4.5 Review

A Review on Defect Detection of Electroluminescence-Based Photovoltaic Cell Surface Images Using Computer Vision

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Engineering, Electrical & Electronic

Impact of Solar Cell Cracks Caused During Potential-Induced Degradation (PID) Tests

Mahmoud Dhimish et al.

Summary: Potential-induced degradation (PID) of photovoltaic (PV) modules is a severe type of degradation, where power losses depend on the electric field strength, temperature, humidity, and module materials. Research shows that cracks and fractural defects in solar cells have a significant impact on PID, with a strong relationship between the size of initial defects/cracks and the presence of hotspots. Quality control can help reduce PID in solar cells with minor cracks, providing some reassurance for the longevity of the cells.

IEEE TRANSACTIONS ON ELECTRON DEVICES (2022)

Article Energy & Fuels

Statistical Analysis and Development of an Ensemble-Based Machine Learning Model for Photovoltaic Fault Detection

Muhammad Hussain et al.

Summary: This paper presents a framework for photovoltaic fault detection based on machine learning approaches, and verifies its accuracy and robustness through experiments.

ENERGIES (2022)

Article Chemistry, Analytical

Domain Feature Mapping with YOLOv7 for Automated Edge-Based Pallet Racking Inspections

Muhammad Hussain et al.

Summary: Pallet racking is crucial for warehouses, distribution centers, and manufacturing facilities. Traditional manual inspections for rack damage are time-consuming and prone to human errors, leading to operational downtime and increased costs. To address these challenges, we propose a computer vision-based autonomous rack inspection framework using YOLOv7 architecture, with a mechanism to generate representative data samples. Our framework achieves an average precision of 91.1%.

SENSORS (2022)

Article Chemistry, Physical

A Layer-Wise Surface Deformation Defect Detection by Convolutional Neural Networks in Laser Powder-Bed Fusion Images

Muhammad Ayub Ansari et al.

Summary: This study proposes a novel approach to real-time identification of surface deformation problems from powder-bed images using a convolutional neural network-based solution, which is a significant step towards achieving real-time monitoring in laser powder-bed fusion (LPBF).

MATERIALS (2022)

Article Energy & Fuels

PV-CrackNet Architecture for Filter Induced Augmentation and Micro-Cracks Detection within a Photovoltaic Manufacturing Facility

Muhammad Hussain et al.

Summary: Photovoltaic cell manufacturing involves external pressure and temperature differentials, which can lead to micro-cracks on the cell surface. Experts currently manually inspect the cell surface for micro-cracks. This research proposes a filter-induced augmentation method to overcome the scarcity of cell data and generate representative data samples. The developed custom architecture is computationally lightweight and achieves a 97% F1-score.

ENERGIES (2022)

Article Materials Science, Textiles

CNN-Based Fabric Defect Detection System on Loom Fabric Inspection

Muhammed Fatih Talu et al.

Summary: In this study, a real-time fabric defect detection system based on machine learning and computer vision is proposed. By developing a fast Fourier transform algorithm and a convolutional neural network model, high accuracy defect classification of fabric images is achieved, even on complex textures.

TEKSTIL VE KONFEKSIYON (2022)

Article Engineering, Manufacturing

Moving toward Smart Manufacturing with an Autonomous Pallet Racking Inspection System Based on MobileNetV2

Muhammad Hussain et al.

Summary: Pallet racking plays a crucial role in manufacturing, storage, and distribution centers. Manual inspection is time-consuming and prone to human error. To address this issue, we propose an autonomous racking inspection mechanism using advanced technology, which provides real-time alerts of damage to forklift drivers.

JOURNAL OF MANUFACTURING AND MATERIALS PROCESSING (2022)

Article Computer Science, Information Systems

A Gradient Guided Architecture Coupled With Filter Fused Representations for Micro-Crack Detection in Photovoltaic Cell Surfaces

Muhammad Hussain et al.

Summary: This paper presents a shallow architecture based on Convolutional Neural Networks (CNN) for detecting micro-cracks in photovoltaic cells within the manufacturing environment. The research introduces mechanisms such as gradient guided filter tuning and filter fused data scaling to improve the generation of PV cell images and overall performance.

IEEE ACCESS (2022)

Article Computer Science, Artificial Intelligence

Channel state information estimation for 5G wireless communication systems: recurrent neural networks approach

Mohamed Hassan Essai Ali et al.

Summary: A deep learning BiLSTM recurrent neural network-based channel state information estimator is proposed for 5G systems, showing superior performance with limited pilots and outperforming traditional estimators in symbol error rate and accuracy. Different classification layers, loss functions, and optimization algorithms are used for performance evaluation. The computational and training time complexities of the BiLSTM and LSTM estimators are provided, highlighting the promising potential of the deep learning approach for 5G and beyond communication systems.

