温室小气候建模方法研究现状与展望

The Actuality and Research Situation on the Modeling Methods of the Greenhouse Microclimate

综述了温室小气候模型的发展现状,包括依据能量和物质平衡的物理建模、线性和非线性的系统辨识建模,如递归最小二乘算法、神经网络等。并分别采用物理建模和神经网络系统辨识方法,通过实验对温室小气候进行建模与仿真。同时,指出了这些方法存在的一些局限性,最后就温室小气候杂交建模方法的发展趋势进行了展望。

The development of the greenhouse microclimate model is summarized. These models could be based on energy and mass flows equations, derived by using a system identification approach using linear and non-linear techniques, such as the recursive least squares algorithms, neural networks to tune the parametric models. Experiments are used to emulating the greenhouse microclimate based on energy and mass flows equations and neural networks .And their drawbacks are pointed out. The development tendency of greenhouse microclimate model is expected.