UDC 681.3
INSTRUMENTAL METHODOLOGY TO FORECAST EMERGENCY
SITUATIONS IN TECHNOLOGICAL PROCESSES
S. A. Tkalich, Ph.D. (Tech.), Assistant Professor, Voronezh State Technical University, Voronezh, Russia;
orcid.org/0000-0001-8689-9798, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
The problem of choosing tools for constructing a compositional model of forecasting process accidents
is considered. The aim of the work is to develop an instrumental methodology for predicting emergency situations
of technological processes. The forecasting model is a composition of thermodynamic, linguistic and
neural network components. An integral criterion for accident-free control of technological processes is
used, which is a functional that simultaneously takes into account not only the current values of process parameters,
but also the time reserves available to accident-free control system for bringing a critical parameter
to its nominal limits. The justification of the choice of tools for constructing the model is given. Two tools
of mathematical and visual construction are used: MATLAB and MICROSOFT VISUAL STUDIO. A method
of integrating MATLAB and MICROSOFT VISUAL STUDIO is described. Block diagram of forecasting system
is presented. An example of a compositional model for emergency forecasting of chemical water cleaning
process is considered. The computational experimental research of the model is presented. Conclusions
about the operability of proposed instrumental methodology for multicomponent models of technological
processes emergency forecasting and its perspectives for modernization of automation systems are made.
Key words: forecasting, emergency, technological process, compositional model, integral criterion,
chemical water cleaning, real-time mode, dynamic graphing