浏览全部资源
扫码关注微信
西安科技大学 电气与控制工程学院,陕西 西安 710054
[ "郝 帅(1986-),男,河北任丘人,博士,副教授,硕士生导师,2014年于西北工业大学获博士学位,主要研究方向为人工智能、电气设备故障诊断。E-mail:haoxust@163.com" ]
[ "马 旭(1985-),女,陕西西安人,博士,讲师,2017年于西北工业大学获博士学位,主要研究方向为人工智能、图像处理。E-mail:414548542@qq.com" ]
收稿日期:2023-05-05,
修回日期:2023-06-16,
纸质出版日期:2023-12-25
移动端阅览
郝帅,吴瑛琦,马旭等.融合知识蒸馏和注意力机制的光伏热斑检测[J].光学精密工程,2023,31(24):3640-3650.
HAO Shuai,WU Yingqi,MA Xu,et al.Photovoltaic hot spot detection method incorporating knowledge distillation and attention mechanisms[J].Optics and Precision Engineering,2023,31(24):3640-3650.
郝帅,吴瑛琦,马旭等.融合知识蒸馏和注意力机制的光伏热斑检测[J].光学精密工程,2023,31(24):3640-3650. DOI: 10.37188/OPE.20233124.3640.
HAO Shuai,WU Yingqi,MA Xu,et al.Photovoltaic hot spot detection method incorporating knowledge distillation and attention mechanisms[J].Optics and Precision Engineering,2023,31(24):3640-3650. DOI: 10.37188/OPE.20233124.3640.
针对复杂环境下光伏电池板热斑故障的多尺度目标导致检测困难的问题,提出一种融合知识蒸馏和注意力机制的检测算法。为实现故障特征信息高效提取与保留,设计一种融合高阶空间交互和通道注意力的模块以提升网络对于故障特征信息的表达能力;为增强复杂背景下目标信息表达能力,构建一种结合通道和位置信息的注意力模块来提高网络对于故障位置信息的识别准确率;采用知识蒸馏思想将教师网络的参数迁移至学生网络,在不增加任何复杂度的前提下提升学生网络的检测精度。为进一步精确定位热斑目标,引入Focal-CIoU损失函数加速网络收敛,从而提升检测性能。为验证算法有效性,与8种经典算法进行比较,实验结果表明,本文算法的检测精度最高,精度达84.8%,对于分辨率为640×512的图像检测速度可达142 FPS。
A detection algorithm combining knowledge distillation and attention mechanism is proposed to solve the problem that multi-scale target of the hot spot fault of photovoltaic panel in a complex environment leads to difficult detection. To efficiently extract and retain fault feature information, a module that integrates higher-order spatial interaction and channel attention was designed to improve the expression ability of fault feature information. To further enhance the ability of expressing target information in a complex background, an attention module combining channel and location information was constructed to improve the recognition accuracy of fault location information. The parameters of teacher network were transferred to student network by knowledge distillation, and the detection accuracy of student network was improved without adding any complexity. A focal-CIoU loss function was introduced to accelerate network convergence and improve detection performance. In verifying the effectiveness of the proposed algorithm against eight classical algorithms, the experimental results show that the proposed algorithm has the highest detection accuracy (84.8%), and the detection speed can reach 142 FPS for images with a resolution of 640×512.
孙海蓉 , 李帆 . 基于注意力机制的光伏热斑识别 [J]. 太阳能学报 , 2023 , 44 ( 2 ): 453 - 459 .
SUN H R , LI F . Photovoltaic hot spot recognition based on attention mechanism [J]. Acta Energiae Solaris Sinica , 2023 , 44 ( 2 ): 453 - 459 . (in Chinese)
蒋琳 , 苏建徽 , 李欣 , 等 . 基于可见光和红外热图像融合的光伏阵列热斑检测方法 [J]. 太阳能学报 , 2022 , 43 ( 1 ): 393 - 397 .
JIANG L , SU J H , LI X , et al . Hot spot detection of photovoltaic array based on fusion of visible and infrared thermal images [J]. Acta Energiae Solaris Sinica , 2022 , 43 ( 1 ): 393 - 397 . (in Chinese)
毛峡 , 石天朋 . 光伏热斑图像有效区域分割算法研究 [J]. 太阳能学报 , 2018 , 39 ( 5 ): 1270 - 1276 .
