多区域暖通空调(heating,ventilation and air conditioning,HVAC)系统相比基础的单区域空调系统能够更好地描述空调房间各区域内的动态热响应过程,传统模型预测控制(model predictive control,MPC)算法能较好实现温湿度控制,但室内区...多区域暖通空调(heating,ventilation and air conditioning,HVAC)系统相比基础的单区域空调系统能够更好地描述空调房间各区域内的动态热响应过程,传统模型预测控制(model predictive control,MPC)算法能较好实现温湿度控制,但室内区域之间传热系数的耦合作用,使得模型中存在不确定性扰动,这种情况下,传统MPC算法难以实现控制。针对这类问题,设计了一种基于线性矩阵不等式的改进鲁棒模型预测控制(robust model predictive control,RMPC)策略,将模型中存在的扰动用多胞不确定集来表示。最终将一个无穷时域控制量无限的最小化最坏情况的min-max问题转化为有限时域内求解状态反馈控制率的问题,同时考虑了状态与输入约束条件,通过在线实时求解即可得到每一时刻最优解。最后对多区域HVAC空调房间系统进行仿真,结果表明本文算法下3个区域温湿度的跟踪精度较高,抗干扰能力也较强。展开更多
For discrete-time T-S fuzzy systems, the stability and controller design method are in-vestigated based on parameter-dependent Lyapunov function (PDLF). T-S fuzzy systems di?er fromnon-fuzzy systems with polytopic des...For discrete-time T-S fuzzy systems, the stability and controller design method are in-vestigated based on parameter-dependent Lyapunov function (PDLF). T-S fuzzy systems di?er fromnon-fuzzy systems with polytopic description or multi-model description in that the weighting coef-ficients have respective meanings. They, however, have stability aspect in common. By adopting astability condition for polytopic systems obtained via PDLF, and combining the properties of T-Sfuzzy systems, new results are given in this paper. An example shows that by applying the newresults, the stability conditions that can be distinguished are less conservative.展开更多
文摘多区域暖通空调(heating,ventilation and air conditioning,HVAC)系统相比基础的单区域空调系统能够更好地描述空调房间各区域内的动态热响应过程,传统模型预测控制(model predictive control,MPC)算法能较好实现温湿度控制,但室内区域之间传热系数的耦合作用,使得模型中存在不确定性扰动,这种情况下,传统MPC算法难以实现控制。针对这类问题,设计了一种基于线性矩阵不等式的改进鲁棒模型预测控制(robust model predictive control,RMPC)策略,将模型中存在的扰动用多胞不确定集来表示。最终将一个无穷时域控制量无限的最小化最坏情况的min-max问题转化为有限时域内求解状态反馈控制率的问题,同时考虑了状态与输入约束条件,通过在线实时求解即可得到每一时刻最优解。最后对多区域HVAC空调房间系统进行仿真,结果表明本文算法下3个区域温湿度的跟踪精度较高,抗干扰能力也较强。
文摘For discrete-time T-S fuzzy systems, the stability and controller design method are in-vestigated based on parameter-dependent Lyapunov function (PDLF). T-S fuzzy systems di?er fromnon-fuzzy systems with polytopic description or multi-model description in that the weighting coef-ficients have respective meanings. They, however, have stability aspect in common. By adopting astability condition for polytopic systems obtained via PDLF, and combining the properties of T-Sfuzzy systems, new results are given in this paper. An example shows that by applying the newresults, the stability conditions that can be distinguished are less conservative.
