A Deep Learning Approach to Photovoltaic Cell Defect Classification

被引：0
作者：
Banda, P. [1 ]
Barnard, L. [1 ]
机构：
[1] Nelson Mandela Univ, Dept Comp Sci, POB 77000, ZA-6031 Port Elizabeth, South Africa
来源：
PROCEEDINGS OF THE ANNUAL CONFERENCE OF THE SOUTH AFRICAN INSTITUTE OF COMPUTER SCIENTISTS AND INFORMATION TECHNOLOGISTS (SAICSIT 2018) | 2018年
关键词：
Deep learning; Machine learning; Photovoltaic; Electroluminescence;
D O I：
暂无
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
The aim of this paper is to determine whether photovoltaic (PV) cells can be automatically identified as either defective or normal from electroluminescence (EL) images. This paper utilizes an experimental methodology to address the identified research problem. This paper provides evidence that deep learning (DL) cart be used to distinguish between a defective and a normal PV cell. The results of this research confirm that techniques front the Computer Science discipline can he applied in photovoltaics to alleviate the tedious processes used in identifying defective PV cells from I I, images.
引用
收藏
页码：215 / 221
页数：7
相关论文
共 28 条
  • [1] Deep learning for biological image classification
    Affonso, Carlos
    Debiaso Rossi, Andre Luis
    Antunes Vieira, Fabio Henrique
    de Leon Ferreira de Carvalho, Andre Carlos Ponce
    [J]. EXPERT SYSTEMS WITH APPLICATIONS, 2017, 85 : 114 - 122
  • [2] Al-Doski J., 2013, Journal of Environment and Earth Science, V3, P141
  • [3] [Anonymous], 2016, DEEP LEARNING PYTHON, V53, P1689, DOI [10.1017/CBO9781107415324004, DOI 10.1017/CBO9781107415324.004]
  • [4] [Anonymous], Neural networks and learning machines
  • [5] Baici Batuhan, 2017, HANDWRITTEN TEXT REC
  • [6] Bishop C. M., 2006, PATTERN RECOGN, V4, DOI DOI 10.1007/978-0-387-45528-0
  • [7] Caesar Dan, 2012, MULTICOLUMN DEEP NEU, DOI [10.1109/CVPR.2012.6248110, DOI 10.1109/CVPR.2012.6248110]
  • [8] Chen Chenyi, 2018, PRINCET VISON ROBOTI, V1
  • [9] Choras RyszardS., 2007, INT J BIO BIOMED ENG, V1, P6
  • [10] Creswell, 2018, RES DESIGN QUALITATI
123