisite for grid reliability. In cluttered substation scenes, however, existing deep learning detectors still struggle with small targets, multi-scale feature fusion, and precise localization. To overcome these limitations, we introduce PBZGNet, a defect-detection network that couples a gradual parallel-branch backbone, a zoom-fusion neck, and a global channel-recalibration module. First, BiCoreNet is embedded in the feature extractor: dual-core parallel paths, reversible residual links, and channel recalibration cooperate to mine fault-sensitive cues. Second, cross-scale ZFusion and Concat-CBFuse are dynamically merged so that no scale loses information; a hierarchical composite feature pyramid is then formed, strengthening the representation of both complex objects and tiny flaws. Third, an attention-guided decoupled detection head (ADHead) refines responses to obscured and minute defect patterns. Finally, within the Generalized Focal Loss framework, a quality rating scheme suppresses background interference while distribution regression sharpens the localization of small targets. Across all scales, PBZGNet clearly outperforms YOLOv11. Its lightweight variant, PBZGNet-n, attains 83.9% mAP@50 with only 2.91 M parameters and 7.7 GFLOPs\u20149.3% above YOLOv11-n. The full PBZGNet surpasses the current best substation model, YOLO-SD, by 7.3% mAP@50, setting a new state of the art (SOTA).<\/jats:p>","DOI":"10.3390\/s26010300","type":"journal-article","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T11:11:46Z","timestamp":1767352306000},"page":"300","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PBZGNet: A Novel Defect Detection Network for Substation Equipment Based on Gradual Parallel Branch Architecture"],"prefix":"10.3390","volume":"26","author":[{"given":"Mintao","family":"Hu","sequence":"first","affiliation":[{"name":"College of Computer and Information Engineering (College of Artificial Intelligence), Nanjing Tech University, Nanjing 211816, China"},{"name":"Department of Automation, North China Electric Power University, Baoding 071003, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Department of Automation, North China Electric Power University, Baoding 071003, China"},{"name":"Hangzhou International Innovation Institute, Beihang University, Hangzhou 311115, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0069-3384","authenticated-orcid":false,"given":"Jiahao","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Automation, North China Electric Power University, Baoding 071003, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaoyi","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Automation, North China Electric Power University, Baoding 071003, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Desheng","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Automation, North China Electric Power University, Baoding 071003, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dawei","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Automation, North China Electric Power University, Baoding 071003, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2997-5840","authenticated-orcid":false,"given":"Yongjie","family":"Zhai","sequence":"additional","affiliation":[{"name":"Department of Automation, North China Electric Power University, Baoding 071003, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1109\/MPE.2023.3288579","article-title":"Next-Generation Power Substation communication networks: IEC 61850 meets programmable networks","volume":"21","author":"Botero","year":"2023","journal-title":"IEEE Power Energy Mag."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1016\/j.aej.2024.06.092","article-title":"Power system resilience and strategies for a sustainable infrastructure: A review","volume":"105","author":"Mohanty","year":"2024","journal-title":"Alex. Eng. J."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"27750","DOI":"10.1109\/ACCESS.2022.3157750","article-title":"Risk assessment of main electrical connection in substation with regional grid safety constraints","volume":"10","author":"Yang","year":"2022","journal-title":"IEEE Access"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2456","DOI":"10.1109\/COMST.2023.3305468","article-title":"Smart Substation Communications and Cybersecurity: A Comprehensive survey","volume":"25","author":"Gaspar","year":"2023","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"090801","DOI":"10.1115\/1.4065503","article-title":"Advancements and Challenges in Integrating Renewable Energy Sources into distribution grid Systems: A Comprehensive review","volume":"146","author":"Singh","year":"2024","journal-title":"J. Energy Resour. Technol."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Lu, W.-M., and Le, T.-T. (2025). From Technology to Strategy: The Evolving Role of Smart Grids and Microgrids in Sustainable Energy Management. Energies, 18.","DOI":"10.3390\/en18174609"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1109\/MPE.2022.3153784","article-title":"Grid innovations and digital transformation: Grid innovations and digital transformation of power substations are accelerating the energy transition for global utilities","volume":"20","author":"Kanabar","year":"2022","journal-title":"IEEE Power Energy Mag."},{"key":"ref_8","first-page":"2021344","article-title":"Image Recognition Technology with Its Application in Defect Detection and Diagnosis Analysis of Substation Equipment","volume":"2021","author":"Luo","year":"2021","journal-title":"Sci. Program."