Designing and optimizing a parallel neural network model for predicting the solubility of diosgenin in n-alkanols

doi:10.1016/j.cjche.2020.09.009

Abstract

Abstract: Accurate estimation of the solubility of a chemical compound is an important issue for many industrial processes. To overcome the defects of some thermodynamic models and simple correlations, a parallel neural network (PNN) model was conceived and optimized to predict the solubility of diosgenin in seven n-alkanols (C₁-C₇). The linear regression analysis of the parity plots indicates that the PNN model can give more accurate descriptions of the solubility of diosgenin than the ordinary neural network (ONN) model. The comparison of the average root mean square deviation (RMSD) shows that the suggested model has a slight advantage over the thermodynamic NRTL model in terms of the calculating precision. Moreover, the PNN model can reflect the effects of the temperature and the chain length of the alcohol solvent on the solution behavior of diosgenin correctly and can estimate its solubility in the n-alkanols with more carbon atoms.

Key words: Solubility, Diosgenin, Parallel neural network model, NRTL model

摘要： Accurate estimation of the solubility of a chemical compound is an important issue for many industrial processes. To overcome the defects of some thermodynamic models and simple correlations, a parallel neural network (PNN) model was conceived and optimized to predict the solubility of diosgenin in seven n-alkanols (C₁-C₇). The linear regression analysis of the parity plots indicates that the PNN model can give more accurate descriptions of the solubility of diosgenin than the ordinary neural network (ONN) model. The comparison of the average root mean square deviation (RMSD) shows that the suggested model has a slight advantage over the thermodynamic NRTL model in terms of the calculating precision. Moreover, the PNN model can reflect the effects of the temperature and the chain length of the alcohol solvent on the solution behavior of diosgenin correctly and can estimate its solubility in the n-alkanols with more carbon atoms.

关键词: Solubility, Diosgenin, Parallel neural network model, NRTL model

Huichao Lv, Dayong Tian. Designing and optimizing a parallel neural network model for predicting the solubility of diosgenin in n-alkanols[J]. Chinese Journal of Chemical Engineering, 2021, 29(1): 288-294.

Huichao Lv, Dayong Tian. Designing and optimizing a parallel neural network model for predicting the solubility of diosgenin in n-alkanols[J]. 中国化学工程学报, 2021, 29(1): 288-294.

