Many countries consider hydrogen as a promising energy source to resolve the energy challenges over the global climate change. However, the potential of hydrogen explosions remains a technical issue to embrace hydrogen as an alternate solution since the Hindenburg disaster occurred in 1937. To ascertain safe hydrogen energy systems including production, storage, and transportation, securing the knowledge concerning hydrogen flammability is essential. In this paper, we addressed a comprehensive review of the studies related to predicting hydrogen flammability by dividing them into three types: experimental, numerical, and analytical. While the earlier experimental studies had focused only on measuring limit concentration, recent studies clarified the extinction mechanism of a hydrogen flame. In numerical studies, the continued advances in computer performance enabled even multi-dimensional stretched flame analysis following one-dimensional planar flame analysis. The different extinction mechanisms depending on the Lewis number of each fuel type could be observed by these advanced simulations. Finally, historical attempts to predict the limit concentration by analytical modeling of flammability characteristics were discussed. Developing an accurate model to predict the flammability limit of various hydrogen mixtures is our remaining issue.
Summary
Despite rapid improvements in the performance of the central processing unit (CPU), the calculation cost of simulating chemically reacting flow using CFD remains infeasible in many cases. The application of the convolutional neural networks (CNNs) specialized in image processing in flow field prediction has been studied, but the need to develop a neural network design fitted for CFD has recently emerged. In this study, a neural network model introducing the finite volume method (FVM) with unique network architecture and physics‐informed loss function was developed to accelerate CFD simulations. The developed network model, considering the nature of the CFD flow field where the identical governing equations are applied to all grids, can predict the future fields with only two previous fields unlike the CNNs requiring many field images (>10 000). The performance of this baseline model was evaluated using CFD time series data from non‐reacting flow and reacting flow simulation; counterflow and hydrogen flame with 20 detailed chemistries. Consequently, we demonstrated that (a) the FVM‐based network architecture provided significantly improved accuracy of multistep time series prediction compared to the previous MLP model (b) the physic‐informed loss function prevented non‐physical overfitting problem and ultimately reduced the error in time series prediction (c) observing the calculated residuals in an unsupervised manner could monitor the network accuracy. Additionally, under the reacting flow dataset, the computational speed of this network model was measured to be about 10 times faster than that of the CFD solver.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.