THE USE OF AI / MACHINE LEARNING IN PREDICTIVE MAINTENANCE OF ELECTRICAL POWER TRANSMISSION LINES
Faculty
Year of Publication
Publication Type
Abstract
This research explores the application of Artificial Intelligence (AI) and Machine Learning (ML) for the predictive maintenance of transmission lines, specifically targeting fault detection, failure prediction, and maintenance optimization.
Synthetic data was used to simulate parameters such as current, voltage, and temperature. Data preprocessing techniques, including cleaning and normalization, were performed. A supervised learning approach, the Random Forest Classifier, was
applied using Python to mimic real-world fault scenarios. Model performance was evaluated using standard metrics: accuracy, precision, recall, and F1-score.The findings demonstrate that AI-based predictive maintenance has the potential to improve power system reliability and efficiency by reducing downtime and optimizing maintenance scheduling. The study also addresses key challenges, such as data availability and model generalization, proposing solutions like data augmentation and
hybrid model design. Ultimately, this research provides a framework for developing scalable, data-driven predictive maintenance systems, advancing smart grid technologies and sustainable power system management
Synthetic data was used to simulate parameters such as current, voltage, and temperature. Data preprocessing techniques, including cleaning and normalization, were performed. A supervised learning approach, the Random Forest Classifier, was
applied using Python to mimic real-world fault scenarios. Model performance was evaluated using standard metrics: accuracy, precision, recall, and F1-score.The findings demonstrate that AI-based predictive maintenance has the potential to improve power system reliability and efficiency by reducing downtime and optimizing maintenance scheduling. The study also addresses key challenges, such as data availability and model generalization, proposing solutions like data augmentation and
hybrid model design. Ultimately, this research provides a framework for developing scalable, data-driven predictive maintenance systems, advancing smart grid technologies and sustainable power system management
Supervisor(s)
co-supervisor