BP神经网络PID控制在空调系统中的应用

Application of BP Neural Network PID Control in Air-Conditioning System

针对空调房间这样一个多干扰、大惯性、高度非线性系统控制性能优化较困难,传统的控制策略不但在控制精度、灵敏度以及系统稳定性上存在缺馅,而且能耗大。为了提高空调制冷和供暖效果,提出一种新的基于BP神经网络的PID控制方案,通过BP算法修正BP网络自身权系数,实现了PID控制器参数的在线调整。仿真结果显示BP神经网络PID控制系统比单纯的BP神经网络或PID控制系统建模时间短,系统更稳定,超调量更小,更适合应用于复杂的空调系统控制中。

For the problem of controlling an air-conditioned room with multi-interference,large inertia and highly nonlinear,the traditional control strategy has disadvantages in control precision,sensitivity and system stability,and also has large energy consumption.In this paper a new PID control scheme based on BP neural network was proposed.The weights of the BP network are conditioned,and then the PID parameters online adjustment is to be achieved.The simulation results show that the scheme is more stability,of smaller overshoots and shorter modeling time than BP neural network or PID control system.The BP neural network PID control system is more suitable for the complex air-conditioning system control.