Hydrogen is considered the next energy to replace fossil fuels, but it must be handled with care given that it is a flammable gas. A barrier wall is an effective way to mitigate the effect of an explosion, and to build a safe barrier wall, research on hydrogen explosions is necessary. Experiments and CFD (computational fluid dynamics) are two commonly used methods, but both are costly to use under any condition. Machine learning can be used to enhance the data from experiments and CFD as the trained model can predict explosion pressure levels very rapidly under various conditions. We propose the prediction of a hydrogen VCE (vapor cloud explosion) with a barrier wall using various machine learning methods. This research uses CFD simulation data from KAERI (Korea Atomic Energy Research Institute) as training data. MLP (multi-layer perceptron), LSTM (long short-term memory), and the Transformer architectures are used to train the hydrogen VCE and are compared. In our research, MLP produces the best score among all learning processes, with an R² value exceeding 0.97, outperforming both LSTM and Transformer in terms of accuracy and speed. The trained machine learning model can be used to build safe barrier walls in hydrogen refueling stations. Evaluating the safe distance from the barrier wall and evaluating the optimal position of the barrier wall are possible usages.

We present a prediction of hydrogen storage vessel explosion using machine learning. A neural network model is trained to learn the waveform of a hydrogen explosion with a blast wall and used to predict the waveform with arbitrary blast wall position. The initial training revealed one of the features, blast wall distance, greatly affects the blast waveform. To emphasize the effect of that feature, feature multiplication is used instead of normalization and this enabled the training to learn the waveform correctly. The trained model can predict the blast waveform with an arbitrarily located blast wall. The result can be used in structural analysis and this will help to construct the blast wall in the hydrogen refuelling station. This research uses the CFD (Computational Fluid Dynamics) simulation by Pukyong University, South Korea, as training data.