Cognition-Driven Approach to Electromagnetic Modeling and Optimization
Significant advances in computational electromagnetics have led to the wide spread use of electromagnetic simulations in high-frequency electronic design. Fairly complex electromagnetic structures can be simulated nowadays with impressive speed and accuracy. However, practical design process requires repetitive adjustments of physical and geometrical parameters of the electromagnetic structure. This becomes computationally very expensive because the electromagnetic simulations have to be repetitively performed. To address these challenges, artificial neural networks and space mapping have been used in the microwave CAD community, significantly speeding up electromagnetic modeling and optimization while retaining the electromagnetic level accuracy. This talk presents recent advances in this area. Knowledge-based neural networks combining empirical and equivalent models are being developed, enabling robust modeling and faster training. Cognition-driven approaches to electromagnetic optimization incorporating engineer's intuition into design formulation are described increasing optimization efficiency and alleviating the long-standing problem of solutions being trapped in local minimum during electromagnetic optimization.
Qijun Zhang received the B.Eng. degree from the Nanjing University of Science and Technology, Nanjing, China in 1982, and the Ph.D. Degree in Electrical Engineering from McMaster University, Hamilton, Canada, in 1987. He was a research engineer with Optimization Systems Associates Inc., Dundas, Ontario, Canada during 1988-1990 developing advanced optimization software for microwave modeling and design. He joined the Department of Electronics, Carleton University, Ottawa, Canada in 1990 where he is presently a Chancellor's Professor. Dr. Zhang is also an adjunct Professor with the School of Microelectronics, Tianjin University. His research interests are modeling, optimization and neural networks for high-speed/high-frequency electronic design, and has over 290 publications in the area. He is an author of the book Neural Networks for RF and Microwave Design (Boston: Artech House, 2000), a coeditor of Modeling and Simulation of High-Speed VLSI Interconnects (Boston: Kluwer, 1994), and a coeditor of Simulation-Driven Design Optimization and Modeling for Microwave Engineering (London, UK: Imperial College Press, 2013). Dr. Zhang is a Fellow of the IEEE, and a Fellow of the Canadian Academy of Engineering. He is on the editorial board of the IEEE Transactions on Microwave Theory and Techniques, and the International Journal of Numerical Modeling. He is an Associate Editor for the International Journal of RF and Microwave Computer-Aided Engineering. He is the Co-Chair of the Technical Committee on CAD (MTT-1) of the IEEE Microwave Theory and Techniques (MTT) Society, and a founding Chair of the Executive Committee of the IEEE MTT Society's annual international conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization