Intelligent Control And Its Application In LED Lab’s Temperature And Humidity Environment

There is a certain time-delay phenomenon in the process of the practical application,and the time-delay has the characteristics of varying and unknown. With the continuous development of industry such time-delay of industrial production has not been ignored, this has time-delay control phenomenon. Conventional control has failed to meet the real needs about time-delay phenomenon, which will affect the control quality and economic benefits. This study therefore not only has a strong time-delay value applied in theory but also in terms of practical applications also exist.In our paper, an intelligent control method has been studied for the pure time-delay appearance. It combines two methods between fuzzy control and neural network and then studies an adaptive neuron fuzzy inference system ANFIS. In this thesis, fuzzy control and neural network have been common known and been combined. Analysis of the similarities of the two theories, research and illustrates the combination of the two applies in the fuzzy neural network systems. We learn the structure of ANFIS and the density clustering algorithm. We analyses the hybrid learning algorithm for the design of the controller structure. Fuzzy neural network controller and intelligent PI controller are used.According to the results, specific evaluations have been made about experiment and controller. Finally, in this paper, adaptive neuron fuzzy inference system is applied to the control of the temperature and humidity of the environment, after building a good system of the test platform, we describe the design, the process of the running system, the control environment, the setting of control interface and results of the control interface.Using this design method not only to improve the problem that mathematical model is difficult to establish in the conventional control system, meanwhile, the stability of the system is greatly improved, especially with non-linear characteristics of the system. Intelligent control methods studied in this paper on the simulation presented good results, showing a strong adaptability.