Leak localization using distributed sensors and machine learning for hydrogen releases from a fuel cell vehicle in a parking garage

Zhao, Mingbin; Huang, Teng; Liu, Chenhui; Chen, Mingjia; Ji, Shui; Christopher, David M.; Li, Xuefang

doi:10.1016/j.ijhydene.2020.09.218

Cited by 43 publications

(8 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The results of their study showed that the ANN model could accurately detect and locate leaks with a prediction accuracy of 78.4%. 17 Wang et al showed the practicality of implementing machine learning algorithms for instant prediction in accidental leakage of Sulfur hexafluoride (SF 6 ) tracer and Sulfur dioxide (SO 2 ) tracer and proved the backpropagation (BP) network has a high prediction accuracy and a strong fitting ability. 18 Duong et al developed and optimized an ANN for quick and accurate prediction of radon dispersion and found that the gamma dose is the most influenced variable in comparison with other input variables for prediction of radon dispersion.…”

Section: Introductionmentioning

confidence: 99%

“…Zhao et al developed a helium leak localization system using a gas sensor network and machine learning. The results of their study showed that the ANN model could accurately detect and locate leaks with a prediction accuracy of 78.4% 17 . Wang et al showed the practicality of implementing machine learning algorithms for instant prediction in accidental leakage of Sulfur hexafluoride (SF 6 ) tracer and Sulfur dioxide (SO 2 ) tracer and proved the backpropagation (BP) network has a high prediction accuracy and a strong fitting ability 18 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Computational fluid dynamics model based artificial neural network prediction of flammable vapor clouds formed by liquid hydrogen releases

Xiao

et al. 2022

Intl J of Energy Research

Self Cite

View full text Add to dashboard Cite

Summary The flammable vapor clouds formed by liquid hydrogen release potentially leads to explosions and serious fires. In this paper, an artificial neural network (ANN) model based on the back propagation algorithm was developed to predict the horizontal and vertical hydrogen diffusion distances (the maximum distance of flammable vapor cloud with a hydrogen volume concentration of 4% to the release source in downwind and height direction). For this purpose, liquid hydrogen releases were modeled using a computational fluid dynamics (CFD) model, which was validated by experimental data. The single hidden layer ANN model used the wind speed, ground temperature, leakage duration, and leakage mass flow rate as input parameters. Then, the ANN model was trained and verified using 50 sets of sample data derived from the CFD simulations selected via the orthogonal experiment method. The results show that the ANN model well predicts the hydrogen diffusion distances, with the percentage error of the horizontal diffusion distance within 10% and the prediction error of the vertical diffusion distance less than 1.5 m for 90% of test points. The overall correlation coefficient between ANN predicted output and target results reaches 0.99329. Furthermore, the ANN model predicts four orders of magnitude faster than the CFD simulation and reduces the root means square error and the maximum relative error by more than 23% compared to predictions by the empirical correlation fitted from the CFD data. Then, the effects of the four input parameters on the diffusion distances were analyzed using the ANN model.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Computational fluid dynamics model based artificial neural network prediction of flammable vapor clouds formed by liquid hydrogen releases

Xiao

et al. 2022

Intl J of Energy Research

Self Cite

View full text Add to dashboard Cite

show abstract

“…Estos tres obtuvieron las mejores puntuaciones y el algoritmo MNN obtuvo los mejores resultados. De igual manera Zhao et al (2021) realizaron este tipo de investigaciones sobre la base de la localización de fugas de hidrógeno en un estacionamiento, usando k dynamic time warping (K-DTW), con 87,5 % de precisión, para distintos escenarios. Finalmente cabe resaltar que Raja Kumar et al (2019) se centraron en la detección de gases contaminantes usando artificial neural network (ANN), SVM y Naive Bayes; como valores redondeados de precisión obtuvieron 89 %, 84 % y 83 %, respectivamente.…”

Section: Introductionunclassified

Influencia de la posición del sensor MQ-6 y el tiempo transcurrido en la detección de concentración de GLP en una fuga doméstica

