陈波,曹歌瀚,黄亚继,岳峻峰,徐文韬,王亚欧,李雨欣,金保昇
CHEN Bo,CAO Gehan,HUANG Yaji,YUE Junfeng,XU Wentao,WANG Ya′ou,LI Yuxin,JIN Baosheng

• 1:江苏方天电力技术有限公司
• 2:东南大学东南大学能源热转换及其过程测控教育部重点实验室

摘要(Abstract)：

经济发展方向与政策导向促使火电厂燃煤锅炉朝着智能化方向升级,燃煤锅炉的燃烧效率是衡量锅炉运行状况的重要指标。为了满足实时计算锅炉热效率的要求,借助于电厂的日常测量数据计算锅炉效率,计算方法为:(1)分析锅炉的燃烧运行特征;(2)根据提取的特征采用剔除异常数据、稳态判别、相似性处理的预处理方法,生成更好的训练样本;(3)采用遗传算法改进的神经网络算法建立锅炉排烟温度、飞灰含碳量和煤质灰分之间的计算模型;利用燃煤热值与理论空气量的比例关系计算入炉煤热值,计算值用于锅炉热效率的反平衡计算模型。计算结果表明,神经网络模型的预测值能满足工程计算的要求;计算所得的排烟温度、飞灰含碳量与煤质灰分用于锅炉效率的计算过程,可实现实时动态的锅炉效率计算;计算所得锅炉效率的变化与实际蒸发量变化基本一致。锅炉实际蒸发量下降时,锅炉效率降低;锅炉实际蒸发量保持60%以上额定蒸发量时,锅炉效率易保持在较高水平。
The direction of economic development and policy orientation has promoted the upgrading of coal-fired boilers in thermal power plants towards the direction of intelligence. The combustion efficiency of coal-fired boiler is an important indicator to measure the operating status of boiler. In order to meet the requirements of real-time calculation of boiler thermal efficiency, the following methods are used to calculate the boiler efficiency with the help of the daily measurement data of the power plant: Firstly, the corresponding combustion and operation characteristics of the boiler were analyzed; Secondly, according to the extracted features, the preprocessing methods of eliminating outliers, steady state discrimination, and similarity processing were carried out to generate better training samples. Finally, the neural network algorithm improved by genetic algorithm was used to establish the calculation model among the boiler exhaust temperature, fly ash carbon content and coal ash content. The calorific value of the coal into the furnace was calculated by using the proportional relationship between the calorific value of coal and the theoretical air volume, and the calculated value was used in the inverse balance calculation model of the boiler thermal efficiency. The calculation results show that the predicted value of the neural network model can meet the requirements of engineering calculation. The calculated exhaust gas temperature, fly ash carbon content and coal ash content can be used in the calculation of boiler efficiency to realize real-time dynamic boiler efficiency calculation. The change of the calculated boiler efficiency is approximately the same as that of the actual evaporation change. When the actual evaporation capacity of the boiler decreases, the efficiency of the boiler will decrease. When the actual evaporation capacity of the boiler is maintained above 60% of the rated evaporation capacity, the boiler efficiency is easily maintained at a high level.

关键词(KeyWords)： 机器学习;神经网络算法;遗传算法;数据分析;锅炉效率
machine learning;neural network algorithm;genetic algorithm;data analysis;boiler efficiency

Abstract:

Keywords:

基金项目(Foundation): 国家重点研发计划资助项目(2018YFC1901200);; 江苏方天电力技术有限公司科技项目(KJ201927);; 江苏省科技成果转化专项基金资助项目(BA2020001)

作者(Author): 陈波,曹歌瀚,黄亚继,岳峻峰,徐文韬,王亚欧,李雨欣,金保昇
CHEN Bo,CAO Gehan,HUANG Yaji,YUE Junfeng,XU Wentao,WANG Ya′ou,LI Yuxin,JIN Baosheng

