Natural gas is transported from producing regions to consumption regions by using transmission pipelines at high pressures. At consumption regions, the pressure of natural gas is reduced in city gate stations(CGSs). B...Natural gas is transported from producing regions to consumption regions by using transmission pipelines at high pressures. At consumption regions, the pressure of natural gas is reduced in city gate stations(CGSs). Before the pressure reduction process, the temperature of natural gas is increased usually by using a water bath heater,which burns natural gas as fuel, to protect against freezing of natural gas. These types of heat exchangers have a low efficiency and consume a lot of fuel to generate the required heat. In the current study, the twisted configuration of the heating coil is proposed and investigated to enhance the heat transfer through a water bath heater with a nominal capacity of 1000 m^3·h^-1. Firstly, the implementation procedure is validated with data collected from the CGS of Qaleh-Jiq(located in Golestan province of Iran). A very good agreement is achieved between the obtained results and the real data. Then, three different twist ratios are considered to examine the twisting effects. The proposed technique is evaluated in the terms of velocity, temperature, and pressure variations, and the results are compared with the conventional case, i.e. straight configuration. It is found that both the heat transfer rate and the pressure drop augment as the twist ratio is raised. Finally, it is concluded that the twisted tubes can reduce the length of the gas coil by about 12.5% for the model with low twist ratio, 18.75% for the model with medium twist ratio, and 25% for the model with high twist ratio as compared to the straight configuration.展开更多
水质指标具有多元相关性、时序性和非线性的特点,为有效预测河流水质变化,针对水质数据存在缺失和异常的问题,提出基于灰色关联分析-门控循环单元(Grey Relational Analysis-Gated Recurrent Unit, GRA-GRU)的水质预测模型。以淮河流域...水质指标具有多元相关性、时序性和非线性的特点,为有效预测河流水质变化,针对水质数据存在缺失和异常的问题,提出基于灰色关联分析-门控循环单元(Grey Relational Analysis-Gated Recurrent Unit, GRA-GRU)的水质预测模型。以淮河流域水质数据为样本,使用线性插值修补缺失数据和剔除的异常数据。使用灰色关联分析计算不同水质指标间的相关性,选择高相关性的水质指标以确定输入变量,并使用门控循环单元(Gated Recurrent Unit, GRU)预测不同的水质指标。将GRA-GRU的预测结果与反向传播神经网络(Back Propagation Neural Network, BPNN)、循环神经网络(Recurrent Neural Network, RNN)、长短期记忆神经网络(Long Short Term Memory, LSTM)、GRU及灰色关联分析-长短期记忆神经网络(Grey Relational Analysis-Long Short Term Memory, GRA-LSTM)进行对比分析,结果显示GRA-GRU在不同水质指标预测上具有较好的适应性,可以有效降低预测误差。其中,与其他模型相比,GRA-GRU预测的化学需氧量在均方根误差上分别降低了3.617%、0.681%、0.478%、1.505%和0.471%。展开更多
基金Islamic Azad University(IAU)Shahrood Branch,Shahrood,IranGolestan Province Gas Company,Gorgan,Iran for their sponsorships.
文摘Natural gas is transported from producing regions to consumption regions by using transmission pipelines at high pressures. At consumption regions, the pressure of natural gas is reduced in city gate stations(CGSs). Before the pressure reduction process, the temperature of natural gas is increased usually by using a water bath heater,which burns natural gas as fuel, to protect against freezing of natural gas. These types of heat exchangers have a low efficiency and consume a lot of fuel to generate the required heat. In the current study, the twisted configuration of the heating coil is proposed and investigated to enhance the heat transfer through a water bath heater with a nominal capacity of 1000 m^3·h^-1. Firstly, the implementation procedure is validated with data collected from the CGS of Qaleh-Jiq(located in Golestan province of Iran). A very good agreement is achieved between the obtained results and the real data. Then, three different twist ratios are considered to examine the twisting effects. The proposed technique is evaluated in the terms of velocity, temperature, and pressure variations, and the results are compared with the conventional case, i.e. straight configuration. It is found that both the heat transfer rate and the pressure drop augment as the twist ratio is raised. Finally, it is concluded that the twisted tubes can reduce the length of the gas coil by about 12.5% for the model with low twist ratio, 18.75% for the model with medium twist ratio, and 25% for the model with high twist ratio as compared to the straight configuration.
文摘水质指标具有多元相关性、时序性和非线性的特点,为有效预测河流水质变化,针对水质数据存在缺失和异常的问题,提出基于灰色关联分析-门控循环单元(Grey Relational Analysis-Gated Recurrent Unit, GRA-GRU)的水质预测模型。以淮河流域水质数据为样本,使用线性插值修补缺失数据和剔除的异常数据。使用灰色关联分析计算不同水质指标间的相关性,选择高相关性的水质指标以确定输入变量,并使用门控循环单元(Gated Recurrent Unit, GRU)预测不同的水质指标。将GRA-GRU的预测结果与反向传播神经网络(Back Propagation Neural Network, BPNN)、循环神经网络(Recurrent Neural Network, RNN)、长短期记忆神经网络(Long Short Term Memory, LSTM)、GRU及灰色关联分析-长短期记忆神经网络(Grey Relational Analysis-Long Short Term Memory, GRA-LSTM)进行对比分析,结果显示GRA-GRU在不同水质指标预测上具有较好的适应性,可以有效降低预测误差。其中,与其他模型相比,GRA-GRU预测的化学需氧量在均方根误差上分别降低了3.617%、0.681%、0.478%、1.505%和0.471%。
