Automated methods of controlling the flow of syrup in the evaporation station with subsystems of decision support and forecasting

Abstract

Introduction. The purpose of the presented study is to substantiate the methods of regulating the consumption of syrup in the evaporation station with a forecasting subsystem, which will allow to predict the behavior of the system and the decision-making subsystem, which will reduce the influence of the human factor on the course of the evaporation process. Materials and methods. The work of the evaporation station with the subsystem of forecasting and decision support when regulating the consumption of syrup was researched. In the automation scheme for regulating the flow rate of syrup, induction flow meters are used as a sensor. Pneumatic saddle valves with a built-in throttle and an electro-pneumatic converter were used as actuators. Results and discussion. The use of neural sensors occurs only in certain specific cases of intelligent control of the evaporation process, there is no data comparing the use of intelligent regulators with classical ones, the possibility of combining the work of several types of intelligent regulators, as well as clear means of predicting their work and supporting decision-making. Therefore, in this paper, a decision-making subsystem has been justified, which made it possible to assess the priorities of user requests when using a human- machine interface. The highest priority was given to the request to display information on possible changes to the adjustment parameters of other control circuits. The forecasting method was also used to compare the methods of regulating the flow rate of syrup in the apparatus, which made it possible to predict the behavior of the system during the formation of the control action and display the finished forecast on the operator's screen and, thus, increase the efficiency of the evaporation station. Statistical data on the behavior of the contours of the automation system in different modes of operation using intelligent and classical regulators were collected, a model for predicting the operation of an evaporation station by the method of local tendency was built and a forecasting algorithm was developed. The accuracy of the obtained forecasting model is also evaluated. The accuracy of the forecasting model was 98% for the PID controller, 95% for the neural fuzzy regulator and 96% for the neural network. Conclusions. The model for predicting the operation of the evaporation station is characterized by high accuracy in general, but during the occurrence of oscillations in the transition process, there is an insignificant delay in predicting these fluctuations. The most important in the output of information by the decision-making subsystem is the function of displaying information about the possible changes to the parameters of regulation of other control circuits.