变风量空调系统机组侧的神经网络建模和解耦控制的仿真实验研究

Simulation Study Based on Neural Networks for Modeling and Decoupling Control of Variable-air-volume Air Handling Units System

针对变风量空调系统机组侧存在强耦合、非线性和时变性的特点,根据实际的实验条件,对机组侧两个回路(送风静压和二氧化碳浓度控制回路)进行了仿真实验研究,结果表明:以神经网络为工具,对多输入多输出非线性动态系统的逆模型进行辨识,具有相当高的精度;同时开环解耦效果也很好,为实际的解耦控制系统设计奠定了基础。

Since VAV system is multivariable,strongly coupled,nonlinear and time variant,the simula- tion study based on neural networks has made for the two loops(static pressure of supply air loop and CO_2 loop)of the AHU(Air Handling Unit).The results show that neural networks i- dentification has high precision for the MIMO nonlinear dynamic system.The result of open loop decoupling is good and can be the reference for the real decoupling control system.