Artificial Neural Network-Group Contribution Method for Predicting Standard Enthalpy of Formation in the Solid State: C–H, C–H–O, C–H–N, and C–H–N–O Compounds

Abstract

In this work, an artificial neural network-group contribution model is developed to predict the standard enthalpy of formation in the solid (crystal) state of pure compounds. Several classes of hydrocarbon compounds CH, oxygenated compounds CHO, nitrogen compounds CHN, and energetic compounds CHNO are investigated to propose a comprehensive and predictive model. The new model is developed and tested for 1222 organic compounds containing complex molecular structures. The performance of the new model has been compared with previous work and is shown to be far more accurate. The obtained results show an average absolute deviation of 9.33 kJ·mol −1 and a coefficient of determination of 0.9972 for the experimental values.

Enthalpy of Formation Modeling Using Third Order Group Contribution Technics and Calculation by DFT Method.

“…The fragmentation of the molecular structures was performed by an automatic program using Marrero and Gani method [32]. For more details on the cutting technique we recommend these works [32,37,38] . The chemical structures of all considered compounds were used.…”

“…For this purpose, in this work the data set was divided into two sub data sets using semi-randomly choice [37,38]. Indeed, if a compound is selected and if this compound is described by one of the irrelevant groups; group having their contribution value generated by less than three compounds, this compound is removed from the test set.…”

“…After analyzing the molecular structures of these compounds having large estimation errors, new structural groups are defined and included in the Marrero-Gani's groups as additional new third-order groups in order to increase the accuracy and reliability of the proposed model. These new groups provide more structural information and allow distinguishing between similar compounds having one or more functional first-order groups in common [37,38]. A list of new groups, along with sample assignments and group occurrences, is presented in appendix C (See supplementary material).…”

Recent Developments for Prediction of Power of Aromatic and Non‐Aromatic Energetic Materials along with a Novel Computer Code for Prediction of Their Power

“…where Q detH 2 O-CO 2 is the predicted heat of detonation by the "H 2 O-CO 2 arbitrary", D f H 0 [H 2 O(l)] and D f H 0 [CO 2 (g)] is the standard heat of formation of H 2 O(l) and CO 2 (g), respectively,a nd D f H 0 (explosive) is the condensed phaseh eat of formation of desired explosive. For those energetic compoundsw here their experimental data of the condensed phase heat of formation are not available, simple empirical [3,[35][36][37][38][39],q uantum mechanical [40][41][42][43],g roup additivity [44,45],a nd artificial neural network [46] methods can be used to find the condensedp hase heat of formation of different classes C a H b N c O d energetic compounds.…”

Accurate or Fast Prediction of Solid-State Formation Enthalpies Using Standard Sublimation Enthalpies Derived From Geometrical Fragments

“…It is a valuable indicator of crystal stability and may be used to evaluate other properties of practical significance such as vapor pressure . Moreover, it is a significant contribution to the solid-state formation enthalpy Δ f H 0 (cr) of organic crystals required to evaluate the energy content, performances, and sensitivities of candidate materials of potential interest as components of fuels, propellants, or explosives. , Although Δ f H 0 (cr) may be estimated directly from molecular structure, i.e., without explicitly evaluating the gas-phase and sublimation enthalpies, such procedures are deprived of physical bases and rely mostly on empiricism. − Since the intra- and intermolecular contributions to Δ f H 0 (cr) depend on distinct interactions, they should ideally be evaluated separately.…”