Enhancing Multi-Objective Optimization through Machine Learning-Supported Multiphysics Simulation

TL;DR

This paper introduces a framework that uses machine learning surrogate models to accelerate multi-objective optimization in multiphysics simulations, demonstrating high accuracy and efficiency with real-world datasets.

Contribution

It presents a novel methodology for training self-optimizing surrogate models that significantly reduce simulation costs in multi-objective optimization tasks.

Findings

Surrogate models trained on small datasets accurately approximate simulations.

Explainable AI techniques identify key features and dependencies.

The pipeline achieves Pareto-optimal solutions with less than 5% MAPE in one case.

Abstract

This paper presents a methodological framework for training, self-optimising, and self-organising surrogate models to approximate and speed up multiobjective optimisation of technical systems based on multiphysics simulations. At the hand of two real-world datasets, we illustrate that surrogate models can be trained on relatively small amounts of data to approximate the underlying simulations accurately. Including explainable AI techniques allow for highlighting feature relevancy or dependencies and supporting the possible extension of the used datasets. One of the datasets was created for this paper and is made publicly available for the broader scientific community. Extensive experiments combine four machine learning and deep learning algorithms with an evolutionary optimisation algorithm. The performance of the combined training and optimisation pipeline is evaluated by verifying the generated Pareto-optimal results using the ground truth simulations. The results from our pipeline and a comprehensive evaluation strategy show the potential for efficiently acquiring solution candidates in multiobjective optimisation tasks by reducing the number of simulations and conserving a higher prediction accuracy, i.e., with a MAPE score under 5% for one of the presented use cases.