姚顺春,刘泽明,卢志民,郭松杰,谢子立,李峥辉,黄泳如,李龙千,卢伟业,陈小玄
YAO Shunchun,LIU Zeming,LU Zhimin,GUO Songjie,XIE Zili,LI Zhenghui,HUANG Yongru,LI Longqian,LU Weiye,CHEN Xiaoxuan

• 1:华南理工大学电力学院
• 2:广东省能源高效清洁利用重点实验室
• 3:广东省特种设备检测研究院顺德检测院

摘要(Abstract)：

火力发电企业作为我国能源结构的重要组成部分，长期以来是我国碳排放的主要来源，在我国和全球加速推动低碳经济发展的宏观环境下，火电企业积极响应国家“能耗双控”向“碳排放双控”转变的战略部署。在此背景下，精确计量燃煤电厂的碳排放量变得至关重要。在燃煤电厂碳计量中，烟气流量影响燃煤发电中在线监测法的精度，而燃煤消耗量、燃煤元素碳含量以及飞灰碳含量共同决定核算法的可靠性。目前，大多数燃煤发电企业只对流量和燃煤消耗量进行实时监测，在现场恶劣的环境中对燃煤元素碳含量以及飞灰碳含量进行短周期、高频次的直接监测需要花费较大的人力以及物力，流量监测设备也易受烟道环境影响。而软测量技术以其高效和低成本的特点，可为传统碳排放计量过程中关键参数的监测提供一种替代方法。鉴于此，首先阐述了软测量模型的建立过程，包含数据预处理、辅助变量选择、软测量模型建立以及模型校正。数据预处理能够确保数据质量，提高建模效率；辅助变量选择是从大量潜在的变量中筛选出对目标变量的辅助变量，进一步提高建模效率；软测量模型建立主要是基于机理建模和数据驱动建模，是实现目标变量预测的核心；模型校正通过实际的离线或在线数据，对模型进行进一步优化，提高模型的预测精度。其次，针对碳计量相关参数，分析了烟气流量、燃煤消耗量、燃煤元素碳含量和飞灰碳含量监测存在的问题，论述了软测量技术在上述碳计量关键参数的国内外研究进展和应用，评估了机理建模和数据驱动建模技术的有效性、准确性和实用性。其中，机理分析建模主要基于电厂锅炉进出口的能量平衡以及烟风质量守恒等原理，有着确定的数学物理关系式，具有高度可解释性和稳定性，但是建模过程复杂，预测精度较低；数据驱动建模主要是利用各种机器学习方法，基于电厂分布式控制系统(Distributed control system, DCS)丰富的运行数据，对碳计量关键参数进行“黑箱建模”,克服了机理分析建模复杂的过程分析，精度相对较高，但是建模过程不明确，且模型对于不同机组的泛化能力较差。最后，对于软测量技术在碳排放计量领域的发展应用进行了总结与展望。对电厂各参数之间的时序结构、电厂自身计算能力的限制以及机理分析融合数据驱动方法的发展提出相关建议，并对国外二氧化碳预测性排放系统结合软测量技术在国内外燃煤电厂的应用进行展望。
As a significant component of China′s energy structure, thermal power generation enterprises have long been the main source of carbon emissions in the country. With the global push for a low-carbon economy, those enterprisesare shifting from "dual control of energy consumption" to "dual control of carbon emissions." Under this backdrop, accurately measuring the carbon emissions of coal-fired power plants has become crucial. In carbon measurement for coal-fired power plants, flue gas flow impacts the accuracy of the online monitoring method. In contrast, coal consumption, carbon content in coal, and carbon content in fly ash jointly determine the reliability of the calculation method.Currently, most coal-fired plants only perform real-time monitoring of flow and coal consumption. However, direct, high-frequency, short-cycle monitoring of carbon content in coal and fly ash in harsh plant environments requires significant human and material resources and flow monitoring equipment is easily affected by the flue gas environment. Soft measurement technology, with its efficiency and low cost, provides an alternative method for monitoring key parameters in traditional carbon emission measurements.Firstly, this study reviews the establishment of a soft measurement model, including data preprocessing, auxiliary variable selection, model establishment, and model correction. Data preprocessing ensures data quality and improves modeling efficiency. Auxiliary variable selection enhances modeling efficiency by filtering out useful variables. The soft measurement model, based on mechanism and data-driven modeling, is key to predicting target variables. Model correction optimizes the model with actual data, improving prediction accuracy.Secondly, the study analyzes issues in monitoring flue gas flow, coal consumption, coal carbon content, and fly ash carbon content. It discusses the research progress and application of soft measurement technology for these parameters. Mechanism modeling, based on energy balance and mass conservation principles, has high interpretability and stability but is complex and less accurate. Data-driven modeling, using machine learning and data from distributed control systems(DCS) offers higher accuracy, but lacks transparency and generalization ability.Finally, this study summarizes and prospects the development and application of soft measurement technology in the field of carbon emission measurement. It provides suggestions for integrating the time-series structure of various plant parameters, the computational limitations of the plant itself, and the development of methods combining mechanism analysis and data-driven approaches. It summarizes the application scenarios of predictive CO_2 emission systems abroad and anticipates the application of such systems combined with soft measurement technology in domestic and international coal-fired power plants.