MAO X , SHI T P . Research on segmentation algorithm of effective region in photovoltaic hot spot image [J]. Acta Energiae Solaris Sinica , 2018 , 39 ( 5 ): 1270 - 1276 . (in Chinese)
马铭遥 , 张志祥 , 刘恒 , 等 . 基于I-V特性分析的晶硅光伏组件故障诊断 [J]. 太阳能学报 , 2021 , 42 ( 6 ): 130 - 137 .
MA M Y , ZHANG Z X , LIU H , et al . Fault diagnosis of crystalline silicon photovoltaic module based on I-V characteristic analysis [J]. Acta Energiae Solaris Sinica , 2021 , 42 ( 6 ): 130 - 137 . (in Chinese)
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)
孙海蓉 , 周映杰 , 张镇韬 , 等 . 基于改进自私羊群算法的光伏红外热图像热斑识别方法 [J]. 中国电机工程学报 , 2022 , 42 ( 24 ): 8942 - 8950 .
SUN H R , ZHOU Y J , ZHANG Z T , et al . Hot spot recognition method of photovoltaic infrared thermal image based on improved selfish herd algorithm [J]. Proceedings of the CSEE , 2022 , 42 ( 24 ): 8942 - 8950 . (in Chinese)
蒋琳 , 苏建徽 , 施永 , 等 . 基于红外热图像处理的光伏阵列热斑检测方法 [J]. 太阳能学报 , 2020 , 41 ( 8 ): 180 - 184 .
JIANG L , SU J H , SHI Y , et al . Hot spots detection of operating PV arrays through IR thermal image [J]. Acta Energiae Solaris Sinica , 2020 , 41 ( 8 ): 180 - 184 . (in Chinese)
GRIMACCIA F , LEVA S , NICCOLAI A . PV plant digital mapping for modules’ defects detection by unmanned aerial vehicles [J]. IET Renewable Power Generation , 2017 , 11 ( 10 ): 1221 - 1228 . doi: 10.1049/iet-rpg.2016.1041 http://dx.doi.org/10.1049/iet-rpg.2016.1041
刘忻伟 , 朴永杰 , 郑亮亮 , 等 . 面向航天光学遥感复杂场景图像的舰船检测 [J]. 光学 精密工程 , 2023 , 31 ( 6 ): 892 - 904 . doi: 10.37188/OPE.20233106.0892 http://dx.doi.org/10.37188/OPE.20233106.0892
LIU X W , PIAO Y J , ZHENG L L , et al . Ship detection for complex scene images of space optical remote sensing [J]. Opt. Precision Eng. , 2023 , 31 ( 6 ): 892 - 904 . (in Chinese) . doi: 10.37188/OPE.20233106.0892 http://dx.doi.org/10.37188/OPE.20233106.0892
张丽丽 , 陈真 , 刘雨轩 , 等 . 基于ZYNQ的Yolo v3-SPP实时目标检测系统 [J]. 光学 精密工程 , 2023 , 31 ( 4 ): 543 - 551 . doi: 10.37188/ope.20233104.0543 http://dx.doi.org/10.37188/ope.20233104.0543
ZHANG L L , CHEN Z , LIU Y X , et al . Yolo v3-SPP real-time target detection system based on ZYNQ [J]. Opt. Precision Eng. , 2023 , 31 ( 4 ): 543 - 551 . (in Chinese) . doi: 10.37188/ope.20233104.0543 http://dx.doi.org/10.37188/ope.20233104.0543
郝帅 , 何田 , 马旭 , 等 . 动态特征优化机制下的跨尺度红外行人检测 [J]. 光学 精密工程 , 2022 , 30 ( 19 ): 2390 - 2403 . doi: 10.37188/OPE.20223019.2390 http://dx.doi.org/10.37188/OPE.20223019.2390
HAO S , HE T , MA X , et al . Cross-scale infrared pedestrian detection based on dynamic feature optimization mechanism [J]. Opt. Precision Eng. , 2022 , 30 ( 19 ): 2390 - 2403 . (in Chinese) . doi: 10.37188/OPE.20223019.2390 http://dx.doi.org/10.37188/OPE.20223019.2390
REN S Q , HE K M , GIRSHICK R , et al . Faster R-CNN: towards real-time object detection with region proposal networks [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017 , 39 ( 6 ): 1137 - 1149 . doi: 10.1109/tpami.2016.2577031 http://dx.doi.org/10.1109/tpami.2016.2577031
CAO J H , ZHANG J J , JIN X . A traffic-sign detection algorithm based on improved sparse R-CNN [J]. IEEE Access , 2021 , 9 : 122774 - 122788 . doi: 10.1109/access.2021.3109606 http://dx.doi.org/10.1109/access.2021.3109606
樊涛 , 孙涛 , 刘虎 . 基于注意力机制的光伏组件热斑检测算法 [J]. 北京航空航天大学学报 , 2022 , 48 ( 7 ): 1304 - 1313 .
