Analysis of traditional and neuro-fuzzy adaptive system of controlling the primary steam temperature in the direct flow steam generators in thermal power stations

Abstract

Methods of adapting automated control systems have been studied in order to determine the advantages of intellectual methods. It has been shown that the application of a self-learning neurofuzzy network enables one to implement adaptive setting parameters of a regulator and provide the given quality criteria and robotic systems’ ability to function in base and regulation modes in a relatively quick, simple manner. The need for many varying parameters in the system setting of the controlled object has been proved.