风冷制冷机组的多变量模糊控制研究

针对一个多输入多输出、非线性复杂系统明显的非线性热力学耦合特性，采用模糊控制与神经网络相结合的方法，提出一种具有结构和参数学习能力的自组织模糊神经网络控制器，在控制过程中通过采样数据在线学习，调整网络结构，产生模糊控制规则并调整规则的参数，使得控制器具有模糊控制的特点，又有神经网络学习的能力．通过对风冷制冷机组控制试验的结果表明，该控制器能够达到同时控制蒸发压力和过热度的目的．

Study on Multi-Variable Fuzzy Neural Control for Air Cooled Refrigeration System

For a multi-input multi-output and nonlinear complex system, a selt-organized fuzzy neural network controller with the capacity of construction and parameter learning was proposed based on the analysis of fuzzy and neural network control. It can adjust the structure of net, pro duce the rules, and regulate the parameters. This controller is easily structured with the feature of fuzzy control and also possesses the learning ability of neutral network. The experimental results for an air-cooled refrigeration unit show that the present controller can modulate the evaporation pressure and the superheating degree.