{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T03:36:51Z","timestamp":1775187411354,"version":"3.50.1"},"reference-count":53,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T00:00:00Z","timestamp":1762473600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Infrared detection of defects in power facilities is critical to the safe operation and fault early warning of power grids. However, conventional inspection methods have distinct limitations, such as delayed response and insufficient condition visualization. To address the pain points and technical challenges of the aforementioned inspection modes, this study proposes a deep learning network model based on multi-angle perception and Transattn feature fusion. This model can effectively improve the defect recognition ability of power facility components in complex scenarios. Firstly, a modified MAPC module is introduced, which enhances the extraction of edge contours of power facility components and detailed infrared thermal textures. Secondly, an innovative Transattn module is proposed to dynamically focus on the core component regions of power facilities. Finally, a feature fusion strategy is used to efficiently integrate the feature maps from each module, outputting component localization results and defect category information. Experimental results based on the infrared detection dataset of power facility components show that compared with classical detection models such as YOLOv10 and DDN, the proposed CMTA model achieves the best performance in all indicators: the highest mAP50 reaches 85.01%, the frame rate (FPS) is 252 frames per second, the parameter count is only 2.8 M, and it significantly shortens the fault response time of operation and maintenance personnel.<\/jats:p>","DOI":"10.3390\/sym17111909","type":"journal-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T14:55:15Z","timestamp":1762527315000},"page":"1909","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["CMTA: Infrared Detection Model for Power Facility Components via Multi-Angle Perception and Transattn Fusion"],"prefix":"10.3390","volume":"17","author":[{"given":"Zhongyuan","family":"Fan","sequence":"first","affiliation":[{"name":"School of Art & Design, Faculty of Arts, Design & Architecture, The University of New South Wales (UNSW), Sydney, NSW 2052, Australia"}]},{"given":"Lufeng","family":"Yuan","sequence":"additional","affiliation":[{"name":"Beijing China-Power Information Technology Co., Ltd., Beijing 100192, China"}]},{"given":"Biyao","family":"Wen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, China"}]},{"given":"Qiang","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao 266590, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8074-3431","authenticated-orcid":false,"given":"Gengkun","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Majchrzak, D., Michalski, K., and Reginia-Zacharski, J. (2021). Readiness of the Polish Crisis Management System to Respond to Long-Term, Large-Scale Power Shortages and Failures (Blackouts). Energies, 14.","DOI":"10.3390\/en14248286"},{"key":"ref_2","first-page":"105","article-title":"Risk Assessment and Mitigation Strategy of Large-Scale Solar Photovoltaic Systems in Pakistan","volume":"14","author":"Inayat","year":"2023","journal-title":"Int. J. Ind. Eng. Manag."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1038\/s44287-024-00112-y","article-title":"High-Temperature Superconductors and Their Large-Scale Applications","volume":"1","author":"Coombs","year":"2024","journal-title":"Nat. Rev. Electr. Eng."},{"key":"ref_4","first-page":"V003T03A017","article-title":"Analysis of Hidden Fault in Digital Instrumentation and Control System of Nuclear Power Plant Based on Environmental Model","volume":"Volume 86373","author":"Guo","year":"2022","journal-title":"International Conference on Nuclear Engineering"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"5018021","DOI":"10.1109\/TIM.2022.3196436","article-title":"Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey","volume":"71","author":"Tao","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_6","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_7","doi-asserted-by":"crossref","first-page":"2504210","DOI":"10.1109\/TIM.2023.3238059","article-title":"CNN-Based Transformer Model for Fault Detection in Power System Networks","volume":"72","author":"Thomas","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"020062","DOI":"10.1063\/5.0278261","article-title":"Optimizing Disease Detection: Advancing Gingivitis and Calculus Accuracy with RESNET V2 50 over RESNET 101","volume":"Volume 3300","author":"Bhargav","year":"2025","journal-title":"AIP Conference Proceedings"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1007","DOI":"10.1109\/TPWRS.2021.3100898","article-title":"Powernet: Multi-Agent Deep Reinforcement Learning for Scalable Powergrid Control","volume":"37","author":"Chen","year":"2021","journal-title":"IEEE Trans. Power Syst."},{"key":"ref_10","first-page":"2567","article-title":"Multi-Scale CNN with Adaptive Receptive Field for Infrared Defect Detection of Power Equipment","volume":"38","author":"Li","year":"2023","journal-title":"IEEE Trans. Power Deliv."