FAN T , SUN T , LIU H . Hot spot detection algorithm of photovoltaic module based on attention mechanism [J]. Journal of Beijing University of Aeronautics and Astronautics , 2022 , 48 ( 7 ): 1304 - 1313 . (in Chinese)
谢誉 , 包梓群 , 张娜 , 等 . 基于特征优化与深层次融合的目标检测算法 [J]. 浙江大学学报(工学版) , 2022 , 56 ( 12 ): 2403 - 2415 .
XIE Y , BAO Z Q , ZHANG N , et al . Object detection algorithm based on feature enhancement and deep fusion [J]. Journal of Zhejiang University (Engineering Science) , 2022 , 56 ( 12 ): 2403 - 2415 . (in Chinese)
JU M , LUO J , LIU G , et al . ISTDet: an efficient end-to-end neural network for infrared small target detection [J]. Infrared Physics & Technology , 2021 , 114 : 103659 . doi: 10.1016/j.infrared.2021.103659 http://dx.doi.org/10.1016/j.infrared.2021.103659
李想 , 特日根 , 仪锋 , 等 . 针对全球储油罐检测的TCS-YOLO模型 [J]. 光学 精密工程 , 2023 , 31 ( 2 ): 246 - 262 . doi: 10.37188/OPE.20233102.0246 http://dx.doi.org/10.37188/OPE.20233102.0246
LI X , TE R G , YI F , et al . TCS-YOLO model for global oil storage tank inspection [J]. Opt. Precision Eng. , 2023 , 31 ( 2 ): 246 - 262 . (in Chinese) . doi: 10.37188/OPE.20233102.0246 http://dx.doi.org/10.37188/OPE.20233102.0246
王道累 , 姚勇 , 张世恒 , 等 . 基于红外热图像的光伏组件热斑深度学习检测方法 [J/OL]. 中国电机工程学报 : 1 - 9 [ 2023-04-20 ]. https://doi.org/10.13334/j.0258-8013.pcsee.221519 https://doi.org/10.13334/j.0258-8013.pcsee.221519 .
WANG D L , YAO Y , ZHANG S H , et al . Deep Learning Detection Method of Photovoltaic Module Hot Spot Based on Infrared Thermal Image [J/OL]. Chinese Society for Electrical Engineering , 1 - 9 [ 2023-04-20 ]. https://doi.org/10.13334/j.0258-8013.pcsee.221519. https://doi.org/10.13334/j.0258-8013.pcsee.221519. (in Chinese)
夏杰锋 , 唐武勤 , 杨强 . 光伏航拍红外图像的热斑自动检测方法 [J]. 浙江大学学报(工学版) , 2022 , 56 ( 8 ): 1640 - 1647 .
XIA J F , TANG W Q , YANG Q . Automatic hot spot detection method for photovoltaic aerial infrared image [J]. Journal of Zhejiang University (Engineering Science) , 2022 , 56 ( 8 ): 1640 - 1647 . (in Chinese)
SU B Y , CHEN H Y , LIU K , et al . RCAG-Net: residual channelwise attention gate network for hot spot defect detection of photovoltaic farms [J]. IEEE Transactions on Instrumentation and Measurement , 2021 , 70 : 1 - 14 . doi: 10.1109/tim.2021.3054415 http://dx.doi.org/10.1109/tim.2021.3054415
0
浏览量
550
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构