Failures of Photovoltaic modules and their Detection: A Review

Akram, Muhammad Waqar; Li, Guiqiang; Jin, Yi; Chen, Xiao

doi:10.1016/j.apenergy.2022.118822

Cited by 65 publications

(11 citation statements)

References 149 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is time-consuming and costly [4,6]. In addition, the exact location of the fault is not provided, as current and voltage sensors have a limited ability to pinpoint the cause of the power loss [3,7,8]. The second group is based on measurements of emitted or reflected radiation with cameras.…”

Section: Introductionmentioning

confidence: 99%

A review of imaging methods for detection of photoluminescence in field-installed photovoltaic modules

Vuković,

Wiig,

dos Reis Benatto

et al. 2024

Prog. Energy

View full text Add to dashboard Cite

It is predicted that the photovoltaic energy conversion will be the largest installed power capacity by 2027. The least costly option for new electricity generation in many of the world’s countries will be the utility-scale solar photovoltaic electricity generation. Accurate monitoring of solar plants for localizing and detecting faults is expected to be one of the critical tasks facing the energy industry. Imaging of photovoltaic modules for the purpose of fault detection can be more efficient and accurate compared to measurements of electrical parameters. Different spectral regions provide different types of information about a faulty module. Detection of photoluminescence, that is, radiation emitted upon band-to-band recombination after charge carrier excitation with an illumination source, has shown a great potential in the laboratory setting. In the recent years, the first approaches in the outdoor setting have been conducted on silicon modules with the Sun and a LED module as excitation source. The present study sums up the different methods for outdoor photoluminescence imaging and emphasizes their differences regarding filtering of the reflected light from the photoluminescence signal. The different types of photoluminescence images obtained from each method and the image processing algorithms are described. Finally, the interpretation of the different types of photoluminescence images is addressed.

show abstract

Section: Introductionmentioning

confidence: 99%

A review of imaging methods for detection of photoluminescence in field-installed photovoltaic modules

Vuković,

Wiig,

dos Reis Benatto

et al. 2024

Prog. Energy

View full text Add to dashboard Cite

show abstract

“…On the other hand, there are several factors that can cause variations in the electrical characteristics of PV modules, such as partial shading [19] and short-circuited bypass diodes [20] . When a low-current PV cell is present in a string of high short-circuit current PV cells, the forward bias across all the cells can reverse bias the shaded cell.…”

Section: Introductionmentioning

confidence: 99%

Detection and analysis of deteriorated areas in solar PV modules using unsupervised sensing algorithms and 3D augmented reality

Oulefki,

Himeur,

Trongtirakul

et al. 2024

Heliyon

View full text Add to dashboard Cite

“…With the development of artificial intelligence, the intelligent detection of PV panel faults is becoming a feasible and promising solution. Using machine vision techniques to identify surface defects in PV panels has become an essential technical basis for building intelligent PV inspection systems [4,5]. Inspired by the success of deep learning in data mining [6][7][8], computer vision [5,[9][10][11][12][13][14][15][16][17] and speech processing [18][19][20][21][22][23][24][25][26], deep learning techniques can significantly improve detection efficiency, provide solutions for the competent inspection of PV power plants, and guide power plants' operation and maintenance procedures [11,27].…”

Section: Introductionmentioning

confidence: 99%

GBH-YOLOv5: Ghost Convolution with BottleneckCSP and Tiny Target Prediction Head Incorporating YOLOv5 for PV Panel Defect Detection

Wang

Zhang

2023

Electronics

View full text Add to dashboard Cite

Photovoltaic (PV) panel surface-defect detection technology is crucial for the PV industry to perform smart maintenance. Using computer vision technology to detect PV panel surface defects can ensure better accuracy while reducing the workload of traditional worker field inspections. However, multiple tiny defects on the PV panel surface and the high similarity between different defects make it challenging to accurately identify and detect such defects. This paper proposes an approach named Ghost convolution with BottleneckCSP and a tiny target prediction head incorporating YOLOv5 (GBH-YOLOv5) for PV panel defect detection. To ensure better accuracy on multiscale targets, the BottleneckCSP module is introduced to add a prediction head for tiny target detection to alleviate tiny defect misses, using Ghost convolution to improve the model inference speed and reduce the number of parameters. First, the original image is compressed and cropped to enlarge the defect size physically. Then, the processed images are input into GBH-YOLOv5, and the depth features are extracted through network processing based on Ghost convolution, the application of the BottleneckCSP module, and the prediction head of tiny targets. Finally, the extracted features are classified by a Feature Pyramid Network (FPN) and a Path Aggregation Network (PAN) structure. Meanwhile, we compare our method with state-of-the-art methods to verify the effectiveness of the proposed method. The proposed PV panel surface-defect detection network improves the mAP performance by at least 27.8%.

show abstract

Failures of Photovoltaic modules and their Detection: A Review

Cited by 65 publications

References 149 publications

A review of imaging methods for detection of photoluminescence in field-installed photovoltaic modules

A review of imaging methods for detection of photoluminescence in field-installed photovoltaic modules

Detection and analysis of deteriorated areas in solar PV modules using unsupervised sensing algorithms and 3D augmented reality

GBH-YOLOv5: Ghost Convolution with BottleneckCSP and Tiny Target Prediction Head Incorporating YOLOv5 for PV Panel Defect Detection

Contact Info

Product

Resources

About