摘要 |
PURPOSE: A hybrid MLR-ANN model is provided to predict lower flammability limit volume percent of pure organic compounds and to improve prediction performance. CONSTITUTION: A molecular descriptor value for LFLVP(lower flammability limit volume percent) of hydrocarbon series compounds is prepared. Experimental data is separated into training and test groups. The optimal MLR(multiple linear regression model) for the training group is detected. The optimal ANNM(artificial neural network model) is detected after diving the total sample into three groups. |