关键词(KeyWords)： 燃煤电厂;碳排放计量;软测量技术;在线监测法;核算法
coal-fired power plants;carbon emission measurement;soft sensing technology;online monitoring method;carbon accounting method

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金联合基金重点资助项目(U22B20119);; 广东省自然科学基金-杰出青年资助项目(2021B1515020071)

作者(Author): 姚顺春,刘泽明,卢志民,郭松杰,谢子立,李峥辉,黄泳如,李龙千,卢伟业,陈小玄
YAO Shunchun,LIU Zeming,LU Zhimin,GUO Songjie,XIE Zili,LI Zhenghui,HUANG Yongru,LI Longqian,LU Weiye,CHEN Xiaoxuan

DOI: 10.13226/j.issn.1006-6772.LC24020101

参考文献(References)：

• [1] 中国电力行业年度发展报告.2023(摘要)[N].中国电力报，2023-07-12(003).
• [2] 生态环境部.企业温室气体排放核算与报告指南发电设施[R/OL].(2022-12-21).https://www.mee.gov.cn/xxgk2018/xxgk/xxgk06/202212/t20221221_1008430.html.
• [3] 陈公达，邹祥波，卢锐，等.中外火电企业碳排放统计方法与质量控制现状分析[J].热力发电，2022,51(10):54-60.CHEN Gongda,ZOU Xiangbo,LU Rui,et al.Domestic and international statistical methods and quality control status for carbon emission from fossil-fired power plants[J].Thermal Power Generation,2022,51(10):54-60.
• [4] LEE S,CHOI Y,WOO J,et al.Estimating and comparing greenhouse gas emissions with their uncertainties using different methods:A case study for an energy supply utility[J].Journal of the Air & Waste Management Association,2014,64(10):1164-1173.
• [5] QUICK J C.Carbon dioxide emission tallies for 210 U.S.coal-fired power plants:A comparison of two accounting methods[J].Journal of the Air & Waste Management Association,2014,64(1):73-79.
• [6] 李峥辉，卢伟业，庞晓坤，等.火电企业CO2排放在线监测系统的研发应用[J].洁净煤技术，2020,26(4):182-189.LI Zhenghui,LU Weiye,PANG Xiaokun,et al.Research and application of on-line monitoring system for CO2 emissions from thermal power enterprises[J].Clean Coal Technology,2020,26(4):182-189.
• [7] 张钦，张达，张希良.在线监测应用于中国碳排放监测的相关问题和制度建议[J].环境经济研究，2021,6(3):136-146.ZHANG Qin,ZHANG Da,ZHANG Xiliang.Application of online monitoring to China′s carbon emission trading system:Key issues and policy recommendations[J].Journal of Environmental Economics,2021,6(3):136-146.
• [8] 王奇伟.某电厂烟气监测系统与脱硝自动控制改造[J].中国电力，2015,48(7):120-123,60.WANG Qiwei.Retrofit of flue gas monitoring and denitration automatic control systems in a power plant[J].Electric Power,2015,48(7):120-123,60.
• [9] 钱枫，程书瑾，王明达，等.基于随机森林的开封市重型柴油车NOx排放总量估算模型[J].环境科学学报，2023,43(2):391-407.QIAN Feng,CHENG Shujin,WANG Mingda,et al.A model for estimating the total NOx emissions of heavy-duty diesel vehicles in Kaifeng City based on random forests [J].Acta Scientiae Circumstantiae,2023,43(2):391-407.
