Research Of Thermal Comfort Predict And Control Algorithms Of The Air Conditioning

With the improvement of living standards, people’s life quality requirements arealso rising. In modern life, people’s work, entertainment, and life are in the room mostof the time, therefore, the demand for indoor environmental quality are increasinglyhigh. To meet people’s pursuit of a comfort, energy saving and healthy indoorenvironment, this paper has done some research on thermal comfort predictivemodeling of the indoor environment and the application of thermal comfort control inthe air conditioning system.Aiming at the problem that thermal comfort prediction, which is a complicatednonlinear process, can not be applied to real-time control of air conditioning directly,this paper proposes a thermal comfort prediction model based on the improvedParticle Swarm Optimization-Back Propagation (PSO-BP) neural network algorithm.By using PSO algorithm to optimize initial weights and thresholds of BP neuralnetwork, the problem that traditional BP algorithm converges slowly and sensitive tothe initial value of the network has been improved in this prediction model.Meanwhile, for the standard PSO algorithm prone to premature convergence, weaklocal search capabilities and other shortcomings, this paper puts forward someimprovement strategies to further enhance the PSO-BP neural network capabilities.Experimental results show that: the thermal comfort prediction model based on theimproved PSO-BP neural network algorithm has faster algorithm converges andhigher prediction accuracy than the traditional BP model and stand ard PSO-BP model.Aiming at the problem of the application of thermal comfort control in the airconditioning system, this paper has done some comparative analysis research oncontrol variables, control modes, control algorithm and so on, and eventuallydetermine the temperature and wind speed as the control variables of system, anddetermine the thermal comfort direct control combined with intelligent fuzzy controlalgorithm as the control way to achieve thermal comfort control of the indoorenvironment. Meanwhile, through the research on design steps and design points offuzzy controller, this paper designs thermal comfort fuzzy controller, and achieves thesimulation of thermal comfort fuzzy controller in the air conditioning system.Simulation results show that the performance of the fuzzy controller designed in thispaper is better than conventional PID controller, and air conditioning system using thethermal comfort fuzzy control than using the conventional temperature-control can better control thermal comfort, and can provide a more comfortable indoorenvironment.