The QSPR Study for the Net Heat of Combustion of Esters based on Ant Colony Optimization

摘要

A quantitative structure-property relationship (QSPR) model for predicting the standard net heat of combustion (ΔH_c~o) was developed based on the ant colony optimization (ACO) method coupled with the partial least square (PLS) for variable selection. Five molecular descriptors were screened out as the parameters of the model, which were finally constructed using multi-linear regression (MLR) method. A reliable model of five parameters for predicting the ΔH_c~o of esters was established, which can provide some help for engineering to predict the ΔH_c~o based on only their molecular structures.