• [10] 蔡庙辉，吴昌子，郇洪江，等.基于CNN-LSTM的垃圾焚烧炉烟气浓度预测方法[J/OL].化学工业与工程：1-9[2024-03-18].https://doi.org/10.13353/j.issn.1004.9533.20220814.CAI Miaohui,WU Changzi,XUN Hongjiang,et al.Prediction method of flue gas concentration in garbage incinerators based on CNN-LSTM [J/OL].Chemical Industry and Engineering:1-9[2024-03-18].https://doi.org/10.13353/j.issn.1004.9533.20220814.
• [11] 李宗琪.电厂燃煤锅炉热效率智能软测量与能耗分布诊断方法研究[D].保定：华北电力大学，2020.
• [12] 佟纯涛.燃煤机组烟气流量软测量技术研究[D].保定：华北电力大学，2017.
• [13] WEBER R B C.The use of secondary measurements to improve control[J].AIChE Journal,1972,18(3):614-623.
• [14] CANTONI E,FLEMMING J M,RONCHETTI E.Variable selection for marginal longitudinal generalized linear models[J].Biometrics,2005,61(2):507-514.
• [15] 王建，杨耀权，马高伟.软测量辅助变量选择方法研究[J].电力科学与工程，2011,27(7):37-40.WANG Jian,YANG Yaoquan,MA Gaowei.Research on method of soft measurement secondary variables selection[J].Electric Power Science and Engineering,2011,27(7):37-40.
• [16] 张婧，曹峰，董毓莹，等.基于互信息和遗传算法的特征选择算法[J].山西大学学报(自然科学版),2024,47(1):1-8.ZHANG Jing,CAO Feng,DONG Yuying,et al.Feature selection algorithm based on mutual information and genetic algorithm[J].Journal of Shanxi University(Natural Science Edition),2024,47(1):1-8.
• [17] 张扬.锅炉飞灰含碳量软测量[D].保定：华北电力大学，2019.
• [18] 任锦.基于改进最小二乘支持向量机的锅炉烟气氧含量软测量研究 [D].西安：陕西科技大学，2018.
• [19] 陈敏生，刘定平.基于核主元分析和支持向量机的电站锅炉飞灰含碳量软测量建模[J].华北电力大学学报，2006(1):72-75,92.CHEN Minsheng,LIU Dingping.Soft-sensing modeling of the unburned carbon in fly ash based on KPCA-SVM for power station boilers[J].Journal of North China Electric Power University,2006(1):72-75,92.
• [20] MEHMOOD T,LILAND K H,SNIPEN L,et al.A review of variable selection methods in Partial Least Squares Regression[J].Chemometrics and Intelligent Laboratory Systems,2012,118:62-69.
• [21] 骆海瑞.基于机器学习的飞灰含碳量软测量模型研究[D].武汉：武汉纺织大学，2023.
• [22] 王孝红，刘文光，于宏亮.工业过程软测量研究[J].济南大学学报(自然科学版),2009,23(1):80-86.WANG Xiaohong,LIU Wenguang,YU Hongliang.Research on industrial process soft-sensor[J].Journal of University of Jinan (Science and Technology),2009,23(1):80-86.
• [23] 姚顺春，支嘉琦，付金杯，等.火电企业碳排放在线监测技术研究进展[J].华南理工大学学报(自然科学版),2023,51(6):97-108.YAO Shunchun,ZHI Jiaqi,FU Jinbei,et al.Research progress of online carbon emission monitoring technology for thermal power enterprises[J].Journal of South China University of Technology(Natural Science Edition),2023,51(6):97-108.
• [24] 马世海，刘思源.大口径通风管道流量测量技术的研究进展与趋势[J].化工自动化及仪表，2022,49(3):253-258.MA Shihai,LIU Siyuan.Research progress and trend of flow measurement technology for ventilation ducts with large caliber[J].Control and Instruments in Chemical Industry,2022,49(3):253-258.
• [25] 俞植馨.热式气体质量流量计的改进研究[D].济南：山东大学，2020.
• [26] KORPELA T,BJ?RKQVIST T,MAJANNE Y,et al.Online monitoring of flue gas emissions in power plants having multiple fuels[J].IFAC Proceedings Volumes,2014,47(3):1355-1360.
• [27] 胡昌镁，邓宇，汪学文.一种基于烟气软测量的SCR脱硝控制系统优化[J].发电设备，2013,27(5):330-333.HU Changmei,DENG Yu,WANG Xuewen.Optimization of a SCR denitration control system based on soft-sensing of flue gas[J].Power Equipment,2013,27(5):330-333.
