摘要
NOx排放量和锅炉效率模型是电站锅炉燃烧优化的基础。采用抗干扰能力更强的加权最小二乘支持向量机(WLS-SVM)建立了NOx排放模型。将序列前向选择(SFS)与WLS-SVM相结合建立了锅炉效率模型,在不影响模型精度前提下去除了模型中的冗余成分,精简了模型结构,提高了模型计算速度。采用遗传算法,以所建模型为基础,提出了一种可兼顾锅炉效率和NOx排放量的优化燃烧方案。实际应用结果表明,该优化方案使锅炉效率平均提高0.386%,NOx排放量平均降低99.147mg/m3。
NOx emission and boiler efficiency model is the foundation of boiler combustion optimi-zation.The weighted least squares support vector machine （WLS-SVM）was employed to estab-lish the NOx emission model.By combining the WLS-SVM with sequential forward selection （SFS）,the boiler efficiency model was built.Moreover,on the premise of not affecting the model accuracy,the redundancy compositions in the model was reduced,which simplifies the model structure and enhances the calculation speed.On the basis of the established models,an optimiza-tion method which can effectively balance the boiler efficiency and NOx emissions was put for-ward,by applying the genetic algorithm.The results show that this optimization program im-proved the boiler efficiency and NOx emission by 0.386% and 99.147 mg/m3 on average,respec-tively.
出处
《热力发电》
CAS
北大核心
2014年第5期7-12,共6页
Thermal Power Generation
基金
国家科技支撑计划项目:大型电站燃煤锅炉燃烧在线优化节能减排技术(2011BAA04B01)
关键词
NOx
排放量
锅炉效率
燃烧优化
WLS-SVM
SFS
NOx emission
boiler efficiency
WLS-SVM
SFS
combustion optimization
