ИСТИНА

There are presented methods for producing acetylene. The classical mathematical model for the production of acetylene by oxidative pyrolysis of natural gas is complex and inconvenient from the point of view of realizing the goals of process control. It is shown that the use of a neuro-fuzzy (hybrid) model makes it possible to improve the quality of the control and management of the process of oxidative pyrolysis in the production of acetylene. Statistical data obtained at the current production of acetylene were used as initial data in the development of the fuzzy model. The structure of a neuro-fuzzy model of the Sugeno type for an oxidative pyrolysis reactor has been developed, and the type of membership functions has been substantiated. The adequacy of the obtained model was verified by a comparative analysis of the results of simulation modeling of the process with different initial data and statistical data obtained in the current production. Recommendations are given on how to use the resulting model to achieve the goals of process control.