Multiple Linear Regression-Artificial Neural Network Hybrid Model Predicting Critical Pressure 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 mathematical models for predicting the number of atoms other than hydrogen at a high accuracy the critical pressure (Critical Pressure) of the pure organic compound consisting of not more than 25 molecules. The model is for a number of organic compounds is the experimental value of the critical pressure satisfying the above condition is known, any of a variety of molecules presenter (molecular descriptor) as independent variables, that the critical pressure in many multi-dependent variable linear regression model (multiple linear regression model) obtained after using a genetic algorithm (genetic algorithm) that one of the best, receives the value of the molecules presenters included with this model of artificial neural network to output the critical pressure (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 included in the model that the presenter any molecule way, gives to predict the critical pressure of the pure compound made by this 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 pressure, and reliable for the number of the organic compound of the experimental conditions is unknown, the research and development of related industries lays the effect of such readily. ;