Optimization of block structure parameters of PEMFC novel block channels using artificial neural network

Abstract

Flow channel design is critically important to the performance of proton exchange membrane fuel cell (PEMFC) due to its great influence on liquid water removal and mass and heat transfer. Block flow channel shows good prospect to improve liquid water removal and mass transport, benefiting the PEMFC performance. In this study, the block structures, namely the length, width and height of the block, are optimized for a novel block channel using data-driven surrogate model based on the artificial neural network (ANN). The training/test datasets are obtained from a three-dimensional multi-phase model based on the volume of fluid (VOF) method, with the water removal time (T) and the maximum channel pressure drop (ΔP) taken as the output and optimization objectives. The results show that the ANN prediction agrees well with the physical model results, with the coefficient of determination (R2) of T and ΔP are 0.99598 and 0.99677, respectively. The block parameters are further optimized using the comprehensive scoring method considering both T and ΔP. The block parameters with the length of 0.8 mm, width of 0.375 mm and height of 0.75 mm are found to be the optimum in terms of the highest score. The optimum parameters obtained from the data-driven surrogate model are verified by the physical model, indicating that the ANN model is an effective and fast method to optimize block structure of block flow channel from the perspective of liquid water removal and channel pressure drop.