AI system catches solar panel defects faster than human inspectors
Researchers have developed an automated system using deep learning to spot defective solar cells in manufacturing with high accuracy. The breakthrough could cut inspection costs and improve quality control across the solar industry, which loses billions annually to undetected manufacturing flaws that reduce panel performance.
Originaltitel: Benchmarking Modern Deep Learning Models for Electroluminescence-Based Solar Cell Defect Detection.
Automatiserad bildanalys kan skärpa kvalitetskontrollen i solcellsproduktion och minska utrangeringsgraden genom snabbare feldetektering. Forskare vid Utrecht University och turkiska universitet har testat fyra neurala nätverk för klassificering av solceller via elektroluminescensbildning – en etablerad inspektionsmetod som avslöjar sprickor och brutna celler. EfficientNet-B2 nådde högst noggrannhet med 99,31 procent på ett balanserat testset om 20 400 bilder. MaxViT-T presterade jämförbar precision med snabbare konvergenstid. Samtliga fyra arkitekturer översteg 98 procents noggrannhet, vilket indikerar att djup inlärning är tillförlitlig för denna klassificeringsuppgift. Resultaten är relevanta för solcellstillverkare som söker kostnadseffektiv automatisering och för investerare som värderar tillverkningskvalitet. Nästa steg är att verifiera modellerna i verklig produktionsmiljö och bedöma implementeringskostnader.
This study proposes a deep learning-based framework for the automated classification of photovoltaic solar cells as defective or normal using electroluminescence (EL) imaging. A balanced dataset containing 20,400 EL images, comprising 10,200 defective and 10,200 normal solar cells, was used for model development and evaluation. To reflect practical inspection requirements, cracked and broken cells were combined into a single defective category, resulting in a binary classification task. The dataset includes both monocrystalline and polycrystalline solar cells, which were analyzed together within a unified classification framework to improve applicability to real-world photovoltaic systems. To ensure a fair and unbiased evaluation, dataset partitioning was performed prior to any preprocessing or augmentation operations, and each image was assigned exclusively to the training, validation, or test subset. Data augmentation was applied only to the training set, eliminating the possibility of data leakage. Four state-of-the-art deep learning architectures, EfficientNet-B2, ConvNeXt-Tiny, MaxViT-T, and ResNet-50, were trained and evaluated under identical experimental conditions using the same preprocessing pipeline, training strategy, and dataset split. Model performance was assessed using accuracy, precision, recall, F1-score, ROC-AUC, confusion matrices, and explainability-based activation and attention heat maps. All evaluated models achieved classification accuracies exceeding 98%, demonstrating strong capability for EL-based defect detection. EfficientNet-B2 achieved the highest numerical performance, reaching 99.31% accuracy, 0.9931 F1-score, and 0.9987 ROC-AUC. MaxViT-T exhibited similarly strong performance with rapid convergence and balanced class-wise metrics, while ConvNeXt-Tiny and ResNet-50 also produced highly reliable results. Heat map visualizations revealed that EfficientNet-B2 and MaxViT-T concentrated their attention more precisely on defect regions such as cracks and fractures, providing visual interpretability in addition to quantitative performance. The results demonstrate that modern deep learning architectures can accurately and reliably detect photovoltaic cell defects from EL images under a unified binary classification framework. Furthermore, explainability techniques enhance the transparency of model predictions, supporting the practical deployment of intelligent inspection systems for photovoltaic manufacturing and maintenance applications.