A Fast Learning-Based Surrogate of Electrical Machines using a Reduced Basis

TL;DR

This paper introduces a real-time, learning-based surrogate model for parameterized PDEs in electrical machines, combining Proper Orthogonal Decomposition and Support Vector Regression to enable interactive analysis in digital twin applications.

Contribution

A novel hybrid method integrating Proper Orthogonal Decomposition with Support Vector Regression for fast, real-time surrogates of complex electrical machine simulations.

Findings

Effective in real-time analysis of electrical machine models

Handles non-linearities and complex geometries

Demonstrates industrial applicability

Abstract

A surrogate model approximates the outputs of a solver of Partial Differential Equations (PDEs) with a low computational cost. In this article, we propose a method to build learning-based surrogates in the context of parameterized PDEs, which are PDEs that depend on a set of parameters but are also temporal and spatial processes. Our contribution is a method hybridizing the Proper Orthogonal Decomposition and several Support Vector Regression machines. This method is conceived to work in real-time, thus aimed for being used in the context of digital twins, where a user can perform an interactive analysis of results based on the proposed surrogate. We present promising results on two use cases concerning electrical machines. These use cases are not toy examples but are produced an industrial computational code, they use meshes representing non-trivial geometries and contain non-linearities.