• [28] 谭鹏，饶德备，李一波，等.一种电站煤粉锅炉烟气流量软测量方法：CN110619929B[P].2021-03-12.
• [29] 程新华，张庆国，刘富国.发电厂风粉流体测量系统的数据校正[J].热力发电，2014,43(11):35-40.CHENG Xinhua,ZHANG Qingguo,LIU Fuguo.Data reconciliation for air and fuel measurements system in power plants[J].Thermal Power Generation,2014,43(11):35-40.
• [30] 仝卫国，杨耀权，金秀章.基于RBF神经网络的气体流量软测量模型研究[J].中国电机工程学报，2006(1):66-69.TONG Weiguo,YANG Yaoquan,JIN Xiuzhang.Study on soft-sensing model of the gas flowrate measurement based upon RBF neural network[J].Proceedings of the CSEE,2006(1):66-69.
• [31] 马祥，李清明，徐海超，等.基于微波法的煤粉浓度在线测量系统开发与应用[J].化工自动化及仪表，2022,49(3):358-61.MA Xiang,LI Qingming,XU Haichao,et al.Development and application of online measurement system for pulverized coal concentration based on microwave method[J].Control and Instruments in Chemical Industry,2022,49(3):358-361.
• [32] 郭琦.基于视频信号的燃烧器入炉煤量实时测量[D].北京：华北电力大学(北京),2020.
• [33] 刘翠翠.基于支持向量机的中速磨入炉煤量软测量技术研究[D].保定：华北电力大学，2016.
• [34] 秦授轩.基于光脉动谱法的煤粉颗粒在线测量[D].青岛：山东科技大学，2010.
• [35] WANG J S,GAO X W,ZHANG L.FCM-SVRs-based soft sensor modeling of granularity of pulverizing coal during ball milling[J].Journal of Northeastern University (Natural Science),2010,31(5):613-616.
• [36] 唐耀华，刘海宝，朱峰，等.基于软测量技术的双进双出磨煤机入炉煤量计算[J].仪表技术与传感器，2012(5):27-28,31.TANG Yaohua,LIU Haibao,ZHU Feng,et al.Calculating as-fired coal quantity for double-inlet and double-outlet mill based on soft sensing[J].Instrument Technique and Sensor,2012(5):27-28,31.
• [37] CHEN H,WANG X,WANG Z,et al.Application of a method for calculating coal quantity feed into boiler for double inlet and outlet ball mill in the coordinated control system[C]//Proceedings of the International Symposium on Resource Exploration and Environmental Science (REES).Ordos:[s.n.].2017-04-14.
• [38] 许伟强，刘翔.配置双进双出磨煤机的超临界机组入炉煤量计算方法及应用[J].华电技术，2018,40(7):10-13,17.XU Weiqiang,LIU Xiang.Research and application on calculating method of coal quantity as fire for supercritical unit equipped with double-inlet and double-outlet mill[J].Huadian Technology,2018,40(7):10-13,17.
• [39] 颜正，肖仁杰，黄鹏，等.基于烟气监测数据的标准煤耗率计量方法[J].能源科技，2023,21(4):51-55.YAN Zheng,XIAO Renjie,HUANG Peng,et al.Method for measuring standard coal consumption rate based on monitoring data of flue gas[J].Energy Science and Technology,2023,21(4):51-55.
• [40] 李健，尚星宇，王瑞.基于聚类算法的双进双出磨煤机入炉煤量软测量方法[J].热力发电，2020,49(11):114-119.LI Jian,SHANG Xingyu,WANG Rui.Soft measurement method of coal quantity for double-inlet and double-outlet mill based on clustering algorithm[J].Thermal Power Generation,2020,49(11):114-119.
• [41] NAHA A,DEB A K.Soft-sensor approach for measuring pulverised coal flow[J].Iet Science Measurement & Technology,2014,8(4):220-227.
• [42] XU C,ZHAO Y,HUANG J.The soft sensor model for mass flow rate measurement of pneumatically conveyed solids based on the artificial neural network[J].Acta Metrologica Sinica,2006,27(3):246-249.
• [43] SINGH B R,VALSALAM S R,PRATHEESH H,et al.Real time pulverised coal flow soft sensor for thermal power plants using evolutionary computation techniques[J].ICTACT Journal on Soft Computing,2015,5(2):911-916.
