摘要
针对水煤浆锅炉控制系统的非线性、强耦合、大时滞的特点，设计了一种神经网络预测控制方法。模型采用BP神经网络实现建模，其中网络结构在对水煤浆锅炉燃烧系统分析研究的基础上获得，并经优化数据训练后达到预期结果；预测控制算法采用一步预测滚动优化算法。仿真结果显示该方法控制效果良好，适合水煤浆锅炉的实时控制。
In response to the coal-water mixture boiler＇s characteristics of nonlinear, strong coupling and large dead time, a neural model predictive control method has been designed. The model is built by BP neural network, which is obtained by the research of combustion system of coal-water mixture boiler. The network meets the requirement after being trained by optimized data. Rolling optimization arithmetic adopts one step prediction. Simulation results show that the designed control system can meet the requirement of real running and be an effective control method.
出处
《洁净煤技术》
CAS
2009年第2期75-78,共4页
Clean Coal Technology
关键词
水煤浆锅炉
建模
神经网络
预测控制
coal-water mixture model, neural network
predictive control