},{"key":"ref_11","first-page":"109876","article-title":"Temporal CNN for Dynamic Thermal Defect Monitoring of Power Transformers","volume":"228","author":"Zhao","year":"2024","journal-title":"Electr. Power Syst. Res."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Li, S., Tan, M., Pang, R., Li, A., Cheng, L., Le, Q.V., and Jouppi, N.P. (2021, January 19\u201325). Searching for Fast Model Families on Datacenter Accelerators. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00799"},{"key":"ref_13","first-page":"121987","article-title":"Lightweight CNN Based on Channel Pruning for Real-Time Infrared Inspection of Power Lines","volume":"351","author":"Zhang","year":"2024","journal-title":"Appl. Energy"},{"key":"ref_14","unstructured":"Wang, Q., Wu, B., and Zhu, P. (2022, January 18\u201324). ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA."},{"key":"ref_15","unstructured":"Guo, J., Liu, J., and Mu, T. (2022, January 18\u201324). Coordinate Attention for Efficient Mobile Network Design. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"19471","DOI":"10.1109\/TITS.2022.3170551","article-title":"Intention-Aware Vehicle Trajectory Prediction Based on Spatial-Temporal Dynamic Attention Network for Internet of Vehicles","volume":"23","author":"Chen","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Wang, Y., Li, Y., Wang, G., and Liu, X. (2024, January 16\u201322). Multi-Scale Attention Network for Single Image Super-Resolution. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPRW63382.2024.00602"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"31831","DOI":"10.1007\/s11042-022-12489-9","article-title":"Spatially Adaptive Multi-Scale Contextual Attention for Image Inpainting","volume":"81","author":"Wang","year":"2022","journal-title":"Multimed. Tools Appl."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Liu, J., Wu, H., Zhang, L., and Zhao, Y. (2022, January 21\u201323). Spatial-Temporal Transformers for EEG Emotion Recognition. Proceedings of the 6th International Conference on Advances in Artificial Intelligence, Birmingham, UK.","DOI":"10.1145\/3571560.3571577"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2024.3493878","article-title":"Cross-Modal Attention Fusion for Infrared and Visible Image Detection","volume":"73","author":"Li","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_21","first-page":"11978","article-title":"Swin Transformer V2: Scaling Up Capacity and Resolution","volume":"45","author":"Liu","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_22","first-page":"21299","article-title":"End-to-End Object Detection with Transformers","volume":"35","author":"Zhou","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_23","unstructured":"Qiao, S., Sun, P., and Wei, H. (2023, January 2\u20136). MobileViT: Light-Weight, General-Purpose, and Mobile-Friendly Vision Transformer. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"042010","DOI":"10.1088\/2516-1083\/ac890b","article-title":"Infrared Imaging of Photovoltaic Modules: A Review of the State of the Art and Future Challenges Facing Gigawatt Photovoltaic Power Stations","volume":"4","author":"Buerhop","year":"2022","journal-title":"Prog. Energy"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zhang, K., Zhang, N., Shi, C., Lu, Q., Zheng, X., Cao, Y., and Yang, J. (2025). YOLOv9-GDV: A Power Pylon Detection Model for Remote Sensing Images. Remote Sens., 17.","DOI":"10.3390\/rs17132229"},{"key":"ref_26","unstructured":"Yaseen, M. (2024). What is YOLOv9: An In-Depth Exploration of the Internal Features of the Next-Generation Object Detector. arXiv."},{"key":"ref_27","first-page":"108","article-title":"Statistical Methods for Comparing Object Detection Models: A Systematic Review","volume":"168","author":"Johnson","year":"2023","journal-title":"Pattern Recognit. Lett."},{"key":"ref_28","first-page":"876","article-title":"Bootstrap-Based Confidence Intervals for Object Detection Metrics in Power Equipment Inspection","volume":"39","author":"Zhao","year":"2024","journal-title":"IEEE Trans. Power Deliv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"656","DOI":"10.37188\/CJLCD.2022-0282","article-title":"Object Detection Method Based on CIoU Improved Bounding Box Loss Function","volume":"38","author":"Liu","year":"2023","journal-title":"Chin. J. Liq. Cryst. Disp."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"107563","DOI":"10.1016\/j.ijepes.2021.107563","article-title":"Hybrid CNN-LSTM Approaches for Identification of Type and Locations of Transmission Line Faults","volume":"135","author":"Moradzadeh","year":"2022","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"141258","DOI":"10.1109\/ACCESS.2021.3119562","article-title":"Scale-Sensitive IOU Loss: An Improved Regression Loss Function in Remote Sensing Object Detection","volume":"9","author":"Du","year":"2021","journal-title":"IEEE Access"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Cheng, R., He, X., Zheng, Z., and Wang, Z. (2021). Multi-Scale Safety Helmet Detection Based on SAS-YOLOv3-Tiny. Appl. Sci., 11.","DOI":"10.3390\/app11083652"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Geng, X., Su, Y., Cao, X., Li, H., and Liu, L. (2024). YOLOFM: An Improved Fire and Smoke Object Detection Algorithm Based on YOLOv5n. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-55232-0"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Ma, L., Zhao, L., Wang, Z., Zhang, J., and Chen, G. (2023). Detection and Counting of Small Target Apples Under Complicated Environments by Using Improved YOLOv7-Tiny. Agronomy, 13.","DOI":"10.3390\/agronomy13051419"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Ma, N., Wu, Y., Bo, Y., and Yan, H. (2024). Chili Pepper Object Detection Method Based on Improved YOLOv8n. Plants, 13.","DOI":"10.3390\/plants13172402"},{"key":"ref_36","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_37","doi-asserted-by":"crossref","unstructured":"Zhou, K., and Jiang, S. (2025). Forest Fire Detection Algorithm Based on Improved YOLOv11n. Sensors, 25.","DOI":"10.3390\/s25102989"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1007\/s11760-024-03679-z","article-title":"DF-YOLOv7: Steel Surface Defect Detection Based on Focal Module and Deformable Convolution","volume":"19","author":"Zhang","year":"2025","journal-title":"Signal Image Video Process."},{"key":"ref_39","first-page":"103516","article-title":"Automatic Identification of Active Landslides Over Wide Areas from Time-Series InSAR Measurements Using Faster RCNN","volume":"124","author":"Cai","year":"2023","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Wang, H., and Ao, N. (2023). Underwater Object Detection Method Based on Improved Faster RCNN. Appl. Sci., 13.","DOI":"10.3390\/app13042746"},{"key":"ref_41","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_42","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1080\/0952813X.2021.1907793","article-title":"Human Detection Based on Deep Learning YOLO-v2 for Real-Time UAV Applications","volume":"34","author":"Boudjit","year":"2022","journal-title":"J. Exp. Theor. Artif. Intell."},{"key":"ref_43","first-page":"972","article-title":"Surface Defect Detection with Limited Data Based on SSD Detector and Siamese Networks","volume":"158","author":"Novgorodcev","year":"2024","journal-title":"J. Sci. Tech. Inf. Technol. Mech. Opt."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Gao, X., Chi, Q., Liu, Y., and Zhang, S. (2025). Radar Intelligence Data Recognition Technology Based on Improved R-FCN Fusion Algorithm. J. Comput. Methods Sci. Eng., 14727978251391295.","DOI":"10.1177\/14727978251391295"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1007\/s42488-024-00128-x","article-title":"Granulated Mask RCNN and Eye Detection Index (EDI) for Detection and Localization of Eye of Tropical Cyclone from Satellite Imagery","volume":"6","author":"Pal","year":"2024","journal-title":"J. Data Inf. Manag."},{"key":"ref_46","first-page":"89","article-title":"Speed-Up Single Shot Detector on GPU","volume":"Volume 1074","author":"Wang","year":"2022","journal-title":"International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel\/Distributed Computing"},{"key":"ref_47","first-page":"1","article-title":"Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutions","volume":"58","author":"Hamidouche","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"4504","DOI":"10.1109\/TNNLS.2024.3376563","article-title":"DPNet: Dual-Path Network for Real-Time Object Detection with Lightweight Attention","volume":"36","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"119102","DOI":"10.1007\/s11432-021-3504-4","article-title":"TinyDet: Accurately Detecting Small Objects Within 1 GFLOPs","volume":"66","author":"Chen","year":"2023","journal-title":"Sci. China Inf. Sci."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Buitr\u00f3n Tandalia, I.A. (2023). An\u00e1lisis de Rendimiento de You Only Look Once, Retinanet y Single Shot Detector Aplicado a la Detecci\u00f3n y Conteo Vehicular. [Master\u2019s Thesis, EPN].","DOI":"10.1007\/978-3-031-45438-7_17"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"346","DOI":"10.12968\/denn.2023.19.7.346","article-title":"Can Extended Duties Dental Nurses (EDDNs) as Oral Health Educators (OHEs) be Beneficial for the Practice and Morale?","volume":"19","author":"Dawson","year":"2023","journal-title":"Dent. Nurs."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"108490","DOI":"10.52202\/079017-3444","article-title":"DDN: Dual-Domain Dynamic Normalization for Non-Stationary Time Series Forecasting","volume":"37","author":"Dai","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"64176","DOI":"10.52202\/079017-2047","article-title":"MO-DDN: A Coarse-to-Fine Attribute-Based Exploration Agent for Multi-Object Demand-Driven Navigation","volume":"37","author":"Cai","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/11\/1909\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T05:19:49Z","timestamp":1762838389000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/11\/1909"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,7]]},"references-count":53,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["sym17111909"],"URL":"https:\/\/doi.org\/10.3390\/sym17111909","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,7]]}}}