基于果蝇优化算法的锅炉高效率低NOx燃烧建模

Fruit fly optimization algorithm based high efficiency and low NO_x combustion modeling for a boiler

为了控制燃煤锅炉的NOx排放量并提高锅炉效率,对某超超临界1 000 MW机组锅炉的热态运行数据进行分析,基于支持向量回归机(SVM),建立了NOx排放和锅炉热效率的FOASVM模型,采用果蝇优化算法(FOA)对模型中的惩罚因子C、核函数参数g和不敏感损失系数ε这3个参数寻优,并与遗传算法(GA)优化参数的预测模型进行比较。结果表明,FOASVM模型的预测精度更高,泛化能力更强,其中误差最大的NOx排放模型测试集数据的平均相对误差仅3.59%,能够精准地预测锅炉热效率和NOx排放,适合于在线建模预测,为大容量锅炉的进一步优化运行提供了良好的模型基础。

In order to control NOx emissions and enhance boiler efficiency in coal-fired boilers,the thermal operating data from an ultra-supercritical 1000MW unit boiler were analyzed.On the basis of the support vector regression machine （SVM）,the fruit fly optimization algorithm （FOA）was applied to optimize the penalty parameter C,kernel parameter g and insensitive loss coefficient of the model.Then,the FOA-SVM model was established to predict the NOx emissions and boiler efficiency,and the performance of this model was compared with that of the GA-SVM model optimized by genetic algorithm （GA）.The results show the FOA-SVM model has better prediction accuracy and generalization capability,of which the maximum aver-age relative error of testing set lies in the NOx emissions model,which is only 3 .5 9%.The above models can predict the NOx emissions and boiler efficiency accurately,so they are very suitable for on-line modeling prediction,which provides a good model foundation for further optimization operation of large capacity boilers.