Multiple Linear Regressionamp;horbar;Artificial Neural Network Hybrid Model Predicting Heat Capacity of Ideal Gas of Organic Compound

摘要

The present invention is hydrogen (H), carbon (C), nitrogen (N), oxygen (O) , sulfur (S), such as composed of more than five kinds of elements and the number of the atoms of the pure compound consisting of not more than 25 molecules, except for hydrogen gas heat capacity (Heat Capacity of Ideal Gas) the mathematical model to predict with a high degree of accuracy, provided. As an example of the model of the QSPR (quantitative structure-property relationship) model, for a number of the organic compound satisfying the above conditions are experimental values of the ideal gas heat capacity is known, various presenter molecule (molecular descriptor) some of the independent variables, the ideal gas heat capacity of the dependent variable in a multiple linear regression model many (multiple linear regression model) are among the best of the genetic algorithm (genetic algorithm) was determined after using this model to include the presenter of the molecule the ideal gas heat capacity, receives the value of the output ANN (artificial neural network) was further enhanced by the construction of multiple linear regression forecasting performance - a hybrid artificial neural network model (hybrid model). If you know the specific values of the molecules presenters included in the model any molecular way, allows to predict the ideal gas heat capacity of pure compounds made by these molecules. As such, the present invention can maintain the cost and time saving experiment to provide a method for giving a more predictable and reliable gas heat capacity value 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. ;