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
Research on Thermal Spot Image Detection Method for Photovoltaic Modules Based on Convolutional Neural Network Algorithms
张绘敏 1赵扬 2康会峰3
作者信息
- 1. 河南应用技术职业学院机电工程学院,郑州 450042
- 2. 河南应用技术职业学院化学工程学院,郑州 450042
- 3. 北华航天工业学院航空宇航学院,河北廊坊 065000
- 折叠
摘要
热斑效应是造成光伏组件损坏的主要原因之一,为提早发现光伏组件热斑效应,利用卷积神经网络算法优化设计光伏组件热斑图像检测方法;根据光伏组件的工作原理以及热斑的产生机理,设置光伏组件热斑图像检测标准;通过红外热像仪和探测器采集光伏组件热斑图像,并对采集得到的图像展开预处理;利用卷积神经网络算法从轮廓和颜色两个方面提取预处理后热斑图像的特征,根据特征匹配结果得出光伏组件热斑图像的检测结果;实验结果表明:与传统检测方法相比,优化设计方法的漏检率和误检率明显更低,且光伏组件热斑面积检测误差较低,说明其检测效果较好.
Abstract
The hot spot effect is one of the main causes of damage to photovoltaic modules,in order to detect the hot spot effect of photovoltaic modules early,convolutional neural network algorithms are used to optimize the design of photovoltaic module hot spot image detection methods.According to the working principle of photovoltaic modules and the mechanism of hot spot generation,the detection standards for hot spot images of photovoltaic modules is set.The collected thermal spot images of photovoltaic modules are preprocessed through the infrared thermal imagers and detectors.Convolutional neural network algorithms are used to extract the fea-tures of preprocessed hot spot images from both contour and color aspects,the detection results of photovoltaic module hot spot ima-ges are obtained based on the feature matching results.The experimental results show that compared with traditional detection meth-ods,the optimized design method has significantly lower missed detection and false detection rates,and the detection error of photo-voltaic module hot spot area is lower,indicating that it has better detection effect.
关键词
机器学习/光伏组件/热斑图像/图像检测Key words
machine learning/photovoltaic modules/hot spot images/image detection引用本文复制引用
基金项目
河南省科技攻关项目(242102220027)
2023年河南省职业教育教学改革研究与实践项目(豫教[2024]05740)
2021年度河南省高等教育教学改革研究与实践项目(2021SJGLX881)
2023年河南省教育科学规划课题(2023YB0447)
河南应用技术职业学院2022年度校级科研课题(2022-KJ-44)
2024河南省高校人文社会科学研究一般项目(2024-ZDJH-201)
出版年
2024
NETL
NSTL
万方数据