
浏览全部资源
扫码关注微信
西安邮电大学 计算机学院, 陕西 西安 710121
邓万宇,男,博士,教授,2010年于西安交通大学获得博士学位,主要从事计算机视觉及图像处理方面的研究。E-mail: dengwanyu@126.com
彭鑫亮,男,硕士研究生,2024年于西安建筑科技大学获得学士学位,主要从事图像处理算法的研究。E-mail:1802368981@stu.xupt.edu.cn
收稿:2026-05-11,
修回:2026-06-24,
纸质出版:2026-08-05
移动端阅览
邓万宇, 彭鑫亮. 基于改进RT-DETR的光伏红外缺陷检测算法[J]. 液晶与显示, 2026,41(8):1175-1186.
DENG Wanyu, PENG Xinliang. Photovoltaic infrared defect detection algorithm based on improved RT-DETR[J]. Chinese Journal of Liquid Crystals and Displays, 2026, 41(8): 1175-1186.
邓万宇, 彭鑫亮. 基于改进RT-DETR的光伏红外缺陷检测算法[J]. 液晶与显示, 2026,41(8):1175-1186. DOI: 10.3724/CJLCD.2026-0079. CSTR: 32172.14.CJLCD.2026-0079.
DENG Wanyu, PENG Xinliang. Photovoltaic infrared defect detection algorithm based on improved RT-DETR[J]. Chinese Journal of Liquid Crystals and Displays, 2026, 41(8): 1175-1186. DOI: 10.3724/CJLCD.2026-0079. CSTR: 32172.14.CJLCD.2026-0079.
光伏板表面缺陷检测是保障光伏系统发电效率与运行安全的关键。针对无人机航拍红外图像中航拍小目标检测难、户外热背景干扰强及缺陷目标尺度跨度大等挑战,本研究提出一种结合多尺度特征与动态卷积的光伏红外缺陷检测模型。首先,在浅层路径采用空间到深度卷积(SPD-Conv)替代传统下采样,规避二极管异常、热斑等微小目标的细粒度特征与边缘信息丢失;其次,引入动态全维卷积(CSPOmniKernel)模块,通过多分支机制自适应调整感受野,增强低对比度缺陷特征并抑制复杂热背景干扰;最后,构建高效多尺度特征融合模块(MFM),借助跨层级信息交互与自适应聚合,提升模型对不同尺度目标的感知鲁棒性。在包含5类典型缺陷的光伏红外航拍数据集上,改进模型的mAP@0.5达到84.12%,较基准RT-DETR-r18提升5.16%,且推理速度达48 FPS,满足工业实时巡检需求。结果表明,该方案在复杂户外场景下能有效提升光伏缺陷检测的精度与可靠性。
Surface defect detection of photovoltaic panels is of paramount importance for ensuring the power generation efficiency and operational safety of photovoltaic systems. To tackle challenges such as the difficulty in detecting small aerial targets in infrared images captured by drones, significant interference from outdoor thermal backgrounds, and the broad scale range of defect targets, this study introduces a photovoltaic infrared defect detection model that integrates multi-scale features with dynamic convolution. First, in the shallow pathway, spatial-to-depthwise convolution(SPD-Conv) is employed to substitute traditional downsampling methods, thereby preventing the loss of fine-grained features and edge information pertaining to small targets, including diode anomalies and hot spots. Second, a dynamic full-dimensional convolution(CSPOmniKernel) module is incorporated, which adaptively modulates the receptive field through a multi-branch mechanism, thereby enhancing low-contrast defect features while mitigating interference from complex thermal backgrounds. Finally, an efficient multi-scale feature fusion module(MFM) is devised, leveraging cross-level information interaction and adaptive aggregation to bolster the model’s robustness in perceiving targets of varying scales. On a photovoltaic infrared aerial dataset encompassing five typical defect types, the enhanced model attains an mAP@0.5 of 84.12%, marking a 5.16% improvement over the baseline RT-DETR-r18, and achieves an inference speed of 48 FPS, fulfilling the demands of industrial real-time inspection. The results demonstrate that this approach significantly elevates the accuracy and reliability of photovoltaic defect detection in intricate outdoor environments.
王小宇 , 刘波 , 孙凯 , 等 . 光伏阵列故障诊断技术综述 [J]. 电工技术学报 , 2024 , 39 ( 20 ): 6526 - 6543 .
WANG X Y , LIU B , SUN K , et al . A review of photovoltaic array fault diagnosis technology [J]. Transactions of China Electrotechnical Society , 2024 , 39 ( 20 ): 6526 - 6543 . (in Chinese)
陈天祥 , 陈志聪 , 吴丽君 , 等 . 面向边缘设备的EL图像光伏电池缺陷检测模型 [J]. 福州大学学报(自然科学版) , 2026 , 54 ( 1 ): 1 - 9 .
