Deep Learning Based Module Defect Analysis for Large-Scale Photovoltaic Farms

被引:101
|
作者
Li, Xiaoxia [1 ]
Yang, Qiang [1 ]
Lou, Zhuo [1 ]
Yan, Wenjun [1 ]
机构
[1] Zhejiang Univ, Coll Elect Engn, Hangzhou 310027, Zhejiang, Peoples R China
关键词
Unmanned aerial vehicles; photovoltaic farm inspection; convolutional neural network; pattern recognition; PV MODULES; NEURAL-NETWORKS; PERFORMANCE; DEGRADATION; INSPECTION; IMPACT; CNN;
D O I
10.1109/TEC.2018.2873358
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
The efficient condition monitoring and accurate module defect detection in large-scale photovoltaic (PV) farms demand for novel inspection method and analysis tools. This paper presents a deep learning based solution for defect pattern recognition by the use of aerial images obtained from unmanned aerial vehicles. The convolutional neural network is used in the machine learning process to classify various forms of module defects. Such a supervised learning process can extract a range of deep features of operating PV modules. It significantly improves the efficiency and accuracy of asset inspection and health assessment for large-scale PV farms in comparison with the conventional solutions. The proposed algorithmic solution is extensively evaluated from different aspects, and the numerical result clearly demonstrates its effectiveness for efficient defect detection of PV modules.
引用
收藏
页码:520 / 529
页数:10
相关论文
共 50 条
  • [1] Solar photovoltaic module defect detection based on deep learning
    Zhang, Yufei
    Zhang, Xu
    Tu, Dawei
    [J]. MEASUREMENT SCIENCE AND TECHNOLOGY, 2024, 35 (12)
  • [2] Design optimization of large-scale bifacial photovoltaic module frame using deep learning surrogate model
    Han, Dongwoon
    Kim, Seongtak
    [J]. SCIENTIFIC REPORTS, 2024, 14 (01):
  • [3] A Dead Broiler Inspection System for Large-Scale Breeding Farms Based on Deep Learning
    Hao, Hongyun
    Fang, Peng
    Duan, Enze
    Yang, Zhichen
    Wang, Liangju
    Wang, Hongying
    [J]. AGRICULTURE-BASEL, 2022, 12 (08):
  • [4] Deep learning for the large-scale cancer data analysis
    Tsuji, Shingo
    Aburatani, Hiroyuki
    [J]. CANCER RESEARCH, 2015, 75 (22)
  • [5] Deep learning based automatic defect identification of photovoltaic module using electroluminescence images
    Tang, Wuqin
    Yang, Qiang
    Xiong, Kuixiang
    Yan, Wenjun
    [J]. SOLAR ENERGY, 2020, 201 : 453 - 460
  • [6] Large-scale Deep Learning at Baidu
    Yu, Kai
    [J]. PROCEEDINGS OF THE 22ND ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT (CIKM'13), 2013, : 2211 - 2211
  • [7] Aerial image recognition and matching for inspection of large-scale photovoltaic farms
    Wu, Fengjie
    Zhang, Duo
    Li, Xiaoxia
    Luo, Xuejing
    Wang, Jixue
    Yan, Wenjun
    Chen, Zhebo
    Yang, Qiang
    [J]. 2017 INTERNATIONAL SMART CITIES CONFERENCE (ISC2), 2017,
  • [8] Edge-Computing-Enabled Unmanned Module Defect Detection and Diagnosis System for Large-Scale Photovoltaic Plants
    Li, Xiaoxia
    Li, Wei
    Yang, Qiang
    Yan, Wenjun
    Zomaya, Albert Y.
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2020, 7 (10): : 9651 - 9663
  • [9] A Vision-based Inspection Strategy for Large-scale Photovoltaic Farms Using an Autonomous UAV
    Xi, Zhipeng
    Lou, Zhuo
    Sun, Yan
    Li, Xiaoxia
    Yang, Qiang
    Yan, Wenjun
    [J]. 2018 17TH INTERNATIONAL SYMPOSIUM ON DISTRIBUTED COMPUTING AND APPLICATIONS FOR BUSINESS ENGINEERING AND SCIENCE (DCABES), 2018, : 200 - 203
  • [10] Deep Learning-Based Sentimental Analysis for Large-Scale Imbalanced Twitter Data
    Jamal, Nasir
    Chen, Xianqiao
    Aldabbas, Hamza
    [J]. FUTURE INTERNET, 2019, 11 (09)