Role of Artificial Intelligence aided Inspection Methods for Sustainable Periodic Maintenance and Renovation of Renewable Energy Systems Project

Abstract

This thesis explores the integration of Artificial Intelligence (AI) to enhance the performance, maintenance, and sustainability of renewable energy projects. The primary objectives are to identify AI methods and techniques for detecting defects, faults, and anomalies in renewable energy systems; analyze AI's role in contributing to the longevity and sustainability of these projects through predictive maintenance and optimized operations; and provide insights into the most suitable AI algorithms for detecting defects in renewable energy equipment.

A systematic literature review was conducted, categorized into sections focusing on general renewable energy, AI, wind energy, solar energy, hydropower energy, and combined wind/solar energy sectors.

The findings reveal that AI-supported inspection processes significantly contribute to the sustainability and longevity of renewable energy projects. Techniques such as computer vision, machine learning, anomaly detection, time series analysis, and reinforcement learning were found effective in diagnosing faults and optimizing system operations. The research concludes that AI-supported inspection processes enhance the longevity and efficiency of renewable energy systems by providing proactive, data-driven maintenance solutions.