A Research to Retention Index of Saturated Alcohols Based on BP Neural Networks

摘要

A model of back_propagation artificial neural network based on Levenberg_Marquardt algorithm for determining the relations between the structure of alcohols and their chromatographic retention indix has been set by means of topological indices. The forecasting results are good when it makes use of the BP neural network to carry out the forecasting, the correlation coefficient has reached 0.999. Therefore,the model is a more satisfactory method for prediction of chromatographic retention indices of organic compounds.