MODELLING

The use of process simulation for identification problem solution of mass transfer plant

A. A. Goncharov, A. Yu. Torgashov

Institute for Automation and Control Processes, Far Eastern Branch of the Russian Academy of Sciences, Vladivostok

Abstract: The identification problem of the mass transfer plant as crude oil distillation unit is considered. It is shown that the use of process simulation allows to improve the identified models that predict the quality of products, if there are measurement errors, a small range of variation of inputs and outputs as well as restricted sample of industrial data. The effectiveness of the proposed identification algorithm compared with ridge regression methods without the use of process simulation is shown.

Keywords: impulse response, constraints, soft sensor, crude oil distillation, process simulation, wavelet transformation.