摘要 |
PURPOSE: An MLR-ANN model for predicting a flash point is provided to improve prediction performance. CONSTITUTION: A molecular descriptor value for a flash point of hydrocarbon series compounds is prepared. The test data is separated into training and test groups. The optimal MLRM(multiple linear regression model) for the training group is detected. The optimal ANNM(Artificial Neural Network Model) is detected after diving total sample into three groups. |