PREDICTION OF CRITICAL-TEMPERATURES AND PRESSURES OF INDUSTRIALLY IMPORTANT ORGANIC-COMPOUNDS FROM MOLECULAR-STRUCTURE

Quantitative-structure property relationships methods are used to deve lop mathematical models to predict critical temperatures and pressures of a diverse set of organic compounds taken from.the Design Institute for Physical Property Data (DIPPR) database. Each compound is represe nted with calculated molecular structure descriptors that encode its t opological, electronic, geometrical, and other features. Subsets of de scriptors are selected with simulated annealing and genetic algorithms . Models to predict the critical properties are constructed using mult iple linear regression analysis and computational neural networks with errors comparable to the experimental errors of the critical property data.