Prediction of sorption enhanced steam methane reforming products from machine learning based soft-sensor models

Carbon dioxide-abated hydrogen can be synthesised via various processes,one of which is sorption enhanced steam methane reforming(SE-SMR),which produces separated streams of high purity H_(2) and CO_(2).Properties of hydrogen and the sorbent material hinder the ability to rapidly upscale SE-SMR,therefore the use of artificial intelligence models is useful in order to assist scale up.Advantages of a data driven soft-sensor model over ther-modynamic simulations,is the ability to obtain real time information dependent on actual process conditions.In this study,two soft sensor models have been developed and used to predict and estimate variables that would otherwise be difficult direct measured.Both artificial neural networks and the random forest models were devel-oped as soft sensor prediction models.They were shown to provide good predictions for gas concentrations in the reformer and regenerator reactors of the SE-SMR process using temperature,pressure,steam to carbon ratio and sorbent to carbon ratio as input process features.Both models were very accurate with high R^(2) values,all above 98%.However,the random forest model was more precise in the predictions,with consistently higher R^(2) values and lower mean absolute error(0.002-0.014)compared to the neural network model(0.005-0.024).

Efficiency analysis of sorption-enhanced method in steam methane reforming process

The sorption-enhanced method can change the thermodynamic equilibrium by absorbing CO_(2).However,it also brings about the problems of high regeneration temperature of adsorbent and large regeneration energy consumption.In order to study the impact of enhanced adsorption methods on the overall energy cost of the system in the hydrogen production process,this paper analyzes and compares steam methane reforming and reactive adsorption-enhanced steam methane reforming with the energy consumption of hydrogen production products as the evaluation index.The results showed that the energy consumption per unit hydrogen production decreased from 276.21 MJ/kmol to 131.51 MJ/kmol,and the decomposition rate of H2O increased by more than 20%after the addition of adsorption enhancement method.It is proved that the advantage of sorption enhanced method on pre-separation of CO_(2)in the product makes up for the disadvantage of energy consumption of adsorbent regeneration.In addition,the ability of the process to obtain H element is improved by the high decomposition rate of H2O,which realizes a more rational distribution of the element.