Real Component Mixture of Petroleum Cuts to be introduced to a Neural Network Reactor model

摘要

Petroleum cuts are very complex mixtures which contain very large number of components, from which only few can be usually identified. In this paper, a method is presented to introduce a range of petroleum fractions to the neural network model of a reactor. To do so, a "model" of the mixture should be used. Reactor feed type plays an essential role on the reactor product qualities. In order to introduce petroleum cuts with final boiling points of 865°F maximum to the neural network, a real component substitute mixture is made from the original mixture. Such substitute mixture is fully defined, it has a chemical character, and physical properties can be simply retrieved from databases. The mixture compositions are defined with the aid of optimization. The obtained TBP curves of several substitute mixtures are in good agreement with the experimentally obtained curves. Nine single carbon structural increments will be the representatives of 93 real component compositions in order to make the topology of the neural network smaller and hence to have less complex model. An NN model was also