Special Sessions

The following special sessions will take place in the frame of the IGTE symposium: 

• Magnetic Losses in Laminated Cores (SpS 1), chaired by Christophe Geuzaine and Manfred Kaltenbacher

  
  The special session on magnetic losses in laminated cores brings together researchers and engineers to explore advanced modelling, simulation, and practical applications. The focus is on understanding how hysteresis, eddy currents, and excess losses develop within laminated magnetic materials under varying operating conditions. Contributions will focus on state-of-the-art computational methods that accurately capture nonlinear magnetic behavior and frequency-dependent effects. Overall, the session emphasizes the critical role of advanced modelling tools in bridging theory and real-world applications. By combining simulation with experimental validation, researchers aim to develop more efficient and sustainable electromagnetic devices such as electromagnetic motors and transformers.

   

• Machine Learning-Based Methods for Modeling, Optimization and Inverse Problems in Electromagnetics (SpS 2), chaired by Sami Barmada and Alice Reinbacher-Köstinger

  
  Machine Learning (ML) is rapidly entering the world computational electromagnetics with the goals of enabling efficient modeling, accelerating simulations, and improving the solution of complex inverse problems. By integrating data-driven approaches with physics-based formulations, ML based methods are expected to offer enhanced performance in high-dimensional, nonlinear, and ill-posed scenarios. This special session invites contributions on recent advances in this exciting research topic joining electromagnetics and ML, including deep learning, physics-informed neural networks, surrogate modeling, and hybrid approaches for forward modeling, design optimization.

  Topics of interest include:

  • ML-based forward and surrogate modeling
  • Physics-informed neural netowrks and hybrid methods
  • Imaging and parameter reconstruction using ML technique
  • ML-based design and optimization of electromagnetic systems
  • Integration with numerical methods (FEM, FDTD, MoM)
  • Applications in electromechanical devices, high frequency devices, sensing, biomedical imaging