Efficient Global Multi Parameter Calibration for Complex System Models Using Machine-Learning Surrogates

Abstract

In this work, we adress challenges associated with multi parameter calibration of complex system models of high computational expense. We propose to replace the Modelica Model for screening of parameter space by a computational effective Machine-Learning Surrogate, followed by a polishing with a gradient-based optimizer coupled to the Modelica Model. Our results show the superiority of this approach compared to common-used optimization strategies. We can resign on determining initial optimization values while using a small number of Modelica model calls, paving the path towards efficient global optimization. The Machine Learning Surrogate, namely a Physics Enhanced Latent Space Variational Autoencoder (PELS-VAE), is able to capture the impact of most influential parameters on small training sets and delivers sufficiently good starting values to the gradient-based optimizer. In order to make this paper self-contained, we give a sound overview to the necessary theory, namely Global Sensitivity Analysis with Sobol Indices and Variational Autoencoders.