NeuralFMU: Presenting a workflow for integrating hybrid NeuralODEs into real world applications

TL;DR

This paper introduces NeuralFMUs, a workflow for integrating hybrid NeuralODEs with existing models, demonstrated through automotive consumption simulation, addressing real-world challenges like noise and discontinuities.

Contribution

It presents an intuitive workflow for deploying NeuralFMUs, enabling reuse of conventional models and integration into neural network topologies for improved prediction accuracy.

Findings

NeuralFMUs achieve higher prediction accuracy than traditional first-principle models.

The workflow facilitates encapsulation and reuse of existing models from common tools.

Handling of real measurement noise and high-frequency discontinuities is demonstrated.

Abstract

The term NeuralODE describes the structural combination of an Artifical Neural Network (ANN) and a numerical solver for Ordinary Differential Equations (ODEs), the former acts as the right-hand side of the ODE to be solved. This concept was further extended by a black-box model in the form of a Functional Mock-up Unit (FMU) to obtain a subclass of NeuralODEs, named NeuralFMUs. The resulting structure features the advantages of first-principle and data-driven modeling approaches in one single simulation model: A higher prediction accuracy compared to conventional First Principle Models (FPMs), while also a lower training effort compared to purely data-driven models. We present an intuitive workflow to setup and use NeuralFMUs, enabling the encapsulation and reuse of existing conventional models exported from common modeling tools. Moreover, we exemplify this concept by deploying a NeuralFMU for a consumption simulation based on a Vehicle Longitudinal Dynamics Model (VLDM), which is a typical use case in automotive industry. Related challenges that are often neglected in scientific use cases, like real measurements (e.g. noise), an unknown system state or high-frequent discontinuities, are handled in this contribution. For the aim to build a hybrid model with a higher prediction quality than the original FPM, we briefly highlight two open-source libraries: FMI.jl for integrating FMUs into the Julia programming environment, as well as an extension to this library called FMIFlux.jl, that allows for the integration of FMUs into a neural network topology to finally obtain a NeuralFMU.