4.6 Review

A review of automated solar photovoltaic defect detection systems: Approaches, challenges, and future orientations

Related references

Note: Only part of the references are listed.
Article Automation & Control Systems

PVEL-AD: A Large-Scale Open-World Dataset for Photovoltaic Cell Anomaly Detection

Binyi Su et al.

Summary: The study creates a dataset for anomaly detection in polycrystalline solar cells and provides ground truth bounding boxes, offering convenience for experimental comparisons and evaluations.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2023)

Article Energy & Fuels

Delafossite as hole transport layer a new pathway for efficient perovskite-based solar sells: Insight from experimental, DFT and numerical analysis

Amal Bouich et al.

Summary: In this study, a successful technique is proposed to produce delafossite materials as Hole Transport Layer (HTL) in inorganic lead halide Perovskite solar cells (PSCs). The effects of M cations, such as Al, Ga, Fe, Cr, Ni, Co, Cr, on the crystal structure, morphology, and optical properties of delafossite CuMO2 were investigated. Experimental and DFT calculations were conducted to analyze the electronic properties of the delafossite layers. Numerical analysis in SCAPS-1D software showed that the HTL delafossite layers achieved the highest power conversion efficiency (PCE%) of 22.90. This research provides a valuable direction for improving the performance of Perovskite-based solar cells (PSCs).

SOLAR ENERGY (2023)

Article Green & Sustainable Science & Technology

Synthetic Dataset of Electroluminescence Images of Photovoltaic Cells by Deep Convolutional Generative Adversarial Networks

Hector Felipe Mateo Romero et al.

Summary: Affordable and clean energy is a Sustainable Development Goal. The increased compliance with SDG and economic crises have led to more investment in solar energy as a renewable generation source. To tackle the complex maintenance of solar plants and the need for advanced artificial intelligence techniques, a model based on Deep Convolutional Generative Adversarial Neural Networks (DCGANs) was trained to generate a synthetic dataset of electroluminescence images of photovoltaic cells. The resulting synthetic dataset showed excellent quality and can be used to improve machine learning algorithms or analyze patterns of solar cell defects.

SUSTAINABILITY (2023)

Article Energy & Fuels

Automated Defect Detection and Localization in Photovoltaic Cells Using Semantic Segmentation of Electroluminescence Images

Joseph Fioresi et al.

Summary: In this article, a deep learning based semantic segmentation model is proposed for identifying and segmenting defects in electroluminescence (EL) images of silicon photovoltaic (PV) cells. The model achieves accurate segmentation of different types of defects and demonstrates high accuracy in extensive testing.

IEEE JOURNAL OF PHOTOVOLTAICS (2022)

Article Energy & Fuels

Automatic Inspection of Photovoltaic Power Plants Using Aerial Infrared Thermography: A Review

Aline Kirsten Vidal de Oliveira et al.

Summary: aIRT has been proven to be a reliable and cost-efficient inspection method for failure detection in PV systems. Current research mainly focuses on autonomous fault detection and classification of PV plants, with accuracies up to 90%, but there are still issues with the accuracy, robustness, and generalization of the algorithms.

ENERGIES (2022)

Article Energy & Fuels

Automated defect identification in electroluminescence images of solar modules*

Xin Chen et al.

Summary: We developed a rapid automatic computer vision pipeline to analyze defects in solar photovoltaic (PV) modules and achieved defect identification using machine learning models. Our methods performed well on real-world validation and testing sets and were applied to analyze the spatial distribution of defects on solar cells in a field survey.

SOLAR ENERGY (2022)

Article Energy & Fuels

Orthogonal modulation based light beam induced current method for anti-noise defect detection in photovoltaic cells

Dongwen Gan et al.

Summary: This paper introduces an orthogonal modulation-based LBIC (OMLBIC) method, which applies orthogonal modulation theory to light beam-induced current (LBIC) scanning for anti-noise defect detection in photovoltaic cells. The proposed method generates orthogonal structured light patterns to illuminate the scanning area surface, measures the combined current output for each pattern, and performs demodulation to extract the signal precisely from the noise. Experimental results demonstrate the potential of the proposed method in improving defect detection accuracy and classification in photovoltaic cells, with increased consistency and reduced sensitivity to noise during scanning.