References

[1] M. Safamirzaei, H. Modarress, Modeling and predicting solubility of n-alkanes in water, Fluid Phase Equilib. 309(2011) 53-61.
[2] M. Lashkarbolooki, B. Vaferi, M.R. Rahimpour, Comparison the capability of artificial neural network (ANN) and EOS for prediction of solid solubilities in supercritical carbon dioxide, Fluid Phase Equilib. 308(2011) 35-43.
[3] K. Moodley, J. Rarey, D. Ramjugernath, Experimental solubility of diosgenin and estriol in various solvents between T=(293.2-328.2) K, J. Chem. Thermodyn. 106(2017) 199-207.
[4] J. Kiepe, S. Horstmann, K. Fischer, J. Gmehling, Experimental determination and prediction of gas solubility data for methane + water solutions containing different monovalent electrolytes, Ind. Eng. Chem. Res. 42(2003) 5392-5398.
[5] R. Sharma, D. Singhal, R. Ghosh, A. Dwivedi, Potential applications of artificial neural networks to thermodynamics:vapor-liquid equilibrium predictions, Comput. Chem. Eng. 23(1999) 385-390.
[6] C. Si-Moussa, S. Hanini, R. Derriche, M. Bouhedda, A. Bouzidi, Prediciton of highpressure vapor liquid equilibrium of six binary systems, carbon dioxide with six esters, using an artificial neural network model, Braz. J. Chem. Eng. 25(2008) 183-199.
[7] P. Kan, C.J. Lee, A neural network model for prediction of phase equilibria in aqueous two-phase extraction, Ind. Eng. Chem. Res. 35(1996) 2015-2023.
[8] H. Buchowski, A. Ksiazczak, S. Pietrzyk, Solvent activity along a saturation line and solubility of hydrogen-bonding solids, J. Phys. Chem. 84(1980) 975-979.
[9] M. Safamirzaei, H. Modarress, M. Mohsen-Nia, Modeling the hydrogen solubility in methanol, ethanol, 1-propanol and 1-butanol, Fluid Phase Equilib. 289(2010) 32-39.
[10] R. Haghbakhsh, H. Adib, P. Keshavarz, M. Koolivand, S. Keshtkari, Development of an artificial neural network model for the prediction of hydrocarbon density at highpressure, high-temperature conditions, Thermochim. Acta 551(2013) 124-130.
[11] E. Vatankhah, D. Semnani, M.P. Prabhakaran, M. Tadayon, S. Razavi, S. Ramakrishna, Artificial neural network for modeling the elastic modulus of electrospun polycaprolactone/gelatin scaffolds, Acta Biomater. 10(2014) 709-721.
[12] M.H. Esfe, M. Afrand, W.M. Yan, M. Akbari, Applicability of artificial neural network and nonlinear regression to predict thermal conductivity modeling of Al₂O₃-water nanofluids using experimental data, Int. Commun. Heat Mass 66(2015) 246-249.
[13] F.F. Chen, M. Breedon, P. White, C. Chu, D. Mallick, S. Thomas, I. Cole, Correlation between molecular features and electrochemical properties using an artificial neural network, Mater. Design 112(2016) 410-418.
[14] M. Afrand, M.H. Esfe, E. Abedini, H. Teimouri, Predicting the effects of magnesium oxide nanoparticles and temperature on the thermal conductivity of water using artificial neural network and experimental data, Phys. E. 87(2017) 242-247.
[15] G.A. Longo, L. Ortombina, M. Zigliotto, Application of artificial neural network (ANN) for modelling H₂O/KCOOH (potassium formate) dynamic viscosity, Int. J. Refrig. 86(2018) 435-440.
[16] A.A. Rohani, G. Pazuki, H.A. Najafabadi, S. Seyfi, M. Vossoughi, Comparison between the artificial neural network system and SAFT equation in obtaining vapor pressure and liquid density of pure alcohols, Expert Syst. Appl. 38(2011) 1738-1747.
[17] F.X. Chen, M.R. Zhao, C.C. Liu, F.F. Peng, B.Z. Ren, Determination and correlation of the solubility for diosgenin in alcohol solvents, J. Chem. Thermodyn. 50(2012) 1-6.
[18] F.X. Chen, M.R. Zhao, B.Z. Ren, C.R. Zhou, F.F. Peng, Solubility of diosgenin in different solvents, J. Chem. Thermodyn. 47(2012) 341-346.
[19] F.X. Chen, Z.L. Qi, L. Feng, J.Y. Miao, B.Z. Ren, Application of the NRTL method to correlate solubility of diosgenin, J. Chem. Thermodyn. 71(2014) 231-235.
[20] Y. Wang, Z. Yang, J. Bao, Y. Hong, A two-stage nanofiltration process for reclamation of diosgenin waste water, Desalination 257(2010) 53-57.
[21] M. Okawara, F. Hashimoto, H. Todo, K. Sugibayashi, Y. Tokudome, Effect of liquid crystals with cyclodextrin on the bioavailability of a poorly water-soluble compound, diosgenin, after its oral administration to rats, Int. J. Pharm. 472(2014) 257-261.
[22] C. Tohda, X. Yang, M. Matsui, Y. Inada, E. Kadomoto, S. Nakada, N. Shibahara, Diosgenin-rich yam extract enhances cognitive function:a placebo-controlled, randomized, double-blind, crossover study of healthy adults, Nutrients 9(2017) 1160-1172.
[23] H. Parhizgar, M.R. Dehghani, A. Khazaei, M. Dalirian, Application of neural networks in the prediction of surface tensions of binary mixtures, Ind. Eng. Chem. Res. 51(2012) 2775-2781.
[24] J. Bourquin, H. Schmidli, P. van Hoogevest, H. Leuenberger, Basic concepts of artificial neural networks (ANN) modeling in the application to pharmaceutical development, Pharm. Dev. Technol. 2(1997) 95-109.
[25] H. Mazaheri, M. Ghaedi, M.A. Azqhandi, A. Asfaram, Application of machine/statistical learning, artificial intelligence and statistical experimental design for the modeling and optimization of methylene blue and Cd (Ⅱ) removal from a binary aqueous solution by natural walnut carbon, Phys. Chem. Chem. Phys. 19(2017) 11299-11317.
[26] L.F. Huang, W.Q. Tong, Impact of solid state properties on developability assessment of drug candidates, Adv. Drug Deliv. Rev. 56(2004) 321-334.
[27] M. Pudipeddi, A.T.M. Serajuddin, Trends in solubility of polymorphs, J. Pharm. Sci. 94(2005) 929-939.
[28] F.X. Chen, Crystallization Thermodynamics and Thermal Decomposition of Diosgenin, M.S. Thesis, Zhengzhou Univ, China, 2014.
[29] C. Saal, A.C. Petereit, Optimizing solubility:kinetic versus thermodynamic solubility temptations and risks, Eur. J. Pharm. Sci. 47(2012) 589-595.