Integration of multi-physics and machine learning-based surrogate modelling approaches for multi-objective optimization of deformed GDL of PEM fuel cells

The development of artificial intelligence (AI) greatly boosts scientific and engineering innovation. As one of the promising candidates for transiting the carbon intensive economy to zero emission future, proton exchange membrane (PEM) fuel cells has aroused extensive attentions. The gas diffusion layer (GDL) strongly affects the water and heat management during PEM fuel cells operation, therefore multi-variable optimization, including thickness, porosity, conductivity, channel/rib widths and compression ratio, is essential for the improved cell performance. However, traditional experiment-based optimization is time consuming and economically unaffordable. To break down the obstacles to rapidly optimize GDLs, physics-based simulation and machine learning-based surrogate modelling are integrated to build a sophisticated M5 model, in which multi-physics and multi-phase flow simulation, machine-learning-based surrogate modelling, multi-variable and multi objects optimization are included. Two machine learning methodologies, namely response surface methodology (RSM) and artificial neural network (ANN) are compared. The M5 model is proved to be effective and efficient for GDL optimization. After optimization, the current density and standard deviation of oxygen distribution at 0.4 V are improved by 20.8% and 74.6%, respectively. Pareto front is obtained to trade off the cell performance and homogeneity of oxygen distribution, e.g., 20.5% higher current density is achieved when sacrificing the standard deviation of oxygen distribution by 26.0%.

Automated summary

The development of artificial intelligence (AI) has greatly accelerated scientific and engineering innovation. Among the promising choices for transitioning to a zero-emission future in the carbon-intensive economy, the proton exchange membrane (PEM) fuel cell has received considerable attention. The gas diffusion layer (GDL) plays a crucial role in the water and heat management during the operation of PEM fuel cells, thus requiring multi-variable optimization. However, traditional experiment-based optimization methods are time-consuming and expensive. In order to overcome these obstacles, this study integrates physics-based simulation and machine learning-based surrogate modeling to rapidly optimize GDLs. Two machine learning methodologies, response surface methodology (RSM) and artificial neural network (ANN), are compared, and the M5 model is proven to be effective and efficient for GDL optimization.