Physically motivated structuring and optimization of neural networks for multi-physics modelling of solid oxide fuel cells. Issue 1 (2nd January 2021)

• Record Type: Journal Article
• Authors: Rauh, Andreas; Kersten, Julia; Frenkel, Wiebke; Kruse, Niklas; Schmidt, Tom
• Is Part Of: Mathematical and computer modelling of dynamical systems. Volume 27:Issue 1(2021)
• Page Start: 586
• Page End: 614
• Publication Date: 2021-01-02
• Subjects: Fuel cell systems -- neural networks -- function approximation -- nonlinear dynamical systems -- singular value decomposition -- robustness analysis; Engineering -- Mathematical models -- Periodicals; Computer simulation -- Periodicals; 515.39
• DOI: 10.1080/13873954.2021.1990966
• Languages: English
• ISSNs: 1387-3954

Abstract

ABSTRACT: Neural network models for complex dynamical systems typically do not explicitly account for structural engineering insight and mutual interrelations of various subprocesses that are related to the multi-physics nature of such systems. For that reason, they are commonly interpreted as a kind of data-driven, black box modelling option that is in opposition to a physically inspired equation-based system representation for which suitable parameters are subsequently identified in a grey box sense. To bridge the gap between data-driven and equation-based modelling paradigms, this paper proposes a novel approach for a physics-inspired structuring of neural networks. The derivation of this kind of structuring, an optimal choice of network inputs and numbers of neurons in a hidden layer as well as the achievable modelling accuracy are demonstrated for the thermal and electrochemical behaviour of high-temperature fuel cells. Finally, different network structures are compared against experimental data.