Research In Central Air Condition Energy Saving Based On Neural Network

With the development of intelligent buildings, the control algorithm and precision of the control system is gradually improved. After the 80’s years the theory of artificial neural network (ANN) sprang up that is a new subject based on the structure and function of brain, which can be applied to the artificial intelligence,mode identification, simulation of biology and advanced control etc. It is attatched importance that artificial neural network is applied in the heating, ventilation and air conditioning field. The PID controller has many advantage such as simple structure,parameter of certain physical meaning, good dynamic and static characteristic and so on. The conventional PID is not also ignored. The combination of the broad-using PID controller and ANN is a way of intelligent control.Then, the paper induced that VAV air-condition system adapt load shift by changing air capacity, and power of blower changed at the same time, with the result that it could save fifty percent power. Because the issue about pressure of duct and state of blowing was often neglected, a control of constant pressure to adjust air capacity based on fuzzy neutral network was presented in this paper. Compared with conventional PID control and ordinary fuzzy control strategy, the method has many advantages.the paper presented a scheme of temperature controller in central air conditional room, which was based on another fuzzy neural network control of self-adjusted PID parameters. the result from simulation of MATLAB shows the validity of the system design oThen, the paper introduces a design of central air-conditioning temperature control system based on CAN bus. The whole structure of the temperature control system is proposed firstly; then the paper expresses the way of communication between PC and MCU; and the paper focuses on proposing the hardware and software design of the temperature control system.