CALCULATION OF THE PROPERTIES OF HYDROCARBON MIXTURES USING ARTIFICIAL NEURAL NETWORKS

This article discusses replacing the classical approaches to calculating properties of hydrocarbons and their mixtures with an artificial neural network. In work, a data sample was created, representing more than 18,000 variants model mixtures. Boiling points, molecular weights, densities were calculated for each mixture. On basis received training sample, network which allows based on limited set initial data: mass concentrations its components normal boiling points