<p>This paper introduces an advanced automated classification system for detecting abnormalities in photovoltaic materials using Optical Coherence Tomography (OCT), hyperspectral imaging, and quantitative phase analysis. Solar cells are crucial in renewable energy generation, requiring robust diagnostic tools to ensure their efficiency and longevity. OCT, initially developed for medical imaging, provides high-resolution cross-sectional imaging and has been adapted for material science applications. In this study, we leverage OCT to examine the internal structures of solar cells, identifying defects and abnormalities that impact performance. Our proposed system integrates OCT with hyperspectral imaging to analyze the optical properties of photovoltaic materials across a range of wavelengths. Quantitative phase analysis further enhances detection by assessing phase differences within the materials. Compared to traditional methods such as I–V characterization, our approach offers non-invasive, real-time imaging with the capability to analyze material properties at different depths. Validation against the gold standard I–V characterization demonstrates the system’s accuracy in detecting and distinguishing between normal and abnormal photovoltaic regions. The findings highlight the system’s potential to enhance early detection, improve maintenance strategies, and optimize solar cell performance. By offering objective and consistent results, this automated classification system represents a significant advancement in renewable energy technology, paving the way for enhanced quality control and sustainable energy solutions.</p>