• [44] 李学斌，谭木娣，孙创奇，等.基于三节炉半微量法测定煤中碳含量[J].洁净煤技术，2018,24(S1):115-117.LI Xuebin,TAN Mudi,SUN Chuangqi,et al.Determination of carbon content in coal based on semi-micro method of three-section furnace[J].Clean Coal Technology,2018,24(S1):115-117.
• [45] 李慧，焦发存.电量-重量法和三节炉法测定煤中碳氢的比较[J].煤质技术，2013(4):35-37.LI Hui,JIAO Facun.Comparison of electricity quantity-gravimetric method and three-part furnace method about determination of carbon and hydrogen content in coal[J].Coal Quality Technology,2013(4):35-37.
• [46] 龚婉莉.采用元素分析仪测定煤中碳氢氮含量的应用研究 [J].煤质技术，2018(1):38-41,9.GONG Wanli.The application study on determination of carbon,hydrogen and nitrogen content in coal by elemental analyzer[J].Coal Quality Technology,2018,(1):38-41,9.
• [47] 韩学义.发电企业入炉煤元素碳含量监测技术研究现状[J].中国资源综合利用，2020,38(5):155-158.HAN Xueyi.Research status of monitoring technology for elemental carbon content of coal in power plants[J].China Resources Comprehensive Utilization,2020,38(5):155-158.
• [48] SHETA S,AFGAN M S,HOU Z Y,et al.Coal analysis by laser-induced breakdown spectroscopy:A tutorial review[J].Journal of Analytical Atomic Spectrometry,2019,34(6):1047-1082.
• [49] 冯有为.基于软测量技术的电站锅炉煤质/煤量在线监测系统的研究[D].武汉：华中科技大学，2011.
• [50] 符慧林，甘国文，谢七月.基于神经网络的电站锅炉入炉煤粉含碳量在线测量研究[J].计算机测量与控制，2015,23(4):1084-1086,1105.FU Huilin,GAN Guowen,XIE Qiyue.Studyon online measuring of carbon content of injected pulverized coal of utility boiler based on neural network[J].Computer Measurement & Control,2015,23(4):1084-1086,1105.
• [51] 王海群张素贞，刘军.人工神经网络在燃煤锅炉含碳量测量中的应用[J].锅炉技术，2004(2):35-38.WANG Haiqun,ZHANG Suzhen,LIU Jun.Application of artifical neural network in a coal burning boiler[J].Boiler Technology,2004(2):35-38.
• [52] 米翠丽，郭江龙，李晓光，等.基于烟气测试的电站锅炉煤质软测量模型[J].热力发电，2015,44(7):62-65,77.MI Cuili,GUO Jianglong,LI Xiaoguang,et al.Flue gas determination based soft-sensing model for coal quality monitoring for utility boilers[J].Thermal Power Generation,2015,44(7):62-65,77.
• [53] 刘福国.电站锅炉入炉煤元素分析和发热量的软测量实时监测技术[J].中国电机工程学报，2005(6):142-148.LIU Fuguo.Real time identification technique for ultimate analysis and calorific value of burning coal in utility boiler[J].Proceedings of the CSEE,2005(6):142-148.
• [54] 刘福国，郝卫东，韩小岗，等.基于烟气成分分析的电站锅炉入炉煤质监测模型[J].燃烧科学与技术，2002(5):441-445.LIU Fuguo,HAO Weidong,HAN Xiaogang,et al.Model of monitoring coal grade for utility boiler basing on flue gas compositional measurement[J].Journal of Combustion Science and Technology,2002(5):441-445.
• [55] ZHAO Z,ZENG D L,HU Y,et al.Soft sensing of coal quality[J].Thermal Science,2015,19(1):231-242.
• [56] 刘福国，郝卫东，胡志宏，等.采用炉膛燃烧和传热反问题在线测量超临界直流锅炉燃煤发热量[J].中国电机工程学报，2013,33(17):8-15,5.LIU Fuguo,HAO Weidong,HU Zhihong,et al.On-line determination of the calorific value of fired coals in supercritical pressure once-through boilers based on inverse furnace combustion and radiation problems[J].Proceedings of the CSEE,2013,33(17):8-15,5.
• [57] 刘吉臻，刘焕章，常太华，等.部分烟气信息下的锅炉煤质分析模型[J].中国电机工程学报，2007(14):1-5.LIU Jizhen,LIU Huanzhang,CHANG Taihua,et al.Analysis model of coal grade into boilers based on incomplete flue gas information[J].Proceedings of the CSEE,2007(14):1-5.
