Prediction of Mixing Uniformity of Hydrogen Injection inNatural Gas Pipeline Based on a Deep Learning Model

Abstract

It is economical and efficient to use existing natural gas pipelines to transport hydrogen. The fast and accurate prediction of mixing uniformity of hydrogen injection in natural gas pipelines is important for the safety of pipeline transportation and downstream end users. In this study, the computational fluid dynamics (CFD) method was used to investigate the hydrogen injection process in a T-junction natural gas pipeline. The coefficient of variation (COV) of a hydrogen concentration on a pipeline cross section was used to quantitatively characterize the mixing uniformity of hydrogen and natural gas. To quickly and accurately predict the COV, a deep neural network (DNN) model was constructed based on CFD simulation data, and the main influencing factors of the COV including flow velocity, hydrogen blending ratio, gas temperature, flow distance, and pipeline diameter ratio were taken as input nodes of the DNN model. In the model training process, the effects of various parameters on the prediction accuracy of the DNN model were studied, and an accurate DNN architecture was constructed with an average error of 4.53% for predicting the COV. The computational efficiency of the established DNN model was also at least two orders of magnitude faster than that of the CFD simulations for predicting the COV.

Computational fluid dynamic analysis of hydrogen‐injected natural gas for mixing and transportation behaviors in pipeline structures

“…The velocity values and HMRs of the gases at different positions in the pipeline are counted through 33 monitoring points. The velocity COV 32 is the ratio of the standard deviation to the mean value, which reflects the flow distribution of the mixed gases in the pipeline, and the formula is…”

“…The velocity values and HMRs of the gases at different positions in the pipeline are counted through 33 monitoring points. The velocity COV 32 is the ratio of the standard deviation to the mean value, which reflects the flow distribution of the mixed gases in the pipeline, and the formula is $$$COV=\frac{s}{\bar{v}}=\frac{1}{\bar{v}}\sqrt{\frac{1}{n-1}\sum _{i=1}^{n}{({v}_{i}-\bar{v})}^{2}},$$$where n is the number of monitoring points selected in the cross‐section, v i is the velocity of the monitoring point, m/s; $$\bar{v}$$ is the average value of the velocity over the monitored section, m/s.…”

Comparative Study of Mathematical Models for Describing the Distribution of Hydrogen-Enriched Natural Gas in Enclosed Spaces

“…The first method involves branch pipe mixing, where initially the gas stratification occurs due to density differences, followed by complete mixing during the transportation process. 15,16 The second method involves preblending hydrogen gas and natural gas in a mixing equipment before pipeline transportation, ensuring a fully homogeneous gas mixture. 17,18 Currently, to mitigate the occurrence of HENG stratification, the industry typically resorts to the second approach: Completely mixing was conducted within hydrogen blending stations prior to transportation.…”

“…Currently, two primary methods are commonly used to mix hydrogen gas into natural gas pipelines. The first method involves branch pipe mixing, where initially the gas stratification occurs due to density differences, followed by complete mixing during the transportation process. , The second method involves preblending hydrogen gas and natural gas in a mixing equipment before pipeline transportation, ensuring a fully homogeneous gas mixture. , Currently, to mitigate the occurrence of HENG stratification, the industry typically resorts to the second approach: Completely mixing was conducted within hydrogen blending stations prior to transportation. However, the issue of whether such well-mixed HENG will restratify under conditions of pipeline shutdown or during vertical riser transit constitutes a focal point of research within the academic community.…”

Blending of hydrogen into a natural gas distribution pipeline in British Columbia through a tee junction for reducing GHG emissions

“…Eames [11] investigated a transmission pressure pipe equipped with a vertical Tee junction and showed that the injection rate, side pipe diameter, and injection location significantly affect the mixing process mainly due to a density contrast of eight times between hydrogen and methane. A deep neural network (DNN) model was developed in [12] to predict the mixing quality of hydrogen and natural gas in low-pressure bottom-sided Tee junctions. In another work, it was suggested that adding a static mixer, such as a helical static mixer, can improve the stratification of gases, resulting in a more uniform mixture [13].…”