Justification of the neuro-fuzzy regulation in evaporator plant control system

Abstract

Introduction. The purpose of the study is the determining the use of which type of regulation will achieve the best indicators of quality control for the regulation of the evaporator plant.Materials and methods. The system of management of a five-body evaporator plant of a sugar refinery was researched. The method of synthesis of modal control was used for evaluating the results of the research.Results and discussion. A comparison between FID and fuzzy regulator was made. Regulation of such responsible parameters as levels of concentrated juice in evaporator plant bodies, which directly affect the quality and value of manufactured products, was implemented. First, in the space of states in Matlab environment, a mathematical model was developed and the results obtained regarding the variation of the problem with respect to the initial conditions and perturbations were obtained. Due to them one can conclude that the time of the transition process is within the range from 0.8 to 1.2 seconds. However, the deviation levels in the evaporator plant bodies are too high. Secondly, a mathematical model with a PID-regulator was developed and transition processes for control schemes across all control channels were obtained. In this case, the time of transition processes is within the range of 60 seconds along the channel X1 to 145 seconds along the channel X2, but this led to a significant decrease in the deviation of levels in the bodies. Thirdly, a mathematical model with a fuzzy regulator is developed and transition processes for control schemes in all control channels were obtained. In this case, the time of transition processes is within the range from 50 seconds along the channel X1 to 110 seconds along the channel X2, which is the better result if compared to the PID regulator. Compared with the previous study, the levels in the bodies also significantly decreased. Therefore, the use of neurofuzzy regulation leads to an increase in qualitative parameters of the process compared with the system with PID-regulators.Conclusions. The scientific substantiation of the feasibility of using neuro-fuzzy regulation during the implementation of optimal control systems is the novelty of the research results.

Порівняння Роботи Підсистем Прогнозування В Автоматизованій Системі Керування Випарним Апаратом

“…Рис. 4 За допомогою алгоритму локальних тенденцій можна проводити оцінку локальних тенденцій з використанням лінгвістичної та числової форм [10], де Ркінцева множина точок на інтервалі n (кінцева множина тенденцій), STчасовий інтервал протяжності нечіткої тенденції. Для роботи даного алгоритму необхідно перетворити початковий часовий ряд на нечіткий часовий ряд [20], використовуючи модель, наведену на рис.…”

Motion Trajectory Control System for Production Line Robots Based on Variable Domain Fuzzy Control

“…Du et al [19] applied genetic variable universe fuzzy controller to the control of train lateral semi-active suspension system and achieved good control effect. Hrama et al [20] studied the temperature control of evaporation source by using the variable universe fuzzy adaptive PID method. Wang et al [21] analyzed the approximation conditions of variable universe fuzzy controller.…”