变风量空调系统优化控制策略研究  

Research on Optimization Control Strategy of VAV Air Conditioning System

作　　者：李界家[1] 瞿睿[1] 

机构地区：[1]沈阳建筑大学信息与控制工程学院,辽宁沈阳110168

出　　处：《控制工程》2012年第5期790-794,共5页Control Engineering of China

基　　金：国家自然科学基金(60874103)

摘　　要：变风量空调系统是多变量,大滞后、非线性和不确定性的系统,普通的模糊神经网络控制已难以满足其多变量动态控制的要求,为改善变风量空调系统控制性能,本文提出了一种小波模糊神经网络预测控制方法,实现变风量空调的温湿度有效控制。通过小波神经网络预测器在线建立被控对象的数学模型,并用模糊RBF神经网络控制器对所得到的信息在线修正,优化控制器参数,从而改善系统的控制效果。仿真结果表明,小波模糊神经网络预测控制具有很强的鲁棒性和自适应能力,控制精度高,控制效果好,安全可靠等优点,具有广泛的应用价值。Aiming at variable air volume air conditioning system which is a multi-variable, large delay, nonlinear and uncertain sys- tem, the common fuzzy neural network control has been difficult to meet the requirements of its multi-variable dynamic control. In order to ＂improve VAV air conditioning system＇s performance, this paper proposed a wavelet fuzzy neural network predictive control, to control the temperature and humidity conditions of variable air volume air conditioning. Through wavelet neural network on line established mathematical model of controlled object, and using fuzzy RBF neural network controller on line corrected the information .we got, to op- timize the parameters of controller, thus to improve control effect of this system. The simulation results show that wavelet fuzzy neural network predictive control has stronger robustness and adaptive ability, high control precision, better and reliable control effect and other advantages.

关 键 词：变风量空调 小波模糊神经网络 小波神经网络 模糊RBF神经网络预测控制 

分 类 号：TP27[自动化与计算机技术—检测技术与自动化装置]