Speaker:

Dr. Md Shafiullah

Assistant Professor

Control and Instrumentation Engineering Department

College of Engineering and Physics

King Fahd University of Petroleum and Minerals

Abstract

Asset management through predictive maintenance is crucial for minimizing costs, maximizing equipment reliability, improving safety, extending asset life span, optimizing maintenance schedules, and optimizing overall operational efficiency. It is a valuable strategy for critical industries like power system networks as it aligns maintenance activities with actual asset conditions, fostering a proactive and data-driven approach to maintenance management. Various components within the electric power system (EPS) grids, including transformers, generators, wind turbines, transmission lines, and underground cables, can be benefited through predictive maintenance to ensure reliability, prevent unexpected failures, and minimize downtime. The use of advanced artificial intelligence (AI) strategies, including machine learning and deep learning approaches, has increased significantly for predictive maintenance due to their tremendous capability to make more accurate predictions by analyzing complex patterns in large datasets. The AI strategies analyze historical data, sensor information, and operational parameters to create predictive models to predict equipment failures based on patterns and anomalies. This seminar will investigate state-of-the-art intelligent strategies for predictive maintenance of the power system components (renewable energy plants). Then, we will discuss and analyze the data acquired for the development of the intelligent frameworks for predictive maintenance. Finally, the obtained results using the developed model will be presented.

Speaker Bio

Dr. Md Shafiullah is a renowned expert in energy and control systems, with over 15 years of experience, and is keen to strive for excellence in energy transition through education, research, development, and innovation initiatives. He is highly motivated to create societal and environmental impacts through innovative projects in the field of controlling and automating electrical power and energy systems. His research interests include intelligent management of energy systems, fault diagnosis in electric power grids, asset management, power system control and stability, evolutionary algorithms, and machine learning techniques. He published more than 200 research articles (journals, conference proceedings, books, and book chapters) in renowned scientific outlets and publishers, including Elsevier, Springer, Wiley, IEEE, etc. He was ranked among the world's top 2% scientists in 2023, 2024, and 2025. He is also the recipient of numerous awards, including the Early Career Research Award and Best Paper and Best Poster Awards from distinguished national and international entities. Since September 2023, he has been working as an Assistant Professor in the Control & Instrumentation Engineering Department and a research scholar in the Interdisciplinary Research Center for Sustainable Energy Systems, both at the King Fahd University of Petroleum & Minerals (KFUPM), Dhahran, Saudi Arabia.