CHEN T X , CHEN Z C , WU L J , et al . An EL image photovoltaic cell defect detection model for edge devices [J]. Journal of Fuzhou University (Natural Science Edition) , 2026 , 54 ( 1 ): 1 - 9 . (in Chinese)
翟金星 , 王力平 , 张艳辉 . 基于无人机红外视觉的光伏电站热斑智能巡检 [J]. 红外技术 , 2026 , 48 ( 1 ): 95 - 104 .
ZHAI J X , WANG L P , ZHANG Y H . Unmanned-aerial-vehicle infrared-vision-based intelligent inspection of hotspots in photovoltaic power station [J]. Infrared Technology , 2026 , 48 ( 1 ): 95 - 104 . (in Chinese)
张绘敏 , 赵扬 , 康会峰 . 基于卷积神经网络算法的光伏组件热斑图像检测方法研究 [J]. 计算机测量与控制 , 2024 , 32 ( 7 ): 57 - 63 .
ZHANG H M , ZHAO Y , KANG H F . Research on thermal spot image detection method for photovoltaic modules based on convolutional neural network algorithms [J]. Computer Measurement & Control , 2024 , 32 ( 7 ): 57 - 63 . (in Chinese)
赵玲玲 , 汪烨 , 刘俊 . 基于无人机与HSV空间的光伏电池板检测分析 [J]. 红外技术 , 2020 , 42 ( 10 ): 978 - 982 . doi: 10.3724/sp.j.7103116037 http://dx.doi.org/10.3724/sp.j.7103116037
ZHAO L L , WANG Y , LIU J . Detection and analysis of photovoltaic panels based on UAV and HSV space [J]. Infrared Technology , 2020 , 42 ( 10 ): 978 - 982 . (in Chinese) . doi: 10.3724/sp.j.7103116037 http://dx.doi.org/10.3724/sp.j.7103116037
张志豪 , 厉小润 , 陈淑涵 . 基于改进YOLO11的无人机航拍图像小目标检测算法 [J]. 液晶与显示 , 2025 , 40 ( 6 ): 915 - 930 . doi: 10.37188/cjlcd.2025-0010 http://dx.doi.org/10.37188/cjlcd.2025-0010
ZHANG Z H , LI X R , CHEN S H . Small object detection algorithm in UAV aerial images based on improved YOLO11 [J]. Chinese Journal of Liquid Crystals and Displays , 2025 , 40 ( 6 ): 915 - 930 . (in Chinese) . doi: 10.37188/cjlcd.2025-0010 http://dx.doi.org/10.37188/cjlcd.2025-0010
王浩 , 闫号 , 叶海瑞 , 等 . 基于无人机的光伏电站智能巡检 [J]. 红外技术 , 2022 , 44 ( 5 ): 537 - 542 .
WANG H , YAN H , YE H R , et al . Intelligent patrol inspection of photovoltaic power station based on UAVs [J]. Infrared Technology , 2022 , 44 ( 5 ): 537 - 542 . (in Chinese)
赵强 , 刘胜杰 , 韩东成 , 等 . 基于改进K均值聚类的光伏板缺陷检测方法 [J]. 红外技术 , 2024 , 46 ( 4 ): 475 - 482 .
ZHAO Q , LIU S J , HAN D C , et al . Improved K-means clustering-based defect detection method for photovoltaic panels [J]. Infrared Technology , 2024 , 46 ( 4 ): 475 - 482 . (in Chinese)
XU X Y , ZHAO M , SHI P X , et al . Crack detection and comparison study based on faster R-CNN and mask R-CNN [J]. Sensors , 2022 , 22 ( 3 ): 1215 . doi: 10.3390/s22031215 http://dx.doi.org/10.3390/s22031215
JIANG P Y , ERGU D , LIU F Y , et al . A review of Yolo algorithm developments [J]. Procedia Computer Science , 2022 , 199 : 1066 - 1073 . doi: 10.1016/j.procs.2022.01.135 http://dx.doi.org/10.1016/j.procs.2022.01.135
孙建波 , 王丽杰 , 麻吉辉 , 等 . 基于改进YOLO v5s算法的光伏组件故障检测 [J]. 红外技术 , 2023 , 45 ( 2 ): 202 - 208 .
SUN J B , WANG L J , MA J H , et al . Photovoltaic module fault detection based on improved YOLOv5s algorithm [J]. Infrared Technology , 2023 , 45 ( 2 ): 202 - 208 . (in Chinese)
杨彦萍 , 高军伟 , 刘兆龙 , 等 . 基于改进YOLO11的印刷电路板表面缺陷检测算法 [J]. 液晶与显示 , 2025 , 40 ( 10 ): 1545 - 1556 . doi: 10.37188/cjlcd.2025-0137 http://dx.doi.org/10.37188/cjlcd.2025-0137
YANG Y P , GAO J W , LIU Z L , et al . Surface defect detection on printed circuit boards based on improved YOLO11 [J]. Chinese Journal of Liquid Crystals and Displays , 2025 , 40 ( 10 ): 1545 - 1556 . (in Chinese) . doi: 10.37188/cjlcd.2025-0137 http://dx.doi.org/10.37188/cjlcd.2025-0137
闫号 , 戴佳佳 , 龚小溪 , 等 . 基于多源图像融合的光伏面板缺陷检测 [J]. 红外技术 , 2023 , 45 ( 5 ): 488 - 497 .
