Bibliometric Analysis of Emerging Trends and Future Directions in AI-Driven Fault Diagnosis for Photovoltaic Systems Using Advanced Image Processing Techniques

Traditional fault detection methods in photovoltaic systems face limitations when handling emerging monitoring systems that generate vast amounts of high-dimensional data across various domains. Consequently, there is growing interest in the international scientific community in applying artificial intelligence (AI) methods, which offer a promising solution for effectively managing large datasets and detecting faults. This paper aims to assess the current state of AI-based fault diagnosis in photovoltaic systems through a bibliometric analysis. A total of 439 papers published between 2008 and March 2025 were analyzed using data from the Web of Science. The study identifies key trends, influential authors, leading journals and countries, prominent citations, collaborative networks, and keyword co-occurrence that shape the field. Overall, the most recurring topics in AI-based fault diagnosis for photovoltaic systems have been identified, offering insights into future research directions. These include the integration of advanced machine learning models, real-time monitoring techniques, predictive maintenance strategies, and the optimization of fault detection algorithms.