Prediction of Standard Enthalpy of Combustion of Pure Compounds Using a Very Accurate Group-Contribution-Based Method

Abstract

The artificial neural network–group contribution (ANN–GC) method is applied to estimate the standard enthalpy of combustion of pure chemical compounds. A total of 4590 pure compounds from various chemical families are investigated to propose a comprehensive and predictive model. The obtained results show the squared correlation coefficient (R 2) of 0.999 99, root mean square error of 12.57 kJ/mol, and average absolute deviation lower than 0.16% for the estimated properties from existing experimental values.

On the rational formulation of alternative fuels: melting point and net heat of combustion predictions for fuel compounds using machine learning methods

“…The MLR model obtained is based on similar variables to those of Gharagheizi's model [29]. Gharagheizi et al have recently used a group contribution (GC) based method to predict the standard enthalpy of combustion of pure compounds [32]. The model, which was trained over a database containing a total of 4590 pure compounds, exhibits the following statistical coefficients: r 2 = 0.999, root mean square error (RMSE) = 12.57 kJ mol -1 and an average absolute relative error (AARE) = 0.16%.…”

Accurate prediction of the standard net heat of combustion from molecular structure

“…The author is currently working toward using a more comprehensive data set obtained from the literature (Gharagheizi et al, 2011) that includes all of the different types of compounds to improve the MVR and ANN predictive models for DH o c by using binary structural groups that require more data. Example: Prediction of the standard net heat of formation for pdiethyl benzene.…”

“…The data sets used in the literature to model the DH o c of pure compounds (Cardozo, 1986;Gharagheizi, 2008;Pan et al, 2011;Cao and Wang, 2013;Seaton and Harrison, 1990;Hshieh, 1999;Hshieh et al, 2003;Diallo et al, 2012;Wang and Li, 2000;Van Krevelen, 1990;National Technical Information Service (NTIS), 2001;Gharagheizi et al, 2011;Cao et al, 2009;Saldana et al, 2013;Albahri, 2013a) are so different that these models cannot be compared to one another. However, Table 2 shows that our proposed SGC-ANN model gives good results compared to the other models used to calculate DH o c .…”

“…However, Table 2 shows that our proposed SGC-ANN model gives good results compared to the other models used to calculate DH o c . Although it is more accurate, the method developed by Gharagheizi et al (Gharagheizi et al, 2011) is complicated by its 142 input structural groups with intricate definitions containing unconventional molecular descriptors, making this method very challenging in practice. In addition, while the QSPR-ANN model of Cao et al (Cao and Wang, 2013) produced very high error for compounds containing fluorine and chlorine, our SGC-ANN model produced very good results for these classes of compounds.…”

“…For models using artificial intelligence, Gharagheizi et al (2011) (Cao et al, 2009), which is high. Saldana et al (Saldana et al, 2013) combined several methods to create a consensus model for predicting the DH o c of 1624 hydrocarbon-based compounds and 1143 oxygenates (alcohols and esters) using QSPR.…”