Multiple Linear Regressionamp;horbar;Artificial Neural Network Model Predicting Absolute Entropy of Ideal Gas for 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 five kinds of standard conditions is more than the number of the atoms of the pure organic compound consisting of not more than 25 other than the hydrogen gas molecules absolute entropy (Standard State Absolute Entropy of Ideal Gas) high fidelity provides a mathematical model for predicting a. The model is, for a number of organic compounds which satisfy the condition of the experimental data than the standard state entropy gas never known, any of a variety of molecules presenter as an independent variable, the absolute gas over the standard state entropy Multiple linear regression model to many as the dependent variable (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 in this model over the standard state gas by constructing artificial neural network (artificial neural network) that outputs the absolute entropy which further enhance the predictability multiple linear regression-ANN hybrid model (hybrid model) as QSPR (quantitative structure-property relationship) is an example of the model, the model If you know the specific value of any molecule that contains the molecular presenter way, gives to predict the absolute entropy of an ideal gas consisting of a standard state of a pure compound in the molecule. As such, the present invention is by giving haejueo saving the cost and time to the experiment to provide a way to estimate the value of the least reliable gas standard conditions for the absolute entropy of a number of organic compounds of the experimental conditions is unknown, the relevant industry effects such as the birth of the research and development activities easily. ;