Multi-physics-resolved digital twin of proton exchange membrane fuel cells with a data-driven surrogate model

TLDR

Digital twins that resolve multi‑physics in proton exchange membrane fuel cells are crucial for advancing PEMFC technology. This study proposes a surrogate modelling approach that fuses a state‑of‑the‑art 3‑D PEMFC physical model with a data‑driven model to address this challenge. The authors integrate the 3‑D physical model with the data‑driven surrogate to build a digital twin, which is then used to design healthy‑operation envelopes and state maps for PEMFCs. The surrogate model attains 3.9–24.8% rRMSE on multi‑physics fields, matching the full 3‑D model’s accuracy while dramatically reducing computation time and enabling efficient digital‑twin‑based designs such as healthy‑operation envelopes and state maps.

Abstract

The development of multi-physics-resolved digital twins of proton exchange membrane fuel cells (PEMFCs) is significant for the advancement of this technology. Here, to solve this scientific issue, a surrogate modelling method that combines a state-of-the-art three-dimensional PEMFC physical model and data-driven model is proposed. The surrogate modelling prediction results demonstrate that the test-set relative root mean square errors (rRMSEs) of the multi-physics fields range from 3.88% to 24.80% and can mirror the multi-physics field distribution characteristics well. In summary, for multi-physics field prediction, the data-driven surrogate model has a comparable accuracy to the comprehensive 3D physical model; however, it considerably reduces the cost of computation and time and achieves the efficient multi-physics-resolved digital-twin. Two model-based designs based on the as-developed digital twin framework, i.e. the PEMFC healthy operation envelope and the PEMFC state map, are demonstrated. This study highlights the potential of combining data-driven approaches and comprehensive physical models to develop the digital twin of complex systems, such as PEMFCs.