Hybrid CMAC-PID Controller in Heating Ventilating and Air-Conditioning System

Abstract

The controlled objects are modeled in heating, ventilating and air-conditioning (HVAC) system, mainly including the heat exchanger and the air-conditioning space. The HVAC system has large inertia, pure lag and nonlinear characteristic. The uncertain disturbance factors affect the control performance. To obtain better performance in HVAC system, this study proposes a hybrid Cerebellar model articulation controller (CMAC)-PID control system, which combines the CMAC neural network and general PID control. This method realized the feedback control by using traditional PID controller to enhance the stability and reject the disturbance and realized the feed forward control by using CMAC neural network to increase the response speed and control precision in HVAC system. The simulation results show the hybrid CMA-PID control system possesses the advantages of high precision, realtime standard, strong ability of anti-interfere and robustness.