SOLAR ENERGY (2022)

Article Chemistry, Multidisciplinary

Investigation of the Surface Coating, Humidity Degradation, and Recovery of Perovskite Film Phase for Solar-Cell Applications

Amal Bouich et al.

Summary: This study investigates the effect of organic/inorganic cations on the structure, morphology, and stability of APbI(3) thin films prepared using a one-step solution method. The study aims to understand these properties by incorporating device modeling and chemical composition analysis. The results show that cesium cation leads to a homogeneous, smooth-surfaced, and pinhole-free perovskite film with a large grain size. The optical analysis reveals a band gap range of 1.4 to 1.8 eV for different cations. CsPbI3 exhibits excellent stability for two weeks and in a 60% humid environment. Numerical analysis and experimental results show that CsPbI3 is more stable compared to FAPbI(3) and MAPbI(3), with a smaller loss in PCE.

NANOMATERIALS (2022)

Article Engineering, Electrical & Electronic

Real-time fault detection in PV systems under MPPT using PMU and high-frequency multi-sensor data through online PCA-KDE-based multivariate KL divergence

Azzeddine Bakdi et al.

Summary: This paper discusses real-time adaptive Fault Detection in Grid-connected PV systems under large variations, utilizing an intelligent algorithm developed through real-time multi-sensor measurements and virtual estimations. The algorithm is computationally efficient and accurate, even under noisy measurements and large temperature and irradiance variations.

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS (2021)

Article Automation & Control Systems

Deep Learning-Based Solar-Cell Manufacturing Defect Detection With Complementary Attention Network

Binyi Su et al.

Summary: The article proposes a novel complementary attention network (CAN) that adaptively suppresses background noise features and highlights defect features by utilizing the advantages of channel features and spatial position features. Experimental results show that the proposed method outperforms other methods in defects classification and detection in raw solar cell EL images.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2021)

Article Energy & Fuels

A fault diagnosis method for photovoltaic module current mismatch based on numerical analysis and statistics

Zhixiang Zhang et al.

Summary: This paper investigates current mismatch faults in PV modules caused by partial shading, hot spots, and cracks, proposing a fault diagnostic method that can effectively identify the fault types, with demonstrated strong discriminating power and adaptability in actual case studies.

SOLAR ENERGY (2021)

Review Energy & Fuels

Infrared thermography-based condition monitoring of solar photovoltaic systems: A mini review of recent advances

A. W. Kandeal et al.

Summary: Solar photovoltaic plants are experiencing continuous growth globally, attracting researchers and governments' interest while facing high competition in the market. The utilization of Infrared Thermography (IRTG) has become a widely-used technique for detecting faults in PV plants, providing reliable and accurate results in a safe and non-destructive manner.

SOLAR ENERGY (2021)

Review Chemistry, Multidisciplinary

Surface Defect Detection Methods for Industrial Products: A Review

Yajun Chen et al.

Summary: This paper summarizes the research status of machine learning methods in surface defect detection of industrial products, including the application of traditional machine vision and deep learning technology, key problems and solutions, as well as an overview of commonly used datasets.

APPLIED SCIENCES-BASEL (2021)

Article Energy & Fuels

Drone-Based Daylight Electroluminescence Imaging of PV Modules

Gisele Alves dos Reis Benatto et al.

IEEE JOURNAL OF PHOTOVOLTAICS (2020)

Article Energy & Fuels

Daylight luminescence system for silicon solar panels based on a bias switching method

Miguel Guada et al.

ENERGY SCIENCE & ENGINEERING (2020)

Article Green & Sustainable Science & Technology

Photovoltaic plant condition monitoring using thermal images analysis by convolutional neural network-based structure

Alvaro Huerta Herraiz et al.

RENEWABLE ENERGY (2020)

Proceedings Paper Automation & Control Systems

Defect detection with generative adversarial networks for electroluminescence images of solar cells

Chunhui Shou et al.

2020 35TH YOUTH ACADEMIC ANNUAL CONFERENCE OF CHINESE ASSOCIATION OF AUTOMATION (YAC) (2020)

Article Computer Science, Theory & Methods

A survey on Image Data Augmentation for Deep Learning

Connor Shorten et al.

