Magnetic-field Sensing and Machine Learning Based Fault Detection and Diagnosis in Renewable Energy Systems
In this seminar, Dr. Wenchao Miao will present his research on fault detection and diagnostic techniques for renewable energy systems with a focus on DC arc faults, while providing an overview of high-frequency current sensing, and battery health monitoring. As renewable energy systems, including photovoltaic (PV) systems and DC microgrids, continue to grow in complexity and scale, ensuring their reliability and safety is essential. This seminar will introduce magnetic-field sensing and machine-learning solutions to some of the most challenging issues in these systems to support safer and more efficient energy management.
DC Arc Fault Detection: The seminar will explore the development of a multi-characteristic arc model and a non-invasive detection technique based on Magnetoresistance (MR) sensors, which significantly enhance the accuracy and speed of DC arc fault detection in PV systems and microgrids. This work addresses a critical risk in DC power systems that can lead to fires and equipment damage.
High-Frequency Current Sensing: With the rise of wide bandgap devices in power electronics, high-frequency current sensing has become increasingly important. The seminar will share his research on using MR sensors to improve current sensing accuracy at higher frequencies, extending bandwidth to meet the demands of next-generation power systems.
Battery Health Monitoring: As lithium-ion batteries play a central role in energy storage, accurate monitoring of their health is essential for long-term system reliability. The seminar will discuss the innovative approach to battery health diagnostics using MR sensors and machine learning, offering a non-invasive, high-precision method to assess the state of health of batteries, which could help prevent failures and extend their lifespan.
A mock lecture on Artificial Neural Network (ANN).
1. Introduction of ANN
2. Perceptron
3. MATLAB Demonstration
Wenchao Miao received a B.Eng. degree from the University of Nottingham, Nottingham, U.K., in 2014, an M.Sc. degree from The University of Manchester, Manchester, U.K., in 2016, and a Ph.D. degree in electrical and electronic engineering from The University of Hong Kong, Hong Kong, in 2020.
He is currently a Lecturer at the School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China. He was selected in the Shanghai Leading Talents (Overseas) Project in 2022. His current research interests include condition monitoring and fault detection in both the system (electrical faults) and equipment levels of photovoltaic systems and DC microgrids.