2022

View full text Add to dashboard Cite

Las fugas de gas en Lima e Ica (Perú) aumentan cada año, provocando accidentes y daños irreparables para la población. En esta investigación se produjo una fuga controlada usando una cocina de dos hornillas y un arreglo de sensores MQ-6 dispuestos en distintos ángulos con respecto a la cocina (45°, 0° y 30 °). Se encontró que, si la cocina se ubica en la posición alta (87 cm), la concentración detectada es menor, pero la detección es más rápida (6,419 s) si el arreglo se ubica a 50 cm del origen de la fuga. El tiempo de detección se encuentra entre 13,515 s y 21,740 s y la máxima concentración detectada es de 98 ppm. El modelo de aprendizaje que mejor se adaptó es Support Vector Machine, con un RMSE de 4,61 ppm. Se concluye que la mejor posición para la detección de gas fue a una altura de 47 cm sobre el suelo, a una distancia de 50 cm del sensor y a un ángulo de 0°. El tiempo de detección es de 13,84 s. Por último, se concluye que 30 segundos de fuga no son suficientes para alcanzar el límite dañino (147 ppm).

show abstract

“…Some relevant safety studies have been performed using Computational Fluid Dynamics (CFD) tools to reveal the accidental risks in various scenarios, such as around fuel cell vehicles [3][4][5][6][7][8], in tunnels [9][10][11][12][13], and in enclosed areas [14][15][16][17][18]. Some researchers have experimentally investigated hydrogen behavior by transporting hydrogen in semi-closed or confined structures [7,8,19]. For security reasons, helium has been widely applied as an alternative experimental gas for the prediction of hydrogen behavior in many studies, since helium has similar physical properties to hydrogen [7,20].…”

Section: Introductionmentioning

confidence: 99%

“…Hydrogen diffused and accumulated uniformly upward toward the ceiling after the leakage, and the concentration reached quasi-steady at 60 s and 12 s for 1 Nml/h/L and 45 Nml/h/L permeation rate, respectively. In addition, the detection of hydrogen dispersion is of critical importance in confined garage-like spaces, so Zhao, M. et al [19] developed a localization technology for safe monitoring of large parking garages, and the model's accuracy can be improved by learning more training data.…”

Section: Introductionmentioning

confidence: 99%

Numerical Simulation of Hydrogen Leakage from Fuel Cell Vehicle in an Outdoor Parking Garage

Shen

Zheng

et al. 2021

WEVJ

View full text Add to dashboard Cite

It is significant to assess the hydrogen safety of fuel cell vehicles (FCVs) in parking garages with a rapidly increased number of FCVs. In the present work, a Flame Acceleration Simulator (FLACS), a computational fluid dynamics (CFD) module using finite element calculation, was utilized to predict the dispersion process of flammable hydrogen clouds, which was performed by hydrogen leakage from a fuel cell vehicle in an outdoor parking garage. The effect of leakage diameter (2 mm, 3 mm, and 4 mm) and parking configurations (vertical and parallel parking) on the formation of flammable clouds with a range of 4–75% by volume was considered. The emission was assumed to be directed downwards from a Thermally Activated Pressure Relief Device (TPRD) of a 70 MPa storage tank. The results show that the 0.7 m parking space stipulated by the current regulations is less than the safety space of fuel cell vehicles. Compared with a vertical parking configuration, it is safer to park FCVs in parallel. It was also shown that release through a large TPRD orifice should be avoided, as the proportion of the larger hydrogen concentration in the whole flammable domain is prone to more accidental severe consequences, such as overpressure.

show abstract

Leak localization using distributed sensors and machine learning for hydrogen releases from a fuel cell vehicle in a parking garage

Cited by 43 publications

References 32 publications

Computational fluid dynamics model based artificial neural network prediction of flammable vapor clouds formed by liquid hydrogen releases

Computational fluid dynamics model based artificial neural network prediction of flammable vapor clouds formed by liquid hydrogen releases

Influencia de la posición del sensor MQ-6 y el tiempo transcurrido en la detección de concentración de GLP en una fuga doméstica

Numerical Simulation of Hydrogen Leakage from Fuel Cell Vehicle in an Outdoor Parking Garage

Contact Info

Product

Resources

About