Application Study Based On ANFIS In Temperature Control System

Temperature control system is widespread in the industrial field at present, and in a very important position. The control object of temperature control generally has the characteristic of large inertia, large delay and it’s parameters are time-varying and uncertain. For temperature control system, it’s very important that whether the control system can adjust timely to maintain the temperature within a small error range when the disturbance occurs outside.This paper firstly describes the background of temperature control at the present stage, and adaptive neural fuzzy control system (ANFIS) theory has been studied, finally we select adaptive neural fuzzy inference system of Sugeno model. ANFIS combines the advantages of both fuzzy control and neural networks, which not only doesn’t require a precise mathematical model of the controlled object, but also has a strong self-learning ability, it can be optimized and adjusted to optimal by itself. Based on the analysis of the controlled object, we make the adaptive neural fuzzy inference system applied to the actual temperature control, design and construct the controller using the dedicated toolbox of Matlab/Simulink, which is robust and flexible, and connect with the actual electric heating furnace rather than stay in the level of simulation.Through the actual control experiments of electric heating furnace using the adaptive neural fuzzy controller, and compared with the resules of conventional PID and fuzzy control algorithm, we conclude that the adaptive neural fuzzy controller could not only achieve the intelligent automatic control of temperature, but also have the high control precision, and the range of error is very small. It shows that this method has a very distinct industrial value.