A machine learning framework to identify the hotspot in photovoltaic module using infrared thermography
A machine learning framework to identify the hotspot in photovoltaic module using infrared thermography
复制标题
DOI：
10.1016/j.solener.2020.08.027
复制
发表时间：
2020-09-15
期刊：
影响因子：
6.7
通讯作者：
Zafar, Amad
中科院分区：
文献类型：
--
作者：
Ali, Muhammad Umair;Khan, Hafiz Farhaj;Zafar, Amad
提出了一种基于混合特征的支持向量机（SVM）模型，并将其应用于红外热像技术的光伏（PV）板热点检测与分类。采用数据融合的方法，形成了一种新的混合特征向量，包括RGB，纹理，方向梯度直方图（HOG）和局部二值模式（LBP）作为特征。采用机器学习算法SVM将所获得的PV板的热图像分类为三个不同的类别（即，健康、无故障热点和故障）。还对不同机器学习算法和数据集进行了比较，以验证所提出的模型和混合特征数据集的优越性。实验结果表明，所提出的混合特征与支持向量机导致96.8%的训练准确率和92%的测试准确率与更少的计算复杂度和存储空间比其他机器学习算法。所提出的方法是很容易实现的有效监测和光伏电池板的故障诊断。
In this paper, a hybrid features based support vector machine (SVM) model is proposed using infrared thermography technique for hotspots detection and classification of photovoltaic (PV) panels. A novel hybrid feature vector consisting of RGB, texture, the histogram of oriented gradient (HOG), and local binary pattern (LBP) as features is formed using a data fusion approach. A machine learning algorithm SVM is employed to classify the obtained thermal images of PV panels into three different classes (i.e., healthy, non-faulty hotspot, and faulty). The comparison of different machine learning algorithms and datasets is also carried out to validate the superiority of the proposed model and hybrid feature dataset. The experimental results reveal that the proposed hybrid features with SVM resulted in 96.8% training accuracy and 92% testing accuracy with lesser computational complexity and storage space than other machine learning algorithms. The proposed approach is easily implementable for efficient monitoring and fault diagnosis of PV panels.