{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T23:20:42Z","timestamp":1777504842960,"version":"3.51.4"},"reference-count":47,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T00:00:00Z","timestamp":1751500800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Shandong Province Science and Technology Small and Medium-sized Enterprises Innovation Ability Improvement Project","award":["2024TSGC0285"],"award-info":[{"award-number":["2024TSGC0285"]}]},{"name":"Shandong Province Science and Technology Small and Medium-sized Enterprises Innovation Ability Improvement Project","award":["2023GX027"],"award-info":[{"award-number":["2023GX027"]}]},{"name":"Taian Science and Technology Innovation Development Project","award":["2024TSGC0285"],"award-info":[{"award-number":["2024TSGC0285"]}]},{"name":"Taian Science and Technology Innovation Development Project","award":["2023GX027"],"award-info":[{"award-number":["2023GX027"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>The growing popularity of solar panels is crucial for global decarbonization, but harsh environmental conditions can lead to defects such as cracks, fingerprints, and short circuits. Existing methods face the challenge of detecting multi-scale defects while maintaining real-time performance. This paper proposes a solar panel defect detection model, DCE-YOLO, based on YOLOv8. The model incorporates a C2f-DWR-DRB module for multi-scale feature extraction, where the parallel DRB branch models spatial symmetry through symmetric-rate dilated convolutions, improving robustness and consistency. The COT attention module strengthens long-range dependencies and fuses local and global contexts to achieve symmetric feature representation. The lightweight and efficient detection head improves detection speed and accuracy. The CIoU loss function is replaced with WIoU, and a non-monotonic dynamic focusing mechanism is used to mitigate the effect of low-quality samples. Experimental results show that compared with the YOLOv8 benchmark, DCE-YOLO achieves a 2.1% performance improvement on mAP@50 and a 4.9% performance improvement on mAP@50-95. Compared with recent methods, DCE-YOLO exhibits broader defect coverage, stronger robustness, and a better performance-efficiency balance, making it highly suitable for edge deployment. The synergistic interaction between the C2f-DWR-DRB module and COT attention enhances the detection of symmetric and multi-scale defects under real-world conditions.<\/jats:p>","DOI":"10.3390\/sym17071052","type":"journal-article","created":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T06:01:33Z","timestamp":1751522493000},"page":"1052","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["An Enhanced YOLOv8 Model with Symmetry-Aware Feature Extraction for High-Accuracy Solar Panel Defect Detection"],"prefix":"10.3390","volume":"17","author":[{"given":"Xiaoxia","family":"Lin","sequence":"first","affiliation":[{"name":"College of Intelligent Equipment, Shandong University of Science and Technology, Taian 271001, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7331-7987","authenticated-orcid":false,"given":"Xinyue","family":"Xiao","sequence":"additional","affiliation":[{"name":"College of Intelligent Equipment, Shandong University of Science and Technology, Taian 271001, China"}]},{"given":"Lin","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Intelligent Equipment, Shandong University of Science and Technology, Taian 271001, China"}]},{"given":"Xiaodong","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Intelligent Equipment, Shandong University of Science and Technology, Taian 271001, China"}]},{"given":"Chunwei","family":"Leng","sequence":"additional","affiliation":[{"name":"Hanqing Data Consulting Co., Ltd., Zibo 255000, China"}]},{"given":"Yan","family":"Li","sequence":"additional","affiliation":[{"name":"Hanqing Data Consulting Co., Ltd., Zibo 255000, China"}]},{"given":"Zhenyu","family":"Niu","sequence":"additional","affiliation":[{"name":"Hanqing Data Consulting Co., Ltd., Zibo 255000, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3557-3236","authenticated-orcid":false,"given":"Yingzhou","family":"Meng","sequence":"additional","affiliation":[{"name":"College of Intelligent Equipment, Shandong University of Science and Technology, Taian 271001, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1361-279X","authenticated-orcid":false,"given":"Weihao","family":"Gong","sequence":"additional","affiliation":[{"name":"College of Intelligent Equipment, Shandong University of Science and Technology, Taian 271001, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"130112","DOI":"10.1016\/j.energy.2023.130112","article-title":"Exploring the effects of mineral depletion on renewable energy technologies net energy returns","volume":"290","author":"Aramendia","year":"2024","journal-title":"Energy"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Parthiban, R., and Ponnambalam, P. (2022). An Enhancement of the Solar Panel Efficiency: A Comprehensive Review. Front. Energy Res., 10.","DOI":"10.3389\/fenrg.2022.937155"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1016\/S0927-0248(01)00192-1","article-title":"Defect recognition and impurity detection techniques in crystalline silicon for solar cells","volume":"72","author":"Istratov","year":"2002","journal-title":"Sol. Energy Mater. Sol. Cells"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1109\/TII.2012.2209663","article-title":"Defect Detection in Solar Modules Using ICA Basis Images","volume":"9","author":"Tsai","year":"2013","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1684","DOI":"10.1109\/TII.2021.3088721","article-title":"Investigating the Impact of Cracks on Solar Cells Performance: Analysis Based on Nonuniform and Uniform Crack Distributions","volume":"18","author":"Dhimish","year":"2022","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_6","first-page":"73","article-title":"Recent Improvements of the Optical and Thermal Performance of the Parabolic Trough Solar Collector Systems","volume":"20","author":"Seres","year":"2022","journal-title":"Facta Univ. Ser. Mech. Eng."