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1878","DOI":"10.1093\/ijlct\/ctae136","article-title":"Real-time performance evaluation and optimization of electrical substation equipment inspection algorithm based on distributed computing","volume":"19","author":"Zhang","year":"2024","journal-title":"Int. J. Low-Carbon Technol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"893","DOI":"10.1109\/94.469984","article-title":"Partial discharge diagnostics for gas insulated substations","volume":"2","author":"Pearson","year":"1995","journal-title":"IEEE Trans. Dielectr. Electr. Insul."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Chen, Y., Ding, Y., Zhao, F., Zhang, E., Wu, Z., and Shao, L. (2021). Surface defect detection methods for industrial products: A review. Appl. Sci., 11.","DOI":"10.3390\/app11167657"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"100294","DOI":"10.1016\/j.egyai.2023.100294","article-title":"Substation rotational object detection based on multi-scale feature fusion and refinement","volume":"14","author":"Li","year":"2023","journal-title":"Energy AI"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Chen, W., Liu, Y., Gao, Y., Hu, J., Liao, Z., and Zhao, J. (2024). Intelligent substation noise monitoring system: Design, implementation and evaluation. Energies, 17.","DOI":"10.3390\/en17133083"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, Y., Zhang, N., Zhang, Y., Zhao, Z., Xu, D., Ben, G., and Gao, Y. (2022). Deep learning-based object detection techniques for remote sensing images: A survey. Remote Sens., 14.","DOI":"10.3390\/rs14102385"},{"key":"ref_15","unstructured":"Rane, N. (2025, December 09). YOLO and Faster R-CNN Object Detection for Smart Industry 4.0 And Industry 5.0: Applications, Challenges, and Opportunities. Available online: https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=4624206."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1007\/s11554-023-01360-1","article-title":"Yolo-inspection: Defect detection method for power transmission lines based on enhanced YOLOv5s","volume":"20","author":"Lu","year":"2023","journal-title":"J. Real-Time Image Process."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Wang, T., Guo, J., Zhang, B., Yang, G., and Li, D. (2025). Deploying AI on Edge: Advancement and Challenges in Edge Intelligence. Mathematics, 13.","DOI":"10.3390\/math13111878"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"111088","DOI":"10.1016\/j.ijepes.2025.111088","article-title":"Optimizing power system edge computing with a high-performance and light-weight YOLO-based substation equipment defect detection network","volume":"172","author":"Wang","year":"2025","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1995","DOI":"10.1007\/s10845-021-01878-w","article-title":"Automated surface defect detection framework using machine vision and convolutional neural networks","volume":"34","author":"Singh","year":"2023","journal-title":"J. Intell. Manuf."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1007\/s00170-021-06592-8","article-title":"Recent advances in surface defect inspection of industrial products using deep learning techniques","volume":"113","author":"Zheng","year":"2021","journal-title":"Int. J. Adv. Manuf. Technol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2973","DOI":"10.1109\/TPWRD.2024.3450185","article-title":"SONet: A small object detection network for power line inspection based on YOLOv8","volume":"39","author":"Shi","year":"2024","journal-title":"IEEE Trans. Power Deliv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Gao, X., Du, J., Liu, X., Jia, D., and Wang, J. (2025). Object Detection Based on Improved YOLOv10 for Electrical Equipment Image Classification. Processes, 13.","DOI":"10.3390\/pr13020529"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Chen, Y., Du, Z., Li, A., Li, H., and Zhang, W. (2024, January 21\u201323). Substation Equipment Defect Detection Based on Improved YOLOv9. Proceedings of the 2024 IEEE 4th International Conference on Software Engineering and Artificial Intelligence (SEAI), Xiamen, China.","DOI":"10.1109\/SEAI62072.2024.10674545"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Meng, D., Xu, X., Jiang, Z., and Xu, L. (2024). Real-time detection of insulator defects with channel pruning and channel distillation. Appl. Sci., 14.","DOI":"10.3390\/app14198587"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"5006512","DOI":"10.1109\/TIM.2023.3241994","article-title":"An ultrasmall bolt defect detection method for transmission line inspection","volume":"72","author":"Luo","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Li, Y., Xiang, Y., Guo, H., Liu, P., and Liu, C. (2022). Swin transformer combined with convolution neural network for surface defect detection. Machines, 10.","DOI":"10.3390\/machines10111083"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"103689","DOI":"10.1016\/j.compind.2022.103689","article-title":"Cas-VSwin transformer: A variant swin transformer for surface-defect detection","volume":"140","author":"Gao","year":"2022","journal-title":"Comput. Ind."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.-P., Song, K., Liang, D., Lu, T., Luo, P., and Shao, L. (2021, January 10\u201317). Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"110069","DOI":"10.1016\/j.ijepes.2024.110069","article-title":"Development of a real-time fault detection method for electric power system via transformer-based deep learning model","volume":"159","author":"Yoon","year":"2024","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"32804","DOI":"10.1109\/JIOT.2024.3409823","article-title":"Defect detection using shuffle Net-CA-SSD lightweight network for turbine blades in IoT","volume":"11","author":"Zhao","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"012025","DOI":"10.1088\/1742-6596\/1754\/1\/012025","article-title":"A defect detection method based on faster RCNN for power equipment","volume":"1754","author":"Cheng","year":"2021","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"111594","DOI":"10.1016\/j.measurement.2022.111594","article-title":"Attention mechanism in intelligent fault diagnosis of machinery: A review of technique and application","volume":"199","author":"Lv","year":"2022","journal-title":"Measurement"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Tang, J., Wang, J., Wang, H., Wei, J., Wei, Y., and Qin, M. (2022, January 25\u201328). Insulator defect detection based on improved faster R-CNN. Proceedings of the 2022 4th Asia Energy and Electrical Engineering Symposium (AEEES), Online.","DOI":"10.1109\/AEEES54426.2022.9759683"},{"key":"ref_34","first-page":"5039513","article-title":"A Two-Stage Insulator Defect Detection Network with Sequence Transduction","volume":"74","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Zhang, J., Cosma, G., and Watkins, J. (2021). Image enhanced mask R-CNN: A deep learning pipeline with new evaluation measures for wind turbine blade defect detection and classification. J. Imaging, 7.","DOI":"10.3390\/jimaging7030046"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Zhang, Q.L., and Yang, Y.B. (2021, January 6\u201311). Sa-net: Shuffle attention for deep convolutional neural networks. Proceedings of the ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, ON, Canada.","DOI":"10.1109\/ICASSP39728.2021.9414568"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"8672","DOI":"10.1109\/JSEN.2022.3159293","article-title":"A channel attention-based method for micro-motor armature surface defect detection","volume":"22","author":"Li","year":"2022","journal-title":"IEEE Sens. J."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., and Jia, J. (2018, January 18\u201322). Path aggregation network for instance segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Zhu, L., Deng, Z., Hu, X., Fu, C.W., Xu, X., Qin, J., and Heng, P.A. (2018, January 8\u201314). Bidirectional feature pyramid network with recurrent attention residual modules for shadow detection. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01231-1_8"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., and Xu, C. (2020, January 14\u201319). Ghostnet: More features from cheap operations. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"ref_41","unstructured":"Howard, A., Sandler, M., Chen, B., Wang, W., Chen, L.-C., Tan, M., Chu, G., Vasudevan, V., Zhu, Y., and Pang, R. (November, January 27). Searching for mobilenetv3. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_42","unstructured":"(2025, December 09). Dataset of Substation Equipment Defects. Available online: https:\/\/www.scidb.cn\/en\/detail?dataSetId=93f3885c1e8d417fab4cb9a724cf1ccf."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Sohan, M., Sai Ram, T., and Rami Reddy, C.V. (2024, January 18\u201320). A review on yolov8 and its advancements. Proceedings of the International Conference on Data Intelligence and Cognitive Informatics, Tirunelveli, India.","DOI":"10.1007\/978-981-99-7962-2_39"},{"key":"ref_44","unstructured":"Wang, C.Y., Yeh, I.H., and Mark Liao, H.Y. (October, January 29). Yolov9: Learning what you want to learn using programmable gradient information. Proceedings of the European Conference on Computer Vision, Milano, Italy."},{"key":"ref_45","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_46","unstructured":"Khanam, R., and Hussain, M. (2024). Yolov11: An overview of the key architectural enhancements. arXiv."},{"key":"ref_47","unstructured":"Tian, Y., Ye, Q., and Doermann, D. (2025). Yolov12: Attention-centric real-time object detectors. arXiv."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., and Chen, J. (2024, January 17\u201324). Detrs beat yolos on real-time object detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"ref_49","unstructured":"Khanam, R., and Hussain, M. (2024). What is YOLOv5: A deep look into the internal features of the popular object detector. arXiv."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"105042","DOI":"10.1109\/ACCESS.2024.3436000","article-title":"A defect detection method for substation equipment based on image data generation and deep learning","volume":"12","author":"Zhang","year":"2024","journal-title":"IEEE Access"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Sun, Y., Sun, X., Lin, Y., Yang, Y., Li, Z., Du, L., and Shi, C. (2025). Substation Equipment Defect Detection Based on Improved YOLOv8. Sensors, 25.","DOI":"10.3390\/s25113410"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Ji, Y., Zhang, D., He, Y., Zhao, J., Duan, X., and Zhang, T. (2025). Improved YOLO11 Algorithm for Insulator Defect Detection in Power Distribution Lines. Electronics, 14.","DOI":"10.3390\/electronics14061201"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"33702","DOI":"10.1038\/s41598-025-18964-1","article-title":"Effectiveness of traditional augmentation methods for rebar counting using UAV imagery with Faster R-CNN and YOLOv10-based transformer architectures","volume":"15","author":"Wang","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"04025186","DOI":"10.1061\/JCEMD4.COENG-16760","article-title":"Safety Helmet Monitoring on Construction Sites Using YOLOv10 and Advanced Transformer Architectures with Surveillance and Body-Worn Cameras","volume":"151","author":"Wang","year":"2025","journal-title":"J. Constr. Eng. Manag."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/1\/300\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T10:55:29Z","timestamp":1767610529000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/1\/300"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,2]]},"references-count":54,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["s26010300"],"URL":"https:\/\/doi.org\/10.3390\/s26010300","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2026,1,2]]}}}