城市固废焚烧过程炉温非线性模型预测控制

Nonlinear model predictive control of furnace temperature for a municipal solid waste incineration process

中文关键词  城市固废  炉温  非线性模型预测控制  随机配置网络  海鸥优化算法  设定值评价与学习

英文关键词  municipal solid waste  furnace temperature  nonlinear model predictive control  stochastic configuration network  seagull optimization algorithm  set value evaluation and learning

中文摘要

      为实现城市固废焚烧(MSWI)过程炉温的稳定控制, 本文提出一种炉温非线性模型预测控制(NMPC)方法.首先, 采用炉排温度与一次风温作为炉温控制的中间变量, 将串级控制策略融入到 NMPC 中, 以获得一种新的MSWI炉温控制结构. 其次, 利用随机配置网络(SCN)离线建立炉温静态非线性预测模型, 并通过递推最小二乘法在线更新SCN隐含层神经元的输出权值, 从而建立炉温动态非线性预测模型. 最后, 将改进的海鸥优化算法同设定值评价与学习模型相融合, 得到一种改进的滚动优化策略, 以提升NMPC滚动优化的求解性能. 实验结果表明, 炉温动态非线性预测模型可以准确预测炉温, 提出的控制方法具有良好的自适应性及鲁棒性, 能够实现MSWI过程炉温的平稳控制.

英文摘要

      To realize the stable control of furnace temperature in a municipal solid waste incineration (MSWI) process, a nonlinear model predictive control (NMPC) method for furnace temperature is proposed in this paper. First, using the grate temperature and primary air temperature as the intermediate variables, a new MSWI furnace temperature control structure is obtained by integrating the cascade control strategy into NMPC. Then, the stochastic configuration network (SCN) is used to establish the furnace temperature static nonlinear prediction model offline, and the output weights of the hidden layer neurons of the SCN are updated online through the recursive least square method, so the furnace temperature dynamic nonlinear prediction model is established. Finally, an improved rolling optimization strategy is obtained by integrating the improved seagull optimization algorithm with the set value evaluation and learning model, which is used to improve the solution accuracy and efficiency of NMPC rolling optimization.The experimental results show that the dynamic nonlinear prediction model of furnace temperature can predict the furnace temperature accurately. The proposed control method has good adaptability and robustness, and can realize the stable control of furnace temperature in the MSWI process.