PEERJ COMPUTER SCIENCE (2021)

Article Energy & Fuels

Deep learning-based automatic detection of multitype defects in photovoltaic modules and application in real production line

Yang Zhao et al.

Summary: This research presents a deep learning-based automatic detection method for multiple types of defects in PV modules production line, achieving improved efficiency and accuracy in defect detection. The method shows high potential for practical application in real production lines, demonstrating effectiveness in normal/defective module classification.

PROGRESS IN PHOTOVOLTAICS (2021)

Article Computer Science, Artificial Intelligence

Efficient deep feature extraction and classification for identifying defective photovoltaic module cells in Electroluminescence images

Mustafa Yusuf Demirci et al.

Summary: Electroluminescence (EL) imaging is the standard test procedure for defect detection in solar modules, but interpreting EL images can be challenging. Therefore, automatic visual inspection is important for photovoltaic cells. A novel automatic defect detection and classification framework is proposed in this study, utilizing deep learning and classical machine learning techniques.

EXPERT SYSTEMS WITH APPLICATIONS (2021)

Review Green & Sustainable Science & Technology

Potential measurement techniques for photovoltaic module failure diagnosis: A review

Md Momtazur Rahman et al.

Summary: Various characterization methods are used to detect defects in photovoltaic modules, but the results can vary depending on the measuring apparatus and data acquisition system, leading to uncertainties. Identifying and quantifying degraded solar panels promptly can prevent costly module failures. This paper discusses the challenges of solar panel defect detection techniques and reviews conventional and emerging technologies for accurately identifying degradation sources and extending the useful lifetime of PV modules.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2021)

Article Computer Science, Hardware & Architecture

Bactran: A Hardware Batch Normalization Implementation for CNN Training Engine

Yang Zhijie et al.

Summary: In recent years, CNNs have been widely used for training, but the increasing number of parameters makes training challenging with GPUs, prompting researchers to focus on training with more energy-efficient hardware. In a letter, researchers designed an efficient CNN training architecture using systolic arrays and implemented a hardware-friendly BN function, RBN. Experimental results showed that implementing RBN saved hardware resources and reduced power consumption and delay.

IEEE EMBEDDED SYSTEMS LETTERS (2021)

Article Computer Science, Artificial Intelligence

CNN with depthwise separable convolutions and combined kernels for rating prediction

Zahid Younas Khan et al.

Summary: A novel deep learning model, CNN-DSCK, is proposed for rating prediction by utilizing product reviews. This model uses two parallel CNN networks with Depthwise Separable Convolutions to extract features from user and item reviews, select important information through different kernels, pool and concatenate the information, and extract higher-order features through a fully connected layer. Extensive experiments show that CNN-DSCK significantly outperforms state of the art baseline models in real-world datasets.

EXPERT SYSTEMS WITH APPLICATIONS (2021)

Article Engineering, Environmental

Tetrazole modulated perovskite films for efficient solar cells with improved moisture stability

Lisha Xie et al.

Summary: This research utilized 5-(ethylthio)-1H-tetrazole (ETT) to improve the quality of perovskite films, resulting in increased power conversion efficiency and enhanced moisture stability in metal hybrid perovskite solar cells (PSCs).

CHEMICAL ENGINEERING JOURNAL (2021)

Review Computer Science, Artificial Intelligence

A robust weakly supervised learning of deep Conv-Nets for surface defect inspection

Haiyong Chen et al.

NEURAL COMPUTING & APPLICATIONS (2020)

Article Energy & Fuels

Photovoltaic defect classification through thermal infrared imaging using a machine learning approach

Christopher Dunderdale et al.

PROGRESS IN PHOTOVOLTAICS (2020)

Article Engineering, Electrical & Electronic

Automatic hotspots detection based on UAV infrared images for large-scale PV plant

Junfei Nie et al.

ELECTRONICS LETTERS (2020)

Article Automation & Control Systems

Intelligent Classification of Silicon Photovoltaic Cell Defects Based on Eddy Current Thermography and Convolution Neural Network

Bolun Du et al.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2020)

Article Green & Sustainable Science & Technology

Photovoltaic cell defect classification using convolutional neural network and support vector machine

Ashfaq Ahmad et al.

IET RENEWABLE POWER GENERATION (2020)

Article Computer Science, Artificial Intelligence

Visual interaction networks: A novel bio-inspired computational model for image classification

Bing Wei et al.

NEURAL NETWORKS (2020)

Article Computer Science, Information Systems

Overview of Intelligent Online Banking System Based on HERCULES Architecture

Guangsheng Luo et al.

IEEE ACCESS (2020)

Article Engineering, Manufacturing

Development of Novel Solar Cell Micro Crack Detection Technique

Mahmoud Dhimish et al.

IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING (2019)

Review Green & Sustainable Science & Technology

Solar energy: Potential and future prospects

Ehsanul Kabir et al.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2018)

Article Energy & Fuels

Mechanical and electrical properties of wave-shaped wires for low-stress interconnection of solar cells

L. C. Rendler et al.

SOLAR ENERGY MATERIALS AND SOLAR CELLS (2018)

Proceedings Paper Computer Science, Artificial Intelligence

DeepSolarEye: Power Loss Prediction and Weakly Supervised Soiling Localization via Fully Convolutional Networks for Solar Panels

Sachin Mehta et al.

2018 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2018) (2018)

Article Computer Science, Hardware & Architecture

ImageNet Classification with Deep Convolutional Neural Networks

Alex Krizhevsky et al.

COMMUNICATIONS OF THE ACM (2017)

Article Energy & Fuels

Impact of transportation on silicon wafer-based photovoltaic modules

Marc Koentges et al.

PROGRESS IN PHOTOVOLTAICS (2016)

Article Computer Science, Artificial Intelligence

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

Kaiming He et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2015)

Article Chemistry, Physical

Optical Characterization of Different Thin Film Module Technologies

R. Ebner et al.

INTERNATIONAL JOURNAL OF PHOTOENERGY (2015)

Article Energy & Fuels

The reliability of thermography- and luminescence-based series resistance and saturation current density imaging

Otwin Breitenstein et al.

SOLAR ENERGY MATERIALS AND SOLAR CELLS (2015)

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

Passive and Active Thermographic Assessment as a Tool for Condition-Based Performance Monitoring of Photovoltaic Modules

J. A. Tsanakas et al.

JOURNAL OF SOLAR ENERGY ENGINEERING-TRANSACTIONS OF THE ASME (2011)

Article Materials Science, Textiles

Automatic recognition of woven fabric pattern based on image processing and BP neural network

Ruru Pan et al.

JOURNAL OF THE TEXTILE INSTITUTE (2011)

Article Energy & Fuels

The risk of power loss in crystalline silicon based photovoltaic modules due to micro-cracks

M. Koentges et al.

SOLAR ENERGY MATERIALS AND SOLAR CELLS (2011)

Article Physics, Applied

Electroluminescence imaging of organic photovoltaic modules

U. Hoyer et al.

APPLIED PHYSICS LETTERS (2010)

Article Engineering, Electrical & Electronic

Robust Defect Size Measurement Using 3D Modeling for LCD Defect Detection in Automatic Vision Inspection System

Young-Bok Joo et al.

IEICE TRANSACTIONS ON ELECTRONICS (2010)

Article Materials Science, Characterization & Testing

Wall thinning defect estimation using pulsed IR thermography in transmission mode

A. Vageswar et al.

NONDESTRUCTIVE TESTING AND EVALUATION (2010)

Article Energy & Fuels

Detection of the voltage distribution in photovoltaic modules by electroluminescence imaging

Torbert Potthoff et al.

PROGRESS IN PHOTOVOLTAICS (2010)

Article Energy & Fuels

Performance analysis of field exposed single crystalline silicon modules

O. S. Sastry et al.

SOLAR ENERGY MATERIALS AND SOLAR CELLS (2010)

Article Materials Science, Multidisciplinary

Photographic diagnosis of crystalline silicon solar cells utilizing electroluminescence

Takashi Fuyuki et al.

APPLIED PHYSICS A-MATERIALS SCIENCE & PROCESSING (2009)

Review Automation & Control Systems

Computer-vision-based fabric defect detection: A survey

Ajay Kumar

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2008)

Article Engineering, Electrical & Electronic

Robust fabric defect detection and classification using multiple adaptive wavelets

X Yang et al.

IEE PROCEEDINGS-VISION IMAGE AND SIGNAL PROCESSING (2005)

Article Computer Science, Artificial Intelligence

Stochastic texture analysis for monitoring stochastic processes in industry

J Scharcanski

PATTERN RECOGNITION LETTERS (2005)

Article Computer Science, Artificial Intelligence

Optimal Gabor filters for textile flaw detection

A Bodnarova et al.

PATTERN RECOGNITION (2002)

Article Engineering, Multidisciplinary

Defect detection in textured materials using gabor filters

A Kumar et al.

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS (2002)

Article Computer Science, Artificial Intelligence

An automatic assessment scheme for steel quality inspection

K Wiltschi et al.

MACHINE VISION AND APPLICATIONS (2000)

Article Engineering, Multidisciplinary

Fabric defect detection by Fourier analysis

CH Chan et al.

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS (2000)

Article Computer Science, Artificial Intelligence

Fast color texture recognition using chromaticity moments

G Paschos

PATTERN RECOGNITION LETTERS (2000)

Article Computer Science, Artificial Intelligence

A defect detection scheme for web surface inspection

J Iivarinen et al.

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE (2000)