Photovoltaic defect classification through thermal infrared imaging using a machine learning approach

被引：104

作者：

Dunderdale, Christopher ^{[1
]}

Brettenny, Warren ^{[1
]}

Clohessy, Chantelle ^{[1
]}

van Dyk, E. Ernest ^{[2
]}

机构：

[1] Nelson Mandela Univ, Dept Stat, Port Elizabeth, South Africa

[2] Nelson Mandela Univ, Dept Phys, Port Elizabeth, South Africa

来源：

PROGRESS IN PHOTOVOLTAICS | 2020年 / 28卷 / 03期

基金：

新加坡国家研究基金会;

关键词：

deep learning; defect classification; defect detection; infrared thermography; machine learning; photovoltaic; random forest; SIFT; support vector machine; DIAGNOSIS; MODULES; FAULTS;

D O I：

10.1002/pip.3191

中图分类号：

TE [石油、天然气工业]; TK [能源与动力工程];

学科分类号：

0807 ; 0820 ;

摘要：

This study examines a deep learning and feature-based approach for the purpose of detecting and classifying defective photovoltaic modules using thermal infrared images in a South African setting. The VGG-16 and MobileNet models are shown to provide good performance for the classification of defects. The scale invariant feature transform (SIFT) descriptor, combined with a random forest classifier, is used to identify defective photovoltaic modules. The implementation of this approach has potential for cost reduction in defect classification over current methods.

引用

页码：177 / 188

页数：12