YAN H , DAI J J , GONG X X , et al . Defect detection of photovoltaic panel based on multisource image fusion [J]. Infrared Technology , 2023 , 45 ( 5 ): 488 - 497 . (in Chinese)
CHEN S H , LU Y , QIN G X , et al . CSPD-DETR: real-time silicon crystalline photovoltaic cell surface defect detection transformer for building photovoltaic systems [J]. Journal of Building Engineering , 2025 , 108 : 112810 . doi: 10.1016/j.jobe.2025.112810 http://dx.doi.org/10.1016/j.jobe.2025.112810
CHEN Y L , SHAN M T , ZHOU W , et al . RT-DETR-Pro: an enhanced RT-DETR model for visual detection of photovoltaic module defects [J]. IEEE Access , 2025 , 13 : 116473 - 116479 . doi: 10.1109/access.2025.3585151 http://dx.doi.org/10.1109/access.2025.3585151
JEONG H , YOON C , LIM H , et al . MT-former: multi-task hybrid transformer and deep support vector data description to detect novel anomalies during semiconductor manufacturing [J]. Light: Advanced Manufacturing , 2025 , 6 ( 2 ): 306 - 318 . doi: 10.37188/lam.2025.032 http://dx.doi.org/10.37188/lam.2025.032
邱刚 , 张廼龙 , 柏仓 , 等 . 基于红外与可见光图像匹配的巡检机器人障碍识别与分类 [J]. 红外技术 , 2025 , 47 ( 1 ): 81 - 88 .
QIU G , ZHANG N L , BAI C , et al . Inspection robot obstacle recognition and classification based on infrared and visible light image matching [J]. Infrared Technology , 2025 , 47 ( 1 ): 81 - 88 . (in Chinese)
WU N F , SUN Y X , HU J T , et al . Intelligent nanophotonics: when machine learning sheds light [J]. eLight , 2025 , 5 ( 1 ): 5 . doi: 10.1186/s43593-025-00085-x http://dx.doi.org/10.1186/s43593-025-00085-x
Mao W Z , Luan H Y , Ma R M . Singulonics: narwhal-shaped wavefunctions for sub-diffraction-limited nanophotonics and imaging [J]. eLight , 2025 , 5 ( 1 ): 27 . doi: 10.1186/s43593-025-00104-x http://dx.doi.org/10.1186/s43593-025-00104-x
LI J L , TONG T , LI D Q , et al . A dynamically adaptive and high-efficiency small object detection network for infrared thermographic images in online monitoring of solar photovoltaic panel defects [J]. Energy , 2025 , 335 : 138129 . doi: 10.1016/j.energy.2025.138129 http://dx.doi.org/10.1016/j.energy.2025.138129
LI Z P , YUAN J Q , ZHANG Z Z . SolarIR-DETR: a lightweight transformer for UAV-assisted thermal hotspot detection in solar photovoltaic panels [J]. Scientific Reports , 2026 , 16 ( 1 ): 17172 . doi: 10.1038/s41598-026-50451-z http://dx.doi.org/10.1038/s41598-026-50451-z
任鹏百 , 雷慧云 , 党建武 , 等 . 基于HMSD与改进PCNN的红外与可见光图像融合 [J]. 光学 精密工程 , 2025 , 33 ( 9 ): 1481 - 1495 . doi: 10.37188/ope.20253309.1481 http://dx.doi.org/10.37188/ope.20253309.1481
REN P B , LEI H Y , DANG J W , et al . Infrared and visible image fusion based on HMSD and improved PCNN [J]. Optics and Precision Engineering , 2025 , 33 ( 9 ): 1481 - 1495 . (in Chinese) . doi: 10.37188/ope.20253309.1481 http://dx.doi.org/10.37188/ope.20253309.1481
YU S S , GAN F B , HAN T , et al . Multimodal fault detection model for photovoltaic modules [J]. Scientific Reports , 2026 , 16 ( 1 ): 3278 . doi: 10.1038/s41598-025-28603-4 http://dx.doi.org/10.1038/s41598-025-28603-4
CAO H , HU H L , LU M , et al . LWMF-DETR: a lightweight transformer network for photovoltaic hot-spot fault detection with multi-scale wavelet feature fusion [J]. Solar Energy Materials and Solar Cells , 2026 , 295 : 114005 . doi: 10.1016/j.solmat.2025.114005 http://dx.doi.org/10.1016/j.solmat.2025.114005
0
浏览量
45
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621