基于改进型粒子群优化算法的CFB锅炉床温建模

Modeling of CFB Boiler Bed Temperature Based on Improved PSO Algorithm

对于循环流化床(CFB)锅炉的自动控制优化,床温动态模型的建立和动态特性分析有着重要的意义。采用粒子群优化(PSO)算法对床温动态模型进行辨识,并且使用自适应惯性权重策略解决标准算法在模型辨识过程中存在局部最优问题。在种群迭代进化过程中,利用粒子适应度值动态变化,使算法在寻优过程中的全局搜索能力和局部搜索能力得到平衡。与传统惯性策略相比,自适应惯性权重能使算法更好地适应动态搜索过程,辨识所得模型的各项误差值更小、精度更高。应用辨识模型,对山西某350 MW CFB锅炉的现场运行数据进行验证。验证结果表明,该模型能够有效地反映燃料量、一次风量、二次风量与床温之间的动态关系。该研究在CFB锅炉床温的自动控制以及优化方面有一定指导意义。

For the automatic control optimization of circulating fluidized bed(CFB)boilers,the establishment of bed temperature dynamic model and dynamic characteristic analysis are of great significance.Particle swarm optimization(PSO)algorithm is used to identify the bed temperature dynamic model,and adaptive inertia weighting strategy is used to solve the problem of local optimum in the model identification process by standard algorithm.During the iterative evolution of the population,the particle fitness value is dynamically changed to balance the global search ability and local search ability of the algorithm in the optimization search process.Compared with the traditional inertia strategy,the adaptive inertia weights enable the algorithm to better adapt to the dynamic search process,and the discriminative model has smaller error values and higher accuracy.The field operation data of a 350 MW CFB boiler in Shanxi are verified by using the identification model.The results show that the model can effectively reflect the dynamic relationship between fuel volume,primary air flow,secondary air flow and bed temperature.The research has certain guidance significance in the automatic control and optimization of bed temperature of CFB boiler.