基于DRNN网络的强排式燃气热水器自整定PID控制  

Adaptive PID Control Strategy of Emission Constrainedly Gas-fired Water Heater Based on DRNN

作　　者：杜福银[1] 

机构地区：[1]西南交通大学电气工程学院,四川成都610031

出　　处：《工业加热》2010年第4期31-34,共4页Industrial Heating

摘　　要：强排式燃气热水器是一个耦合的两输入两输出系统,随机负荷的变化又表现出参数快时变的特性。固定参数PID控制难以适应此系统控制要求,因此,提出一种基于回归神经网络(DRNN)的两输入两输出PID控制器结构,给出了DRNN神经网络参数学习算法和PID控制器参数自整定算法。计算机仿真结果验证了该控制策略可行性,这为以后进一步研究奠定了基础。Emission constrainedly Gas-fired water heater system is a coupling two input two output system, and has a property of fast parameter variance while the unit load changes. Conventional PID controller which is tuned at typical operating point can hardly work well at different unit load, so that a two input two output PID controller structure based on Diagonal Recurrent Neural Network （DRNN） is proposed, besides, the learning algorithms of the parameters of DRNN and PID controller are proposed. Finally, the validity of the proposed control strategy is revealed via computer simulations, and which is foundation for further study.

关 键 词：强排式燃气热水器 PID控制 回归神经网络(DRNN) 计算机仿真 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]