Real-time hydrogen release and dispersion modelling of hydrogen refuelling station by using deep learning probability approach

• Published in: International journal of hydrogen energy 2024-01, Vol.51, p.794-806
• Main Authors: Li, Junjie, Xie, Weikang, Li, Huihao, Qian, Xiaoyuan, Shi, Jihao, Xie, Zonghao, Wang, Qing, Zhang, Xinqi, Chen, Guoming
• Format: Article
• Language: English
• Subjects: Deep learning; Digital twin; Hydrogen refuelling station; Hydrogen release and dispersion; Variation Bayesian inference
• ISSN: 0360-3199; 1879-3487
• DOI: 10.1016/j.ijhydene.2023.04.126

Hydrogen release and dispersion from hydrogen refuelling stations have the potential to cause explosion disaster and bring significant causalities and economic losses to the surroundings. Real-time spatial hydrogen plume concentration prediction is essential for the quick emergency response planning to dissipate such flammable vapor cloud and prevent explosion disaster. Deep learning approaches have recently been applied to real-time gas release and dispersion modeling, however, are ‘over-confident’ for spatial plume concentration and boundary estimation, which could not support the robust decision-makings. This study proposes a hybrid deep probability learning-based spatial hydrogen plume concentration prediction model, namely DPL_H2Plume by integrating deep learning and Variational Bayesian Inference. Numerical model of hydrogen release and dispersion from hydrogen refuelling station is built to construct the benchmark dataset. By using such dataset, two pre-defined parameters, namely Monte Carlo sampling number m = 300 and dropout probability p = 0.1 are determined to ensure the model's tradeoff between inference accuracy and efficiency. Comparison between our proposed model and the state-of-the-art model is also conducted. The results demonstrate that our model exhibits a competitive accuracy of R2 = 0.97 as well as an inference time 3.32 s. In addition, our model gives the comprehensive estimations including not only spatial hydrogen plume concentration but also its uncertainty. Also, our model provides the more accurate estimation at plume boundary compared to the state-of-the-art model. Overall, our proposed model could provide reliable alternative for constructing a digital twin for emergency management of hydrogen refuelling station. •Deep probabilistic learning-based hydrogen plume prediction model is proposed.•Optimal hyperparameters of variational Bayesian inference are determined.•Model accurately predicts real-time spatial hydrogen plume concentration given scenario-related parameters.•Model predicts additional uncertainty information for comprehensive emergency decision-makings.