Estimation of carbon dioxide solubility in pure water using artificial neural network

Vapour liquid equilibrium (VLE) data are important for designing and modeling of process equipments. The phase behavior of the CO2+H2O system is of importance for many industrial processes. Since it is not always possible to carry out experiments at all possible temperatures and pressures, generally thermodynamic models based on equations of state are used for estimation of VLE. In this paper, an alternate tool, i.e. the artificial neural network (ANN) technique has been applied for estimation of solubility of carbon dioxide in water. ANN was applied to the raw data of the 105 experiments were carried out in R&D sector of Iran Behnoosh Co in range of 278.15–348.15K and 0.1–1MPa for temperature and pressure respectively. To check the ANN model, the samples were divided into two groups. One of them contained 85 samples and was used to train the network and the remaining 20 samples were used as the test set. For the training of the different networks, the standard feed forward back propagation algorithm was used and several types of structures were tested to obtain the most suitable network for the prediction of solubility. To check the reproducibility of the results, each of the networks studied was trained three times. Finally the best ANN structure was determined as 28-19-1. In comparison of performance analysis of ANN, the relative error (RE) was studied and maximum error found 6.98 percent and R2 was equal to 0.9957. To ensure, the results of ANN was compared with the results of software presented by L.W Diamond & N.N Akinfiev. To sum up ANN shows the better results in comparison with it. So it can be concluded that ANN provides a good method in predicting the solubility of carbon dioxide in pure water.

Estimation of carbon dioxide solubility in pure water using artificial neural network Keywords:

Artificial neural network , Solubility , Carbon dioxide , Water