Principle Organizer:

Name: Zaixin Song

Email: zaixin.song@polyu.edu.hk

Affiliations: The Hong Kong Polytechnic University, Hong Kong

Co-Organizer 1:

Name: Chunhua Liu

Email: chunliu@cityu.edu.hk

Affiliations: City University of Hong Kong, Hong Kong

Co-Organizer 2:

Name: Tao Yang

Email: tao.yang@nottingham.ac.uk

Affiliations: University of Nottingham, U.K.

Co-Organizer 3:

Name: Senyi Liu

Email: senyiliu2-c@my.cityu.edu.hk

Affiliations: City University of Hong Kong, Hong Kong

Theme:

There is a promising trend that machine learning techniques are being used in the field of electrical engineering. In particularly, the design, control of electric machines and power electronics benefit from emerging machine learning techniques for a higher level of performance and reliability. By predicting the performance characteristics of different machine schemes, the most efficient and cost-effective design options can be shortlisted. By setting the coupling electromechanical model to training and computation, more complex drive topologies and control algorithms become accessible. By predefined and trained models, the real-time implementation and stability of power converters can be greatly enhanced. In short, the aim of this special session is to highlight the most recent techniques involving machine learning for electric machine design, motor control, and power electronics. Any contribution in this technical field is welcomed in this special session.