The Research On Building Heating Indoor Temperature Forecasting And Controlling

With the increasingly serious environmental and energy problems in the world,saving energy and protecting the environment has become one of the most important tasks for governments.Building energy consumption accounts for 1/5 of the world's total energy consumption.The construction system of our country's energy consumption accounted for more than 1/3 of the total energy consumption in the building system,all of the energy consumption in the heating energy consumption accounted for about 60%,so the heating energy consumption of building waste is most serious,and the energy saving potential.At present,most of the existing building heating systems lack of advanced control methods and the level of automation is not high,not only caused a waste of energy,but also reduces the user's comfort.The building heating system is a great inertia,complex nonlinear system,a nonlinear relationship between the degree of indoor temperature and outdoor environment,building envelope and heating facilities to provide heat,using mechanism modeling involves many parameters and difficult,the prediction results have big errors.By using the artificial neural network does not depend on the model itself and good nonlinear approximation ability,choose BP(Back Propagation)and RBF(Radial Basis Function)artificial neural network method,according to the collected K moment K-T moment of indoor temperature,indoor temperature,the temperature difference,K moment control state,outdoor temperature and illumination respectively for building K+T time indoor temperature modeling and forecasting.The results show that the RBF neural network is more stable and the mean square error is lower than BP neural network 10.5%.Based on the prediction of indoor temperature,it is necessary to adjust the indoor temperature.In this paper,an expert controller is designed based on the actual situation of building heating in a university in Dalian.Firstly,the control strategy of building heating is analyzed.According to the different heating requirements of different buildings,the strategy of time-sharing heating is adopted;According to the characteristics of large inertia and large time delay in room temperature control,this paper adopts the method of combining the temperature model with fuzzy control;At the same time,in order to ensure the safety of heating,a series of protection strategies are designed.Then based on the wireless communication technology in the design of a building heating expert control platform,the platform has remote monitoring,fault and emergency handling capabilities,greatly improving the automation level of building heating,ensure the safety and comfort of the heating.Finally,the experimental analysis,the use of expert control in a timely manner to adjust the indoor temperature,reduce the overshoot,to achieve a reasonable use of heat,the average energy saving rate can reach 9.23%,and has good social value and economic value.