CFD Simulation and ANN Prediction of Hydrogen Leakage and Diffusion Behavior in a Hydrogen Refuelling Station
Bibliographic record
Abstract
Hydrogen refueling station (HRS) is an essential part of the infrastructure for promoting the hydrogen economy. Since hydrogen is a flammable and explosive gas, hydrogen released from high‐pressure hydrogen storage equipment in HRS will likely cause combustion or explosion accidents. Studying high‐pressure hydrogen leakage in HRS is a prerequisite for promoting hydrogen fuel cell vehicles and HRS. A computational fluid dynamics (CFD) model of an HRS in a demonstrated project in Ningbo, China, was established on the ANSYS FLUENT software platform. The CFD model for hydrogen leakage simulation was validated by comparing the simulation results with experimental data in the literature. The effects of the direction and mass flow rate of the hydrogen leakage jet, as well as the direction and speed of ambient wind, on hydrogen diffusion behavior were investigated. The spreading distances of the flammable hydrogen cloud were predicted using an artificial neural network for horizontal leakage. The results show that the jet direction strongly affected the flammable cloud flow. The greater the mass flow rate of the leak, the greater the hydrogen dispersion distance and the volume of the flammable hydrogen cloud. At a hydrogen leakage mass flow rate of 4.5589 kg/s, the volume of the hydrogen flammable cloud reached 6,140.46 m 3 at 30 s of leakage. The ambient wind speed has complicated effects on spreading the flammable cloud. The wind makes the flammable cloud move in certain directions, and the higher wind speed accelerates the diffusion of the flammable gas in the air. The results of the study can be used as a reference for the study of high‐pressure hydrogen leakage in HRS and will play an important role in the safe demonstration of the studied project.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".