Deep Learning-Based Algorithm for Multi-Type Defects Detection in Solar Cells with Aerial EL Images for Photovoltaic Plants

被引:10
|
作者
Tang, Wuqin [1 ]
Yang, Qiang [1 ]
Yan, Wenjun [1 ]
机构
[1] Zhejiang Univ, Coll Elect Engn, Hangzhou 310027, Peoples R China
来源
关键词
Electroluminescence images; deep clustering; automatic defect classification; transfer learning; PERFORMANCE;
D O I
10.32604/cmes.2022.018313
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Defects detection with Electroluminescence (EL) image for photovoltaic (PV) module has become a standard test procedure during the process of production, installation, and operation of solar modules. There are some typical defects types, such as crack, finger interruption, that can be recognized with high accuracy. However, due to the complexity of EL images and the limitation of the dataset, it is hard to label all types of defects during the inspection process. The unknown or unlabeled create significant difficulties in the practical application of the automatic defects detection technique. To address the problem, we proposed an evolutionary algorithm combined with traditional image processing technology, deep learning, transfer learning, and deep clustering, which can recognize the unknown or unlabeled in the original dataset defects automatically along with the increasing of the dataset size. Specifically, we first propose a deep learning-based features extractor and defects classifier. Then, the unlabeled defects can be classified by the deep clustering algorithm and stored separately to update the original database without human intervention. When the number of unknown images reaches the preset values, transfer learning is introduced to train the classifier with the updated database. The fine-tuned model can detect new defects with high accuracy. Finally, numerical results confirm that the proposed solution can carry out efficient and accurate defect detection automatically using electroluminescence images.
引用
收藏
页码:1423 / 1439
页数:17
相关论文
共 50 条
  • [1] Cloud detection of multi-type satellite images based on spectral assimilation and deep learning
    Li, Kaining
    Ma, Nan
    Sun, Lin
    [J]. INTERNATIONAL JOURNAL OF REMOTE SENSING, 2023, 44 (10) : 3106 - 3121
  • [2] Multi-type factors representation learning for deep learning-based knowledge tracing
    Liangliang He
    Jintao Tang
    Xiao Li
    Pancheng Wang
    Feng Chen
    Ting Wang
    [J]. World Wide Web, 2022, 25 : 1343 - 1372
  • [3] Multi-type factors representation learning for deep learning-based knowledge tracing
    He, Liangliang
    Tang, Jintao
    Li, Xiao
    Wang, Pancheng
    Chen, Feng
    Wang, Ting
    [J]. WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS, 2022, 25 (03): : 1343 - 1372
  • [4] Comprehensive Analysis of Deep Learning-Based Vehicle Detection in Aerial Images
    Sommer, Lars
    Schuchert, Tobias
    Beyerer, Juergen
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2019, 29 (09) : 2733 - 2747
  • [5] A Deep Learning-Based Surface Defects Detection and Color Classification Method for Solar Cells
    Zhang, Huimin
    Zhao, Yang
    Huang, Shuangcheng
    Kang, Huifeng
    Han, Haimin
    [J]. JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS, 2023, 32 (09)
  • [6] A LEARNING-BASED MULTI-TYPE NOISE SUPPRESSING METHOD FOR REMOTE SENSING IMAGES
    Li, Yuhui
    Yu, Xindi
    Pei, Jifang
    Huo, Weibo
    Zhang, Yin
    Huang, Yulin
    Yang, Jianyu
    [J]. 2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 2022, : 3299 - 3302
  • [7] Deep learning-based method for defect detection in electroluminescent images of polycrystalline silicon solar cells
    Liu, Yuqi
    Wu, Yiquan
    Yuan, Yubin
    Zhao, Langyue
    [J]. OPTICS EXPRESS, 2024, 32 (10): : 17295 - 17317
  • [8] Scalable Deep Reinforcement Learning-Based Online Routing for Multi-Type Service Requirements
    Liu, Chenyi
    Wu, Pingfei
    Xu, Mingwei
    Yang, Yuan
    Geng, Nan
    [J]. IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2023, 34 (08) : 2337 - 2351
  • [9] Machine learning-based algorithm for the classification and prediction of multi-type spot weld quality
    Jia, Pengzhen
    Sheng, Buyun
    Zhao, Guangde
    [J]. JOURNAL OF ADVANCED MECHANICAL DESIGN SYSTEMS AND MANUFACTURING, 2023, 17 (06)
  • [10] Deep learning based multi-category object detection in aerial images
    Sommer, Lars W.
    Schuchert, Tobias
    Beyerer, Juergen
    [J]. AUTOMATIC TARGET RECOGNITION XXVII, 2017, 10202