Multiple Linear Regression-Artificial Neural Network Hybrid Model Predicting Critical Temperature of Pure Organic Compound

摘要

The present 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 to predict with high accuracy the critical temperature of the pure organic compound, the number of atoms consisting of not more than 25 other than the hydrogen molecule (Critical Temperature). The model is for a number of organic compounds is the experimental value of the critical temperature that satisfies the condition is known, any of a variety of molecules presenter (molecular descriptor) as independent variables, many of the critical temperature as a dependent variable, multi- linear regression 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 received critical temperature the output of ANN (artificial neural network) was further improved by configuring multiple linear regression forecasting performance - as a hybrid artificial neural network model (hybrid model) QSPR (quantitative and structure-property relationship) example of a model, if you know the specific values of the molecules presenters included in the model any molecule that way, the prediction gives the critical temperature of the pure compound made by the molecule. 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 critical temperature and reliable even in the condition of a number of organic compounds are known to the experimental data, the research and development of related industries lays the effect of such readily. ;