| Popis: |
Air conditioning system is known as a multi-variable, large delay, nonlinear and uncertain system, and it is difficult to achieve the ideal performance by using the traditional PID control strategy. In order to improve the system performance and reduce energy consumption at the same time, a neural network based MPC controller is proposed in this paper. After establishing the predictive model by using neural networks based on experiment data, the online optimization programming method is utilized to produce the control sequence of the future. And only the first control law is applied to the system to improve the control effect. The simulation result at last shows that the proposed strategy has strong robustness and adaptive ability, high control precision, better and reliable control effect and other advantages. |
