Hydrogen-doped natural gas technology has been gradually used in pipeline transportation, but hydrogen-doped natural gas is suspectible to leakage and explosion accidents. The study used a 20-L spherical device to investigate the effects of hydrogen doping ratio and CO2 addition on the explosion pressure and flame propagation characteristics of hydrogen-doped natural gas, and the chemical reaction kinetics method was used to analyze the explosion mechanism. The results showed that the hydrogen doping ratio has a promoting effect on the pressure parameters of hydrogen-doped natural gas explosion and flame propagation speed. As the hydrogen doping ratio increases, the maximum explosion pressure gradually increases, while both the rapid burn time and sustained burn time decrease progressively. The maximum rise rate of explosion pressure and flame propagation speed gradually increase when the hydrogen doping ratio is lower than 0.5. When the hydrogen doping ratio is greater than 0.5, the maximum rise rate of explosion pressure and flame propagation speed rise rapidly. The addition of CO2 has an inhibitory effect on the explosion pressure and flame propagation speed of the mixed gas, but the suppression effect on pressure parameters with high hydrogen doping ratio is weak. Through reaction kinetic analysis, it can be seen that as the hydrogen doping ratio increases, the laminar burning velocity and adiabatic flame temperature gradually increase. Meanwhile the concentration of active free radicals and the product formation rate increase significantly, and the mixing of hydrogen changes the reaction path of methane. When the hydrogen doping ratio is greater than 0.5, reactions R84, R46 and R3 enter the top ten steps of the reaction, producing H and OH radicals, which promotes the reaction. CO2 can reduce the laminar burning velocity, adiabatic flame temperature, active free radical concentration and product formation raten of the mixed gas, but adding CO2 does not change the reaction path of methane.Hydrogen-doped natural gas technology has been gradually used in pipeline transportation, but hydrogen-doped natural gas is prone to leakage and explosion accidents. The study used a 20L spherical device to investigate the effects of hydrogen blending ratio and CO2 addition on the explosion pressure and flame propagation characteristics of hydrogen-doped natural gas, and the chemical reaction kinetics method was used to analyse the explosion mechanism. The results showed that the hydrogen doping ratio has a promoting effect on the hydrogen-doped natural gas explosion pressure parameters and flame propagation speed. As the hydrogen doping ratio increases, the maximum explosion pressure gradually increases, the rapid burn time and sustained burn time are gradually decreasing. The maximum explosion pressure rise rate and flame propagation speed gradually increase when the hydrogen doping ratio is less than 0.5. When the hydrogen doping ratio is greater than 0.5, the maximum explosion pressure rise rate and flame propagation speed rise rapidly. The addition of CO2 has an inhibitory effect on the explosion pressure and flame propagation speed of the mixed gas, but the suppression effect on pressure parameters with high hydrogen doping ratio is poor. Through reaction kinetic analysis, it can be seen that as the hydrogen doping ratio increases, the laminar burning velocity and adiabatic flame temperature gradually increase, the mole fraction of active free radicals and the rate of product increase significantly, and the mixing of hydrogen changes the reaction path of methane. When the hydrogen doping ratio is greater than 0.5, reactions R84, R46 and R3 enter the top ten steps of the reaction, producing H and OH radicals, which promotes the reaction. CO2 can reduce the laminar burning velocity, adiabatic flame temperature, active free radical mole fraction and rate of production of the mixed gas, but adding CO2 does not change the reaction path of methane.
- Article type
- Year
- Co-author
Open Access
Issue
Spontaneous coal combustion is one of the major natural disasters in coal mining; thus, accurate prediction of the risk of spontaneous coal combustion is crucial to prevent and control coal fire disasters. However, the complexity of the physicochemical process of spontaneous coal combustion and its various influencing factors poses a challenge to the risk prediction of spontaneous coal combustion. Strengthening research on spontaneous coal combustion hazard prediction technology using deep learning is crucial for improving the intelligent control level of coal mine safety production.
In this study, CO volume fraction was chosen as the index for spontaneous coal combustion evaluation. A dataset was constructed, and the field observation data were visualized. Next, the dataset was tested for the distribution of eigenvariables, normalized for the distribution of eigenvariables, and normalized for the dataset using kernel density estimation, logarithmic transformation, and maximum-minimum normalization. Finally, three algorithms, namely recurrent neural network (RNN), long short-term memory (LSTM) network, and gated recurrent unit (GRU), were applied to the data mining of spontaneous coal combustion feature information, and a dynamic sequence prediction model of spontaneous coal combustion CO volume fraction was established. During the model construction process, the full connectivity layer and Dropout class were added to prevent overfitting, and the mean square error and three model performance test indicators were introduced to analyze and optimize the model parameters and test the model performance.
The results were presented as follows: (1) The CO volume fraction sequence dataset was established based on the field data of the Dafosi Coal Mine, the model generalization capability was enhanced, and the training time of the model was shortened by preprocessing the dataset. (2) The RNN, LSTM, and GRU models achieved the dynamic prediction of CO with an error of less than 1 %. (3) The optimal parameters of the three models were determined from the mean absolute error (MAE), the root mean square error (RMSE), and R2 of the training and validation sets. A comparative study using the model performance evaluation metrics revealed that the LSTM model had the highest prediction accuracy under the same sequence data, followed by the RNN and GRU models.
Using 285 sets of field data, the spontaneous coal combustion CO volume fraction sequence prediction models based on the RNN, LSTM, and GRU algorithms were established. The experimental values of the CO volume fraction were highly consistent with the predicted values, and the prediction error was less than 1 %. The model can predict the change in the CO volume fraction in future moments using the dataset. The results reveal that the dynamic time series prediction of CO volume fraction from spontaneous coal combustion using sequence models is possible compared with conventional static models. Moreover, the process of constructing the three models and optimizing the parameters can be employed as a basic study for developing sequence prediction models for other indicator gases.
京公网安备11010802044758号