},{"key":"ref_7","first-page":"1","article-title":"Novel GAN-Based Image Completion: Addressing Structure and Texture Consistency in Missing Regions","volume":"1","author":"Edalatpanah","year":"2024","journal-title":"Comput. Eng. Technol. Innov."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"6200","DOI":"10.1039\/C6TA10377D","article-title":"Influence of defects and dopants on the photovoltaic performance of Bi2S3: First-principles insights","volume":"5","author":"Han","year":"2017","journal-title":"J. Mater. Chem. A"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1211","DOI":"10.1016\/j.renene.2021.06.086","article-title":"Defect detection and quantification in electroluminescence images of solar PV modules using U-net semantic segmentation","volume":"178","author":"Pratt","year":"2021","journal-title":"Renew. Energy"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"941","DOI":"10.1016\/j.renene.2022.04.046","article-title":"A multi-stage model based on YOLOv3 for defect detection in PV panels based on IR and visible imaging by unmanned aerial vehicle","volume":"193","author":"Betti","year":"2022","journal-title":"Renew. Energy"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1091","DOI":"10.1109\/JPHOTOV.2019.2913342","article-title":"Analysis of Photovoltaic Performance Loss Rates of Six Module Types in Five Geographical Locations","volume":"9","author":"Ingenhoven","year":"2019","journal-title":"IEEE J. Photovolt."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"e18826","DOI":"10.1016\/j.heliyon.2023.e18826","article-title":"Solar panel defect detection design based on YOLO v5 algorithm","volume":"9","author":"Huang","year":"2023","journal-title":"Heliyon"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1010","DOI":"10.1016\/j.optlastec.2010.01.022","article-title":"Detection of physical defects in solar cells by hyperspectral imaging technology","volume":"42","author":"Li","year":"2010","journal-title":"Opt. Laser Technol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1177\/0142331212457583","article-title":"Automatic detection of micro-crack in solar wafers and cells: A review","volume":"35","author":"Israil","year":"2012","journal-title":"Trans. Inst. Meas. Control"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1016\/j.imavis.2009.08.001","article-title":"Micro-crack inspection in heterogeneously textured solar wafers using anisotropic diffusion","volume":"28","author":"Tsai","year":"2010","journal-title":"Image Vis. Comput."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"885","DOI":"10.1109\/TEC.2012.2217144","article-title":"Diagnosis of Output Power Lowering in a PV Array by Using the Kalman-Filter Algorithm","volume":"27","author":"Kang","year":"2012","journal-title":"IEEE Trans. Energy Convers."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e992","DOI":"10.7717\/peerj-cs.992","article-title":"Identifying defective solar cells in electroluminescence images using deep feature representations","volume":"8","author":"Ibrahim","year":"2022","journal-title":"PeerJ Comput. Sci."},{"key":"ref_18","first-page":"103713","article-title":"A comparative study on bayes classifier for detecting photovoltaic module visual faults using deep learning features","volume":"64","author":"Venkatesh","year":"2024","journal-title":"Sustain. Energy Technol. Assess"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"106375","DOI":"10.1016\/j.jobe.2023.106375","article-title":"A photovoltaic surface defect detection method for building based on deep learning","volume":"70","author":"Cao","year":"2023","journal-title":"J. Build. Eng."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"107866","DOI":"10.1016\/j.engappai.2024.107866","article-title":"Improved YOLOv8-GD deep learning model for defect detection in electroluminescence images of solar photovoltaic modules","volume":"131","author":"Cao","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"80804","DOI":"10.1109\/ACCESS.2022.3195901","article-title":"Solar Cell Surface Defect Detection Based on Improved YOLO v5","volume":"10","author":"Zhang","year":"2022","journal-title":"IEEE Access"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"75599","DOI":"10.1109\/ACCESS.2025.3564714","article-title":"SparkNet-A Solar Panel Fault Detection Deep Learning Model","volume":"13","author":"Rohith","year":"2025","journal-title":"Ieee Access"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Khang, N.P.H., Triet, N.M., Van Tuan, H., and Nhan, N.C. (2025). Applying RetinaNet Machine Learning Models for Hot-Spot Detection in Thermal Images of Photovoltaic Panel. IEEJ Trans. Electr. Electron. Eng., ahead of print.","DOI":"10.1002\/tee.70067"},{"key":"ref_24","first-page":"200509","article-title":"Efficient combination of deep learning and tree-based classification models for solar panel dust detection","volume":"26","author":"Bassil","year":"2025","journal-title":"Intell. Syst. Appl."