摘要
热风炉燃烧系统是复杂多变量系统,基于最优控制策略,对具有耦合作用的多变量热风炉燃烧系统进行解耦。通过引入神经网络环节,将强耦合多变量系统转化成多个独立的单变量系统,对每个单变量系统进行预测函数控制,实现热风炉燃料流量的最优控制和拱顶温度及废气温度的平稳控制。解耦控制采用前馈补偿器解耦,解耦补偿器采用BP神经网络结构。现场实际应用结果表明,该控制策略具有较好的动态跟踪特性,能满足复杂多变量控制系统的实时控制要求。
The combustion system of hot stove is a complex and multivariable system. The multivariable combustion system of hot stove with coupling relation is decoupled based on optimization control strategy. The multivariable system with strong coupling quality is changed into several independent single variable system by neural network sector. The predicting function control is conducted in every single variable system. The optimization control of hot stove fuel and stable control for dome temperature and waste gas temperature are realized. Feed forward compensator decoupling is used in the decoupling control. The BP neural network structure is adopted in the de- coupling compensator. The practical application result shows that the control strategy has better dynamic tracking property and can meet the requirements of real time control for complex multivariable control system.
出处
《计算机工程与设计》
CSCD
北大核心
2009年第22期5218-5220,共3页
Computer Engineering and Design
基金
北京市教育委员会科技发展计划基金项目(KM200710028017)
关键词
燃烧控制
神经网络
补偿器
解耦算法
最优策略
combustion control
neural network
compensator
decoupling algorithm
optimization strategy