• [58] 成艳亭，宋立信，池锋，等.入炉煤质在线软测量技术研究与应用进展[J].洁净煤技术，2021,27(5):38-51.CHENG Yanting,SONG Lixin,CHI Feng,et al.Development and application of soft-measurement technology for online monitoring of coal quality in power generation[J].Clean Coal Technology,2021,27(5):38-51.
• [59] 程启明，胡晓青，王映斐，等.锅炉飞灰含碳量测量方法综述[J].上海电力学院学报，2011,27(5):519-524.CHENG Qiming,HU Xiaoqing,WANG Yingfei,et al.Summary of measurement methods of carbon content in fly ash[J].Journal of Shanghai University of Electric Power,2011,27(5):519-524.
• [60] 程启明，程尹曼，汪明媚，等.火电厂锅炉飞灰含碳量测量技术发展与现状[J].锅炉技术，2011,42(1):1-4.CHENG Qiming,CHENG Yinman,WANG Mingmei,et al.The development and status on the measurement techniques of carbon content of fly ash in b oiler of thermal power plant[J].Boiler Technology,2011,42(1):1-4.
• [61] 马维喆，董美蓉，黄泳如，等.激光诱导击穿光谱的飞灰碳含量定量分析方法[J].红外与激光工程，2021,50(9):201-210.MA Weizhe,DONG Meirong,HUANG Yongru,et al.Quantitative analysis method of unburned carbon content of fly ash by laser-induced breakdown spectroscopy[J].Infrared and Laser Engineering,2021,50(9):201-210.
• [62] 解海龙，张帅.锅炉飞灰含碳量监测的必要性及其技术的发展[J].科学技术与工程，2016,16(7):115-121.XIE Hailong,ZHANG Shuai.The necessity of monitoring the carbon content in boiler fly ash and the development of its technology [J] .Science Technology and Engineering,2016,16(7):115-121.
• [63] 方湘涛，叶念渝.基于BP神经网络的电厂锅炉飞灰含碳量预测[J].华中科技大学学报(自然科学版),2003(12):75-77.FANG Xiangtao,YE Nianyu.A system for forecasting the unburned carbon of the fly ash from utility boilersbased on BP artificial neural netwoks[J].Journal of Huazhong University of Science and Technology(Natural Science Edition),2003(12):75-77.
• [64] 刘鑫屏，李波，邓拓宇.一种SSAE+BPNN的变工况飞灰含碳量软测量方法[J].热力发电，2023,52(1):66-73.LIU Xinping,LI Bo,DENG Tuoyu.A soft measurement method of carbon content in fly ash under variable operating conditions of SSAE+BPNN[J].Thermal Power Generation,2023,52(1):66-73.
• [65] 白继亮，李斌，朱琎琦，等.基于BP神经网络的CFB锅炉飞灰含碳量建模[J].洁净煤技术，2020,26(S1):212-217.BAI Jiliang,LI Bin,ZHU Jinqi,et al.Modeling of carbon content in fly ash of CFB boiler based on BP neural network[J].Clean Coal Technology,2020,26(S1):212-217.
• [66] 叶兆青，鄢晓忠，卢坤杰，等.基于BP神经网络的超临界对冲火焰锅炉飞灰含碳量预测分析[J].锅炉制造，2014(5):1-9,30.YE Zhaoqing,YAN Xiaozhong,LU Kunjie,et al.A predictive analysis of carbon content in fly ash based on bp neural network[J].Boiler Manufacturing,2014(5):1-9,30.
• [67] 朱琎琦，牛晓凡，肖显斌.基于改良BP神经网络的生物质锅炉飞灰含碳量预测模型研究[J].可再生能源，2020,38(2):150-157.ZHU Jinqi,NIU Xiaofan,XIAO Xianbin.Prediction models of the carbon content of fly ash in a biomass boiler based on improved BP neural networks[J].Renewable Energy Resources,2020,38(2):150-157.
• [68] 陈植元，谭厚章，成思扬，等.基于机器学习的飞灰含碳量预测模型比较研究[J].热力发电，2023,52(7):64-73.CHEN Zhiyuan,TAN Houzhang,CHENG Siyang,et al.Comparison of prediction models of carbon content of fly ash based on machine learning[J].Thermal Power Generation,2023,52(7):64-73.