AI-Driven Defect Analysis in Photovoltaic Systems: Enhancing PV Efficiency through Ultraviolet Fluorescence Inspection

This PhD project aims to revolutionize the maintenance and efficiency of photovoltaic (PV) systems by developing advanced machine learning (ML) and artificial intelligence (AI) methodologies to analyze and predict defects using ultraviolet fluorescence (UVF) inspection technology. The project seeks to improve the detection and classification of micro-level defects that traditional inspection methods often overlook.

Objectives:

Develop Advanced AI Models: To create and train deep learning algorithms that can accurately identify, classify, and predict the occurrence of defects in PV panels using data captured by UVF inspection.

Data Acquisition and Analysis: To implement a comprehensive data collection strategy using UVF technology that captures a wide range of defect signatures, which will serve as the training set for the AI models.

Enhancement of UVF Technology: To refine UVF imaging techniques to increase the resolution and sensitivity of defect detection, tailored specifically for integration with AI analytical tools.

Real-World Testing and Validation: To deploy the developed models in real-world settings to validate and refine the approach, ensuring it can handle various environmental conditions and different types of PV technologies.

Sustainability Impact Assessment: To evaluate the potential impacts of implementing such advanced defect detection technology on the overall sustainability and efficiency of solar energy systems.

Expected Outcomes and Significance:

This PhD project is expected to yield a sophisticated AI platform capable of real-time, accurate defect detection and diagnosis in photovoltaic (PV) systems. By integrating machine learning with enhanced ultraviolet fluorescence (UVF) imaging technology, the platform will lead to significantly reduced maintenance costs and improved efficiency of PV panels. Additionally, the project will advance UVF technology, establishing it as a vital tool for comprehensive health monitoring of PV systems. The significance of this research lies in its potential to extend the operational lifespan and optimize the performance of solar energy systems, thereby supporting more sustainable energy practices worldwide. This project not only contributes to the scientific and technological advancements in renewable energy but also aligns with global efforts to enhance energy security and reduce carbon footprints through smarter, AI-driven solutions.

This project is open-ended making it suitable for MSc by Research and PhD level.

How to Apply:

The potential candidate must hold a previous degree and have experience in Electrical, Electronics, or Communications Engineering, Computer Science, Physics, or a related field. Candidates with practical experience in AI or machine learning are particularly encouraged to apply.

Applicants should apply via the University’s online application system at https://www.york.ac.uk/study/postgraduate-research/apply/. Please read the application guidance first so that you understand the various steps in the application process.