Multiple Linear Regressionamp;horbar;Artificial Neural Network Model Predicting Flash Point of Pure Organic Compound

摘要

invention is hydrogen (H), carbon (C), nitrogen (N), oxygen (O) , sulfur (S) consists of elements, such as less than 5 kinds and provides a mathematical model for predicting the flash point (flash point) of the pure organic compound, the number of atoms consisting of not more than 25 other than the hydrogen molecule with a high degree of accuracy. The model is, for a number of organic compounds is the experimental data of the flash point that satisfies the condition is known, any of a variety of molecules presenter (molecular descriptor) as independent variables, many multiple linear regression to the flash point as the dependent variable model (multiple linear regression model) are among the best that the genetic algorithm (genetic algorithm) was determined after using this model to include molecular presenter of the value of the input receives the output of the flash point ANN (artificial neural network) to As further improve the prediction performance was QSPR (quantitative structure-property relationship) model by configuration, if you know the specific values of the molecules presenters included in the model that whatever molecules, gives to predict the flash point of the pure compound is composed of molecules . As such, the present invention can maintain the cost and time savings by giving the experiment to provide a way to predict the value of the flash point and reliable for the number of the organic compound of the experimental conditions is unknown, facilitate the research and development of related industries lays effects such as that. ;