DOI: 10.13226/j.issn.1006-6772.CE21042501

参考文献(References)：

• [1] 赵俊杰，冯树臣，杨如意，等.新基建时代的燃煤智慧电厂建设与技术升级分析[J].神华科技，2019,17(12):5-10.ZHAO Junjie,FENG Shuchen,YANG Ruyi,et al.Construction and technical upgrading analysis of coal-fired intelligent power plants in the new infrastructure era[J].Shenhua Technology,2019,17(12):5-10
• [2] 蔡培，葛荣存，葛铭，等.燃烧优化调整对NOx排放和锅炉效率的影响[J].洁净煤技术，2018,24(5):77-83.CAI Pei,GE Rongcun,GE Ming,et al.Effect of combustion optimization adjustment on NOx emission and boiler efficiency[J].Clean Coal Technology,2018,24(5):77-83.
• [3] 李成喜，王焕新，陈国艳.65 t/h生物质循环流化床锅炉热效率性能实验[J].洁净煤技术，2011,17(4):58-61,3.LI Chengxi,WANG Huanxin,CHEN Guoyan.Study on the influence of coal circuler economy on CO2 emission reduction[J].Clean Coal Technology,2011,17(4):58-61,3.
• [4] 应明良，吕洪坤，茅建波，等.基于实时数据库的电站锅炉热效率在线计算方法[J].浙江电力，2019,38(7):92-95.YING Mingliang,LV Hongkun,MAO Jianbo,et al.An online calculation method of power station boiler efficiency based on real-time database[J].Zhejiang Electric Power,2019,38(7):92-95.
• [5] 王诣.锅炉效率快速分析检测系统的研究[D].杭州：中国计量大学，2017.WANG Yi.Research and development of rapid analysis system for boiler efficiency[D].Hangzhou:China Jiliang University,2017.
• [6] 赵国强.燃煤电站锅炉在线热效率计算及应用研究[D].保定：华北电力大学，2016.ZHAO Guoqiang.Research on online thermal efficiency calculation and application of coal fired power station boiler[D].Baoding:North China Electric Power University,2016.
• [7] WU X Y,TANG Z H,CAO S X.A hybrid least square support vector machine for boiler efficiency prediction[J].IEEE,2017:1202-1205.
• [8] XU X Y,CHEN Q,REN M F,et al.,Combustion optimization for coal fired power plant boilers based on improved distributed ELM and distributed PSO[J].Energies,2019,12(6):1036.
• [9] SHI Y,ZHONG W Q,CHEN X,et al.Combustion optimization of ultra supercritical boiler based on artificial intelligence[J].Energy,2019,170:804-817.
• [10] ZHAO Y D,WU Q H,LI H,et al.Optimization of thermal rfficiency and unburned carbon in fly ash of coal-fired utility boiler via grey wolf optimizer algorithm[J].IEEE Access,2019,7:114414-114425.
• [11] 牛鹏坤，洪辉，王炜哲.基于改进遗传算法的电站锅炉效率优化[J].热能动力工程，2020,35(3):111-115.NIU Pengkun,HONG Hui,WANG Weizhe.Optimization of boiler combustion efficiency based on improved genetic algorithm[J].Journal of Engineering for Thermal Energy and Power Engineering,2020,35(3):111-115.
• [12] 崔育奎，陶丽，崇培安.神经网络Skeletonization算法在优化锅炉运行参数中的应用[J].锅炉技术，2016,47(2):21-26.CUI Yukui,TAO Li,CHONG Peian.Application of neural network algorithm Skeletonization forboiler performance optimization[J].Boiler Technology,2016,47(2):21-26.
• [13] 尹凌霄，王明春，尚强.基于支持向量机和粒子群算法的电站锅炉燃烧优化[J].锅炉技术，2014,45(4):13-17.YIN Lingxiao,WANG Mingchun,SHANG Qiang.The combustion optimization of a coal-fired boiler based on support vector machine and particle swarm algorithm[J].Boiler Technology,2014,45(4):13-17.
• [14] 沈利.燃煤电站锅炉的燃烧优化技术及相关算法应用研究[D].杭州：浙江大学，2011.SHEN Li.Research on combustion optimization technology and application of related algorithm in coal-fired boiler[D].Hangzhou:Zhejiang University,2011.
• [15] 江苏方天电力技术有限公司.一种燃煤锅炉入炉原煤热值在线软测量方法：CN111753389A[P].2020-10-09.
• [16] 单衍江，地力木拉提.偏最小二乘回归神经网络模型在燃煤锅炉结渣预测中的应用[J].洁净煤技术，2009,15(4):64-67.SHAN Yanjiang,DILI Mulati.Application of neural network model with partial least squares regression on predicting slagging of coal-fired boiler[J].Clean Coal Technology,2009,15(4):64-67.