用一个多层前向神经网络，采用反向传播算法依据控制要求实时输出Kp、Ki、Kd，依次作为PID控制器的实时参数，代替传统PID参数靠经验的人工整定和工程整定，以达到对大迟延主气温系统的良好控制。-We use a multilayer feedforward neural network using back propagation algorithm and based on control requirements.This net can real-time output Kp, Ki, Kd as the PID controller parameters ,insteading of the traditional PID parameters determined by experience. So it can obtain good control performance .