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Karakan, A. (2025). Detection of Defective Solar Panel Cells in Electroluminescence Images with Deep Learning. Sustainability, 17.","DOI":"10.3390\/su17031141"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Li, L., Wang, Z., and Zhang, T. (2023). GBH-YOLOv5: Ghost Convolution with BottleneckCSP and Tiny Target Prediction Head Incorporating YOLOv5 for PV Panel Defect Detection. Electronics, 12.","DOI":"10.3390\/electronics12030561"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"107836","DOI":"10.1016\/j.engappai.2023.107836","article-title":"Identification of surface defects on solar PV panels and wind turbine blades using attention based deep learning model","volume":"131","author":"Dwivedi","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"101603","DOI":"10.1016\/j.aei.2022.101603","article-title":"Multi-component attention-based convolution network for color difference recognition with wavelet entropy strategy","volume":"52","author":"Zhuang","year":"2022","journal-title":"Adv. Eng. Inform."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"23744","DOI":"10.1109\/JSEN.2023.3300350","article-title":"An Enhancement Generative Adversarial Networks Based on Feature Moving for Solar Panel Defect Identification","volume":"23","author":"Jiang","year":"2023","journal-title":"IEEE Sens. J."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"117087","DOI":"10.1016\/j.eswa.2022.117087","article-title":"Convolution neural network based polycrystalline silicon photovoltaic cell linear defect diagnosis using electroluminescence images","volume":"202","author":"Tang","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"7335","DOI":"10.1109\/TII.2022.3211088","article-title":"Automatic Detection of Defective Solar Cells in Electroluminescence Images via Global Similarity and Concatenated Saliency Guided Network","volume":"19","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1007\/s11554-024-01415-x","article-title":"Deeplab-YOLO: A method for detecting hot-spot defects in infrared image PV panels by combining segmentation and detection","volume":"21","author":"Lei","year":"2024","journal-title":"J. Real-Time Image Process."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"5553","DOI":"10.1109\/JSTARS.2024.3369660","article-title":"Extracting Photovoltaic Panels From Heterogeneous Remote Sensing Images with Spatial and Spectral Differences","volume":"17","author":"Zhao","year":"2024","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zheng, P., Bahadir Kocer, B., and Kovac, M. (2024). Drone-Based Solar Cell Inspection with Autonomous Deep Learning. Infrastructure Robotics: Methodologies, Robotic Systems and Applications, John Wiley & Sons, Inc.","DOI":"10.1002\/9781394162871.ch16"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"112466","DOI":"10.1016\/j.measurement.2023.112466","article-title":"Solar panel inspection techniques and prospects","volume":"209","author":"Meribout","year":"2023","journal-title":"Measurement"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"116342","DOI":"10.1016\/j.measurement.2024.116342","article-title":"PCBSSD: Self-supervised symmetry-aware detector for PCB displacement and orientation inspection","volume":"243","author":"Li","year":"2025","journal-title":"Measurement"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"103888","DOI":"10.1016\/j.cad.2025.103888","article-title":"Face2Wear: An automatic and user-friendly facewear personalization framework with 3D symmetry-aware face registration using RGB-D selfies","volume":"185","author":"Zhang","year":"2025","journal-title":"Comput.-Aided Des."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Naeem, U., Chadda, K., Vahaji, S., Ahmad, J., Li, X., and Asadi, E. (2025). Aerial Imaging-Based Soiling Detection System for Solar Photovoltaic Panel Cleanliness Inspection. Sensors, 25.","DOI":"10.3390\/s25030738"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"053704","DOI":"10.1063\/5.0222316","article-title":"High-noise solar panel defect identification method based on the improved EfficientNet-V2","volume":"16","author":"Yang","year":"2024","journal-title":"J. Renew. Sustain. Energy"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2583","DOI":"10.1007\/s11760-022-02475-x","article-title":"Surface defect detection of solar cell based on similarity non-maximum suppression mechanism","volume":"17","author":"Wang","year":"2023","journal-title":"Signal Image Video Process."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"154292","DOI":"10.1109\/ACCESS.2021.3119631","article-title":"DPiT: Detecting Defects of Photovoltaic Solar Cells with Image Transformers","volume":"9","author":"Xie","year":"2021","journal-title":"IEEE Access"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2016). Feature Pyramid Networks for Object Detection. arXiv.","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., and Jia, J. (2018). Path Aggregation Network for Instance Segmentation. arXiv.","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref_45","unstructured":"Wei, H., Liu, X., Xu, S., Dai, Z., Dai, Y., and Xu, X. (2022). DWRSeg: Rethinking Efficient Acquisition of Multi-scale Contextual Information for Real-time Semantic Segmentation. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, Y., Ge, Y., Zhao, S., Song, L., Yue, X., and Shan, Y. (2023). UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition. arXiv.","DOI":"10.1109\/CVPR52733.2024.00527"},{"key":"ref_47","unstructured":"Tong, Z., Chen, Y., Xu, Z., and Yu, R. (2023). Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism. arXiv."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/7\/1052\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:03:43Z","timestamp":1760033023000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/7\/1052"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,3]]},"references-count":47,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["sym17071052"],"URL":"https:\/\/doi.org\/10.3390\/sym17071052","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,3]]}}}