Deep learning based Meta-modeling for Multi-objective Technology Optimization of Electrical Machines
This addresses the problem of separate optimization for different machine technologies in electrical engineering, offering a concurrent approach, though it appears incremental as it builds on existing VAE and deep learning methods.
The paper tackles the time- and computationally expensive optimization of rotating electrical machines by applying a variational auto-encoder (VAE) to simultaneously optimize asynchronous and permanent magnet synchronous machines, using meta-models to predict key performance indicators and generate new designs through a unified latent space.
Optimization of rotating electrical machines is both time- and computationally expensive. Because of the different parametrization, design optimization is commonly executed separately for each machine technology. In this paper, we present the application of a variational auto-encoder (VAE) to optimize two different machine technologies simultaneously, namely an asynchronous machine and a permanent magnet synchronous machine. After training, we employ a deep neural network and a decoder as meta-models to predict global key performance indicators (KPIs) and generate associated new designs, respectively, through unified latent space in the optimization loop. Numerical results demonstrate concurrent parametric multi-objective technology optimization in the high-dimensional design space. The VAE-based approach is quantitatively compared to a classical deep learning-based direct approach for KPIs prediction.