Development of a Neural Network for Controlling the Polymerization of Isoprene in an Isopentane Solution Using a Virtual Analyzer

At the moment, the process of polymerization of isoprene in an isopentane solution makes it possible to obtain a semi-product for the production of synthetic rubber. It is used instead of natural both independently and in combination with other elastomers in the manufacture of almost all rubber products. To control the quality of the technological process, the development of a virtual analyzer is required. A neural network controller, a predicted virtual analyzer of the quality indicator of the flow rate and temperature of the catalytic complex, will increase the adaptability of the system. As a result of this work, a virtual analyzer was developed that continuously predicts the quality indicator of the process in the form of a mass fraction of the catalytic complex after the polymerizer and a neural network for regulating the technological parameters of isoprene polymerization in an isopentane solution.