Study On The Control System Of Intelligent Variable Frequency Air-Conditioner Based On Fuzzy Neural Networks Algorithms

Temperature control system of traditional air-conditioner depends on its sensors to monitor indoor temperature's changes and to control the compressor to run at a certain speed.Because indoor environment temperature is a large time-delay system of non-linearity and big inertia ,it is a discontinuous process to adjust temperature by traditional air-conditioner inevitably.The compressor can't adjust its running situation at an appropriate speed according to indoor temperature changes,which will result in dweller's uncomfortableness.In recent years,a new algorithms—fuzzy logic that can overcome PID's shortcoming,has been put into practice.With the help of it,air-conditioner,namely fuzzy variable frequency air-conditioner,has the intelligence character so that temperature is adjusted automatically,continuously,according to temperature's change indoors.All this will avoid frequent switches of the compressor which always appears on the traditional air-conditioner.Although fuzzy variable frequency air-conditioner,compared with the traditional air-conditioner,has been proven to be more effective in complex,time-varying and uncertain control system,it has a main problem,that is,its control parameters are set by expert's experience beforehand,mostly under standard environment.When indoor environment changes suddenly,the fuzzy variable frequency air-conditioner are controlled sharply at set membership functions and control rules.It will have a great effect on comfortability of human.The thesis tries to combine the fuzzy control and neural networks to control the compressor.The project designs the fuzzy neural networks model with six layers , which employes the error of temperature and the changing rate of temperature as input,the working frequency of compressor as output.Based on the theory research,the thesis designs the control system of the air-conditioner and does a experiment on the sample.The contents of the thesis are as following:1.Chapter one first introduce the shortcoming of traditional air-conditioner control method and fuzzy variable frequency air conditioner.based on it,the chapter introduces the current research situation both home and abroad,and raises the new project.2.Chapter two compares the design schemes and decides one of them as a control scheme for it,and introduces the hardware system briefly.3.Chapter three studies the fuzzy theory and neural networks ,and summarizes the combination method of the two theories.4.Chapter four designs the fuzzy neural networks controller for the air conditioner,and simulates it ,the result proves its intelligence.5.Chapter five designs the hardware of the indoor syetem with the chip PIC16F877,and designs the outdoor system with the chip SST89E564RD.6.Chapter six designs the software of the control system including the indoor control system software ,the outdoor control system software and the communication rules of the two ones.7.Chapter seven makes a research on the experiment and optimizes some parameters ,which proves the availability of the theory.8.Chapter eight summarizes the thesis and raises some points which need more research.The innovative points of this project:1.By the research on the current control technology of air-conditioner and analysis of its advantages and disadvantages,the thesis raises the new idea to control the compressor.2.The thesis studies the fuzzy neural network model and designs the hardware and software of the intelligent variable frequency air-conditioner.3. By the experiment, the thesis optimizes some parameters,which set the nice foundation for the new technology.