支持向量机理论与遗传算法相结合的300MW机组锅炉多目标燃烧优化

Multi-objective combustion optimization for a 300MW unit using support vector machine theory combining with genetic algorithm

为提高电站锅炉燃烧的经济性并尽可能降低NOx排放量,以煤耗率和NOx生成量最小为目标,运用支持向量机算法建立了某亚临界300 MW机组烟煤锅炉的煤耗率和NOx生成量预测模型,并结合该机组的实际运行数据,对所建模型的准确性进行了验证。将建立的煤耗率和NOx生成量模型进行耦合,生成锅炉燃烧优化模型,并将煤耗率和NOx生成量综合作为优化目标,建立目标函数,应用遗传算法寻找锅炉的最优运行方案。结果表明:基于支持向量机算法建立的锅炉燃烧模型对锅炉煤耗率和NOx生成量具有较高的预测能力;增加燃尽风量可降低NOx生成量,但同时会提高煤耗率,为优化运行,应将同时降低煤耗率和NOx生成量综合作为优化目标;对于该亚临界300MW机组烟煤锅炉,满负荷运行时机组经济性较好,且NOx生成量最低,其他负荷下,一、二次风比例和各层二次风挡板开度在某特定值时机组经济性和NOx排放可达到最佳情况。

In order to improve the utility boilers＇economy and reduce NOx emission as much as possible,this paper regards the minimum coal consumption rate and NOx formation as the goals to establish the predic-tion models of coal consumption rate and NOx formation for a sub-critical 300 MW unit boiler,on the basis of the support vector machine （SVM）theory.Combining with the operation data of this 300 MW unit,the above two models were verified.Moreover,the established coal consumption rate prediction model was cou-pled with the NOx formation prediction model,thus a combustion optimization model was formed.Both the coal consumption rate and NOx formation were considered as the optimization obj ect to set up the obj ective function.Then the genetic algorithm （GA）was employed to find out the optimal operation solution for the boiler.It concludes that the SVM-based boiler combustion model has high ability in predicting the unit coaln consumption rate and NOx formation.It is often conflicting to reduce NOx generation as well as coal con-sumption rate,namely increasing the over fire air volume can reduce the NOx generation,but at the same time will increase the coal consumption rate.Aiming at optimizing the boiler operation,the coal consump-tion rate and NOx generation should be integrated as the optimization goal.For this sub-critical 300 MW u-nit boiler burning bituminous coal,it＇s better to run at full load for the lowest NOx generation,and at other loads,the unit economy and NOx emission can achieve the best situation when the secondary air ratio and the opening degree of each layer of the secondary air baffles are kept at a certain value.