A Comprehensive Case Study on the Performance of Machine Learning Methods on the Classification of Solar Panel Electroluminescence Images

TL;DR

This study compares traditional machine learning and deep learning models for classifying solar cell electroluminescence images, addressing challenges of data imbalance and providing practical guidelines for model selection and evaluation.

Contribution

It offers a comprehensive comparison of ML and DL methods for EL image classification, including insights on metrics and handling class imbalance, which was lacking in prior research.

Findings

Deep learning models generally outperform traditional ML methods.

Class imbalance significantly affects model performance and metric selection.

Guidelines are provided for practitioners on choosing models and evaluation metrics.

Abstract

Photovoltaics (PV) are widely used to harvest solar energy, an important form of renewable energy. Photovoltaic arrays consist of multiple solar panels constructed from solar cells. Solar cells in the field are vulnerable to various defects, and electroluminescence (EL) imaging provides effective and non-destructive diagnostics to detect those defects. We use multiple traditional machine learning and modern deep learning models to classify EL solar cell images into different functional/defective categories. Because of the asymmetry in the number of functional vs. defective cells, an imbalanced label problem arises in the EL image data. The current literature lacks insights on which methods and metrics to use for model training and prediction. In this paper, we comprehensively compare different machine learning and deep learning methods under different performance metrics on the classification of solar cell EL images from monocrystalline and polycrystalline modules. We provide a comprehensive discussion on different metrics. Our results provide insights and guidelines for practitioners in selecting prediction methods and performance metrics.