神经网络PID控制器在温度控制中的应用

The Use of GA-BP Neural Network in Temperature Control

现代智能建筑中空调的温度控制是非常重要的环节,利用神经网络来控制温度是目前一种比较先进的控制方法。针对神经网络中BP算法易陷入局部极小的缺点,利用了遗传算法具有全局寻优的优点,将二者结合起来形成混合GA-BP算法来训练神经网络;通过算法比较和实例结果验证,表明该算法可以有效、可靠的实现空调的温度控制。

The temperature control is an important link in modern intelligent building,and the neural network controlling is now a advanced control method.In order to overcome the shortcomings that BP algorithm is usually trapped to a local optimum,we use genetic algorithm to training neural network with the advantage of the globe optimal searching of genetic algorithm.This algorithm can effectively and reliably be used in the by comparing the two algorithms and analyzing the results of real examples.