Hydrogen solubility in furfural and furfuryl bio-alcohol: Comparison between the reliability of intelligent and thermodynamic models. (22nd October 2021)

• Record Type: Journal Article
• Authors: Xie, Juanjuan; Liu, Xiaoqing; Lao, Xiaodong; Vaferi, Behzad
• Is Part Of: International journal of hydrogen energy. Volume 46:Number 73(2021)
• Page Start: 36056
• Page End: 36068
• Publication Date: 2021-10-22
• Subjects: Hydrogen solubility -- Bio-compounds -- Intelligent modeling -- Thermodynamic correlations -- Comparison study; Hydrogen as fuel -- Periodicals; Hydrogène (Combustible) -- Périodiques; Hydrogen as fuel; Periodicals; 665.81
• DOI: 10.1016/j.ijhydene.2021.08.166
• Languages: English
• ISSNs: 0360-3199

Abstract

Abstract: This study compares the reliability of intelligent and thermodynamic modeling of hydrogen (H2 ) solubility in two bio-derived compounds (furfuryl alcohol and furfural). The intelligent modeling phase conducts using seven different scenarios. The most accurate approach selects employing the ranking analysis over various statistical indices. The general regression neural network appears as the best intelligent model for the given purpose. This model presents the relative absolute deviation (RAD) of 0.6%, mean square error of 3.87 × 10 −7, and regression coefficient of 0.99912 for predicting experimental measurements in the literature. The general regression neural network accuracy is far better than the perturbed-chain statistically associating fluid theory (PC-SAFT), Peng-Robinson, and Soave-Redlich-Kwong correlations. The most accurate thermodynamic approach, i.e., PC-SAFT, predicts H2 solubility in furfuryl alcohol and furfural with the RAD = 4.58% and 4.62%, while the general regression model has RAD = 0.79% and 0.5%. Indeed, the proposed model improves the prediction accuracy by more than three hundred percent. Graphical abstract: Image 1 Highlights: Hydrogen solubility in industrially relevant biochemicals is precisely estimated. General regression neural network is the best model for the given purpose. The (H2 solubility) −0.1 has the maximum relevancy with the independent variables. The proposed approach shows the overall MSE = 3.87 × 10 −7, RAD = 0.6%, and R 2 = 0.99912 Increasing pressure and temperature intensifies H2 solubility in the biochemicals.