一种基于航拍红外图像的光伏热斑故障分类检测方法  

CLASSIFICATION DETECTION METHOD OF PHOTOVOLTAIC THERMAL SPOT IN AERIAL INFRARED IMAGE

在线阅读下载全文

作  者:张妍[1,2] 裴兴豪 李冰[1] 张雄 Zhang Yan;Pei Xinghao;Li Bing;Zhang Xiong(Department of Automation,North China Electric Power University,Baoding 071003,China;Hebei Technology Innovation Center of Simulation&Optimized Control for Power Generation,North China Electric Power University,Baoding 071003,China)

机构地区:[1]华北电力大学自动化系,保定071003 [2]华北电力大学河北省发电过程仿真与优化控制技术创新中心,保定071003

出  处:《太阳能学报》2024年第9期353-359,共7页Acta Energiae Solaris Sinica

基  金:国家自然科学基金(U21A20486);河北省省级科技计划(22567643H)。

摘  要:针对航拍光伏红外图像热斑检测方法中小目标特征易丢失问题,提出一种光伏热斑故障分类检测方法。首先将多头自注意力机制结合CSPNet结构进行改进,提出CSPMAT网络,再将其引入New CSP-Darknet网络,构建CSPMAT-Darknet模型,实现了光伏组件热斑定位及分类。实验结果表明:该模型在小目标检测任务中的性能显著提升,且在目标尺寸差异较大的故障分类检测任务中,均值平均精度达到82.92%,提高了13.97个百分点,具有良好的检测精度和泛化能力。A photovoltaic thermal spot fault classification detection method is proposed to resolve the issue of small target feature loss in the thermal spot detection method for aerial photovoltaic infrared images.Firstly,the multi-head self-attention mechanism is integrated with the CSPNet structure for improvement,resulting in the proposed CSPMAT network.Subsequently,this network is introduced into the New CSP-Darknet architecture,leading to the construction of the CSPMAT-Darknet model,achieving both localization and classification of photovoltaic component thermal spots.Experimental results demonstrate that the model enhances performance in small target detection tasks significantly.Moreover,in fault classification detection tasks with substantial target size variations,the achieved mean average precision(mAP)reaches 82.92%,an increase of 13.97 percentage points,thereby showcasing commendable detection accuracy and generalization capability.

关 键 词:红外热图像 图像识别 特征提取 CSPNet 多头自注意力机制 分类检测 

分 类 号:TP18[自动化与计算机技术—控制理论与控制工程] TM615[自动化与计算机技术—控制科学与工程]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象