电站锅炉省煤器受热面的积灰监测
|
摘要
为了实现电站锅炉省煤器受热面的污染情况在线监测,采用支持向量机算法对省煤器的清洁吸热量进行预测,使用灰狼算法(GWO)和遗传算法对模型进行参数寻优并进行预测精确度的对比。再由清洁吸热量计算清洁因子,根据清洁因子的变化来判断省煤器的积灰状态。以某660MW机组为例,将短吹后的数据作为清洁数据样本进行训练和验证,结果表明灰狼算法比遗传算法预测精度更高,所需训练时间更短。最后利用上述模型来预测长吹前省煤器的清洁吸热量,绘制出清洁曲线图。该模型能较好表现省煤器的积灰情况,为受热面积灰在线监测提供依据。
To realize online monitoring heating surface pollution of an economizer in coal-fired power plant boiler, support vector machine(SVM) algorithm was used to predict the clean heat absorption of the economizer. At the same time, the gray wolf algorithm(GWO) and genetic algorithm was used for parameters optimization, and prediction accuracy in two models was compared. According to the cleaning heat absorption, the cleaning factor was calculated. The economizer's fouling was judged according to the change of cleaning factor. Take a 660 MW unit as an example, the data after short blow was taken as clean samples for training and validation. The results showed that GWO has higher prediction accuracy than genetic algorithm(GA), and the training time of GWO is shorter. Finally, this model was used to predict the clean heat absorption of an economizer before long blowing, then the clean factor curve was drawn.The fouling in an economizer heating surface can be performed well. Thus, a basis for an economizer fouling on-line monitoring is offered.
To realize online monitoring heating surface pollution of an economizer in coal-fired power plant boiler, support vector machine(SVM) algorithm was used to predict the clean heat absorption of the economizer. At the same time, the gray wolf algorithm(GWO) and genetic algorithm was used for parameters optimization, and prediction accuracy in two models was compared. According to the cleaning heat absorption, the cleaning factor was calculated. The economizer's fouling was judged according to the change of cleaning factor. Take a 660 MW unit as an example, the data after short blow was taken as clean samples for training and validation. The results showed that GWO has higher prediction accuracy than genetic algorithm(GA), and the training time of GWO is shorter. Finally, this model was used to predict the clean heat absorption of an economizer before long blowing, then the clean factor curve was drawn.The fouling in an economizer heating surface can be performed well. Thus, a basis for an economizer fouling on-line monitoring is offered.
引文
[1]MA Z,IMAN F,LU P,et al.A comprehensive slagging and fouling prediction tool for coal-fired boilers and its validation/application[J].Fuel Processing Technology,2007,88(11/12):1035-1043.
[2]TERUEL E,CORTéS C,DíEZ L I,et al.Monitoring and prediction of fouling in coal-fired utility boilers using neural networks[J].Chemical Engineering Science,2005,60(8):5035-5048.
[3]PE?A B,TERUEL E,DíEZ L I.Soft-computing models for sootblowing optimization in coal-fired utility boilers[J].Applied Soft Computing,2011,11(2):1657-1668.
[4]信晶,孙保民,肖海平,等.应用支持向量机监测电站锅炉受热面积灰研究[J].中国电机工程学报,2013,33(5):21-26.XIN Jing,SUN Baomin,XIAO Haiping,et al.Research on applying support vector machine to monitor ash deposition of heating surface in a utility boiler[J].Proceedings of the CSEE,2013,33(5):21-26.
[5]喻火明,孙保民,徐鸿,等.锅炉受热面积灰在线监测的研究[J].工程热物理学报,2006,27(3):534-536.YU Huoming,SUN Baomin,XU Hong,et al.Research on on-line fouling monitoring of boiler heating surface[J].Journal of Engineering Thermophysics,2006,27(3):534-536.
[6]MIRJALILI S,MIRJALILI S M,LEWIS A.Grey wolf optimizer[J].Advance in Engineering Software,2014,69(3):46-61.
[7]牛培峰,史春见,刘楠,等.基于自适应量子灰狼算法的锅炉NOx预测模型[J].动力工程学报,2018,38(4):278-285.NIU Peifeng,SHI Chunjian,LIU Nan,et al.A boiler NOx prediction model based on adaptive quantum gray wolf algorithm[J].Journal of Chinese Society of Power Engineering,2018,38(4):278-285.
[8]王宏武,孙保民,张振星,等.基于模糊C均值聚类和支持向量机算法的燃煤锅炉结渣特性预测[J].动力工程学报,2014,34(2):91-96.WANG Hongwu,SUN Baomin,ZHANG Zhenxing,et al.State prediction of slagging on coal-fired boilers based on fuzzy C-means clustering and support vector machine[J].Journal of Chinese Society of Power Engineering,2014,34(2):91-96.
[9]杜必强,孙立江.基于PSO-SVM模型的焊接转子环焊缝超声缺陷识别[J].动力工程学报,2017,37(5):379-385.DU Biqiang,SUN Lijiang.Ultrasonic defect identification of welding rotor ring weld based on pso-svm model[J].Journal of Chinese Society of Power Engineering,2017,37(5):379-385.
[10]王禹朋,阎维平,祝云飞,等.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[J].热力发电,2015,44(10):91-96.WANG Yupeng,YAN Weiping,ZHU Yunfei,et al.Multi-objective combustion optimization for a 300MW unit using support vector machine theory combining with genetic algorithm[J].Thermal Power Generation,2015,44(10):91-96.
