Hydrogen safety is a critical issue during the construction and development of the hydrogen energy industry. Hydrogen refueling stations play a pivotal role in the hydrogen energy chain. In the event of an accidental hydrogen leak at a hydrogen refueling station, the ability to quickly predict the leakage location is crucial for taking immediate and effective measures to prevent disastrous consequences. Therefore, the development of precise and efficient technologies to predict leakage locations is vital for the safe and stable operation of hydrogen refueling stations. This paper studied the localization technology of high-risk leakage locations in the fuel cell system of a skid-mounted hydrogen refueling station. The hydrogen leakage and diffusion processes in the fuel cell system were predicted using CFD simulations, and the hydrogen concentration data at various monitoring points were obtained. Then, a multilayer feedforward neural network was developed to predict leakage locations using simulated concentration data as training samples. After multiple adjustments to the network structure and hyperparameters, a final model with two hidden layers was selected. Each hidden layer consisted of 10 neurons. The hyperparameters included a learning rate of 0.0001, a batch size of 32, and 10-fold cross-validation. The Softmax classifier and Adam optimizer were used, with a training set for 1500 epochs. The results show that the algorithm can predict leakage locations not included in the training set. The accuracy achieved by the model was 95%. This approach addresses the limitations of sensor detection in accurately locating leaks and mitigates the risks associated with manual inspections. This paper provides a feasible method for locating hydrogen leakage in hydrogen energy application scenarios.

With the development of hydrogen energy, containerized hydrogen fuel cell systems are being used in distributed energy-supply systems. Hydrogen pipelines and electronic equipment of fuel cell containers can trigger hydrogen-explosion accidents. In the present study, Computational Fluid Dynamics (CFD) software was used to calculate the affected areas of hydrogen fuel cell container-explosion accidents with and without protective walls. The protective effects were studied for protective walls at various distances and heights. The results show that strategically placing protective walls can effectively block the propagation of shock waves and flames. However, the protective wall has a limited effect on the reduction of overpressure and temperature behind the wall when the protective wall is insufficiently high. Reflected explosion shock waves and flames will cause damage to the area inside the wall when the protective wall is too close to the container. In this study, a protective wall that is 5 m away from the container and 3 m high can effectively protect the area behind the wall and prevent damage to the container due to the reflection of shock waves and flame. This paper presents a suitable protective wall setting scheme for hydrogen fuel cell containers.

Hydrogen refueling stations are one of the key infrastructure components for the hydrogen-fueled economy. Skid-mounted hydrogen refueling stations (SHRSs) can be more easily commercialized due to their smaller footprints and lower costs compared to stationary hydrogen refueling stations. The present work modeled hydrogen explosions in a skid-mounted hydrogen refueling station to predict the overpressures for hydrogen-air mixtures and investigate the protective effects for different explosion vent layouts and protective wall distances. The results show that the explosive vents with the same vent area have similar overpressure reduction effects. The layout of the explosion vent affects the flame shape. Explosion venting can effectively reduce the inside maximum overpressure by 61.8%. The protective walls can reduce the overpressures, but the protective walls should not be too close to the SHRS because high overpressures are generated inside the walls due to the confined shock waves. The protective wall with a distance of 6 m can effectively protect the surrounding people and avoid the secondary overpressure damage to the container.