Quantitative structure–property relationships for the reactivity parameters of acrylate monomers

Two artificial neural network (ANN) models have been developed for predicting reactivity parameters ln Q and e of acrylate monomers by performing density functional theory (DFT) calculations at the B3LYP/6-31G(d,p) level. The investigated results have demonstrated that the resonance and polar effect of acrylate monomers can be reflected by quantum chemical descriptors such as Mulliken and atomic polar tensor (APT) charges, the total dipole moment (μ), the lowest unoccupied molecular orbital energy (ELUMO) and the total energy (ET). Training sets root-mean-square (rms) errors (0.302 for ln Q and 0.127 for e) and prediction sets rms errors (0.175 for ln Q and 0.176 for e) are acceptable. Therefore, the quantitative structure–property relationship (QSPR) models based on quantum chemical descriptors are reliable in predicting ln Q and e values for unknown acrylate monomers with structures H2C1double bond; length as m-dashC2R4(C3OR5). The developed ANN models have been proved to be successful in predicting reactivity parameters ln Q and e.