[11]柳长安,王晓鹏,刘春阳,等.基于改进灰狼优化算法的无人机三维航迹规划[J].华中科技大学学报(自然科学版),2017,45(10):38-42.LIU Changan,WANG Xiaopeng,LIU Chunyang,et al.UAV threedimensional track planning based on improved gray Wolf optimization algorithm[J].Journal of Huazhong University of Science and Technology(Natural Science Edition),2017,45(10):38-42.
[12]阎维平,朱予东,谭蓬,等.变负荷工况下锅炉对流受热面污染的监测[J].动力工程学报,2007,27(1):58-61.YAN Weiping,ZHU Yudong,TAN Peng,et al.Monitoring of convective heating surface of boiler under variable load condition[J].Journal of Chinese Society of Power Engineering,2007,27(1):58-61.
[13]徐力刚,黄亚继,岳峻峰,等.600MW超临界锅炉半辐射受热面积灰监测模型研究[J].动力工程学报,2015,35(11):871-877.XU Ligang,HUANG Yaji,YUE Junfeng,et al.Study on the monitoring model of semi-radiant heating surface of 600MW supercritical boiler[J].Journal of Chinese Society of Power Engineering,2015,35(11):871-877.
[14]SHI W,WANG J,SHI Y,et al.Online prediction of unburned carbon content in fly ash with clustering LS-SVM models[C]//Control Conference,IEEE,2015:1947-1952.
[2]TERUEL E,CORTéS C,DíEZ L I,et al.Monitoring and prediction of fouling in coal-fired utility boilers using neural networks[J].Chemical Engineering Science,2005,60(8):5035-5048.
[3]PE?A B,TERUEL E,DíEZ L I.Soft-computing models for sootblowing optimization in coal-fired utility boilers[J].Applied Soft Computing,2011,11(2):1657-1668.
[4]信晶,孙保民,肖海平,等.应用支持向量机监测电站锅炉受热面积灰研究[J].中国电机工程学报,2013,33(5):21-26.XIN Jing,SUN Baomin,XIAO Haiping,et al.Research on applying support vector machine to monitor ash deposition of heating surface in a utility boiler[J].Proceedings of the CSEE,2013,33(5):21-26.
[5]喻火明,孙保民,徐鸿,等.锅炉受热面积灰在线监测的研究[J].工程热物理学报,2006,27(3):534-536.YU Huoming,SUN Baomin,XU Hong,et al.Research on on-line fouling monitoring of boiler heating surface[J].Journal of Engineering Thermophysics,2006,27(3):534-536.
[6]MIRJALILI S,MIRJALILI S M,LEWIS A.Grey wolf optimizer[J].Advance in Engineering Software,2014,69(3):46-61.
[7]牛培峰,史春见,刘楠,等.基于自适应量子灰狼算法的锅炉NOx预测模型[J].动力工程学报,2018,38(4):278-285.NIU Peifeng,SHI Chunjian,LIU Nan,et al.A boiler NOx prediction model based on adaptive quantum gray wolf algorithm[J].Journal of Chinese Society of Power Engineering,2018,38(4):278-285.
[8]王宏武,孙保民,张振星,等.基于模糊C均值聚类和支持向量机算法的燃煤锅炉结渣特性预测[J].动力工程学报,2014,34(2):91-96.WANG Hongwu,SUN Baomin,ZHANG Zhenxing,et al.State prediction of slagging on coal-fired boilers based on fuzzy C-means clustering and support vector machine[J].Journal of Chinese Society of Power Engineering,2014,34(2):91-96.
[9]杜必强,孙立江.基于PSO-SVM模型的焊接转子环焊缝超声缺陷识别[J].动力工程学报,2017,37(5):379-385.DU Biqiang,SUN Lijiang.Ultrasonic defect identification of welding rotor ring weld based on pso-svm model[J].Journal of Chinese Society of Power Engineering,2017,37(5):379-385.
[10]王禹朋,阎维平,祝云飞,等.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[J].热力发电,2015,44(10):91-96.WANG Yupeng,YAN Weiping,ZHU Yunfei,et al.Multi-objective combustion optimization for a 300MW unit using support vector machine theory combining with genetic algorithm[J].Thermal Power Generation,2015,44(10):91-96.
[11]柳长安,王晓鹏,刘春阳,等.基于改进灰狼优化算法的无人机三维航迹规划[J].华中科技大学学报(自然科学版),2017,45(10):38-42.LIU Changan,WANG Xiaopeng,LIU Chunyang,et al.UAV threedimensional track planning based on improved gray Wolf optimization algorithm[J].Journal of Huazhong University of Science and Technology(Natural Science Edition),2017,45(10):38-42.
[12]阎维平,朱予东,谭蓬,等.变负荷工况下锅炉对流受热面污染的监测[J].动力工程学报,2007,27(1):58-61.YAN Weiping,ZHU Yudong,TAN Peng,et al.Monitoring of convective heating surface of boiler under variable load condition[J].Journal of Chinese Society of Power Engineering,2007,27(1):58-61.
[13]徐力刚,黄亚继,岳峻峰,等.600MW超临界锅炉半辐射受热面积灰监测模型研究[J].动力工程学报,2015,35(11):871-877.XU Ligang,HUANG Yaji,YUE Junfeng,et al.Study on the monitoring model of semi-radiant heating surface of 600MW supercritical boiler[J].Journal of Chinese Society of Power Engineering,2015,35(11):871-877.
[14]SHI W,WANG J,SHI Y,et al.Online prediction of unburned carbon content in fly ash with clustering LS-SVM models[C]//Control Conference,IEEE,2015:1947-1952.