JOURNAL OF BIG DATA (2019)

Article Engineering, Electrical & Electronic

Generative Adversarial Networks An overview

Antonia Creswell et al.

IEEE SIGNAL PROCESSING MAGAZINE (2018)

Article Engineering, Electrical & Electronic

An Irradiance-Independent, Robust Ground-Fault Detection Scheme for PV Arrays Based on Spread Spectrum Time-Domain Reflectometry (SSTDR)

Sourov Roy et al.

IEEE TRANSACTIONS ON POWER ELECTRONICS (2018)

Review Green & Sustainable Science & Technology

Fault detection and monitoring systems for photovoltaic installations: A review

Asma Triki-Lahiani et al.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2018)

Review Green & Sustainable Science & Technology

Fault detection and diagnosis methods for photovoltaic systems: A review

A. Mellit et al.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2018)

Review Green & Sustainable Science & Technology

A comprehensive review on protection challenges and fault diagnosis in PV systems

Dhanup S. Pillai et al.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2018)

Article Engineering, Electrical & Electronic

Fault Detection for Photovoltaic Systems Based on Multi-Resolution Signal Decomposition and Fuzzy Inference Systems

Zhehan Yi et al.

IEEE TRANSACTIONS ON SMART GRID (2017)

Article Construction & Building Technology

Deep Convolutional Neural Networks with transfer learning for computer vision-based data-driven pavement distress detection

Kasthurirangan Gopalakrishnan et al.

CONSTRUCTION AND BUILDING MATERIALS (2017)

Article Materials Science, Characterization & Testing

Detection and characterisation of delamination in PV modules by active infrared thermography

A. Sinha et al.

NONDESTRUCTIVE TESTING AND EVALUATION (2016)

Article Engineering, Electrical & Electronic

Fault Diagnosis of Photovoltaic Panels Using Dynamic Current-Voltage Characteristics

Wenguan Wang et al.

IEEE TRANSACTIONS ON POWER ELECTRONICS (2016)

Review Green & Sustainable Science & Technology

Faults and infrared thermographic diagnosis in operating c-Si photovoltaic modules: A review of research and future challenges

John A. Tsanakas et al.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2016)

Article Computer Science, Interdisciplinary Applications

Artificial neural network-based modelling and fault detection of partial shaded photovoltaic modules

H. Mekki et al.

SIMULATION MODELLING PRACTICE AND THEORY (2016)

Article Energy & Fuels

Fault detection algorithm for grid-connected photovoltaic plants

Mahmoud Dhimish et al.

SOLAR ENERGY (2016)

Proceedings Paper Engineering, Electrical & Electronic

Hot Spots Detection of Operating PV Arrays through IR Thermal Image Using Method Based on Curve Fitting of Gray Histogram

Jiang Lin et al.

INTERNATIONAL SEMINAR ON APPLIED PHYSICS, OPTOELECTRONICS AND PHOTONICS (APOP 2016) (2016)

Article Materials Science, Characterization & Testing

Optimization of pulsed thermography inspection by partial least-squares regression

Fernando Lopez et al.

NDT & E INTERNATIONAL (2014)

Article Engineering, Electrical & Electronic

Micro-crack detection of multicrystalline solar cells featuring an improved anisotropic diffusion filter and image segmentation technique

Said Amirul Anwar et al.

EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING (2014)

Article Thermodynamics

Automatic fault diagnosis in PV systems with distributed MPPT

J. Solorzano et al.

ENERGY CONVERSION AND MANAGEMENT (2013)

Article Automation & Control Systems

Defect Detection in Solar Modules Using ICA Basis Images

Du-Ming Tsai et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2013)

Article Energy & Fuels

Defect detection of solar cells in electroluminescence images using Fourier image reconstruction

Du-Ming Tsai et al.

SOLAR ENERGY MATERIALS AND SOLAR CELLS (2012)

Article Energy & Fuels

Experimental studies of fault location in PV module strings

Takumi Takashima et al.

SOLAR ENERGY MATERIALS AND SOLAR CELLS (2009)

Article Energy & Fuels

Disconnection Detection Using Earth Capacitance Measurement in Photovoltaic Module String

Takumi Takashima et al.

PROGRESS IN PHOTOVOLTAICS (2008)