Variational Autoencoder based Metamodeling for Multi-Objective Topology Optimization of Electrical Machines

TL;DR

This paper introduces a variational autoencoder-based metamodeling approach that enables efficient multi-objective topology optimization of electrical machines by predicting key performance indicators across different designs simultaneously.

Contribution

It presents a novel variational autoencoder framework that maps high-dimensional design parameters into a lower-dimensional space for concurrent multi-topology optimization.

Findings

Reduces computational time for electrical machine design analysis.

Enables simultaneous prediction of KPIs for multiple topologies.

Facilitates efficient parameter-based optimization across different designs.

Abstract

Conventional magneto-static finite element analysis of electrical machine design is time-consuming and computationally expensive. Since each machine topology has a distinct set of parameters, design optimization is commonly performed independently. This paper presents a novel method for predicting Key Performance Indicators (KPIs) of differently parameterized electrical machine topologies at the same time by mapping a high dimensional integrated design parameters in a lower dimensional latent space using a variational autoencoder. After training, via a latent space, the decoder and multi-layer neural network will function as meta-models for sampling new designs and predicting associated KPIs, respectively. This enables parameter-based concurrent multi-topology optimization.