肖红亮,柯希玮,潘帅,郎丽萍,王君峰,祁海鹰,张守玉,吕俊复,黄中

• 1:北京怀柔实验室
• 2:怀柔实验室山西研究院
• 3:中国石油大学(北京)机械与储运工程学院
• 4:哈尔滨锅炉厂有限责任公司

摘要(Abstract)：

循环流化床（CFB）锅炉在我国发电行业具有重要地位，然而炉膛燃烧系统具有多参数、多变量、非线性、时变性等强耦合特征，使系统的精确建模和预测困难。机器学习凭借强大的非线性处理能力和预测性能，在CFB领域展现出广阔的应用前景。探讨了机器学习技术在该领域的应用，包括最小流化速度预测、污染物排放预测、床层压力预测、床层温度/热效率预测、颗粒循环流率预测、计算流体力学（computational fluid dynamics,CFD）场的降阶模型、锅炉安全控制系统模型等方面。分析了这些技术在不同场景中的优势和局限，展望了CFB锅炉在大数据时代面临的机遇和挑战，关注模型解释性、泛化能力提升、数据质量多样性、模型结合传统方法、实验验证等是未来研究的重点方向。

关键词(KeyWords)： 燃煤锅炉;CFB锅炉;机器学习;非线性;预测

Abstract:

Keywords:

基金项目(Foundation): 怀柔实验室项目(ZD2023008A)~~

作者(Author): 肖红亮,柯希玮,潘帅,郎丽萍,王君峰,祁海鹰,张守玉,吕俊复,黄中

DOI: 10.19666/j.rlfd.202411246

参考文献(References)：

• [1]胡南,李金晶,刘雪敏,等.大型CFB锅炉床压横向波动的机制研究[J].中国电机工程学报, 2013, 33(20):1-7.HU Nan, LI Jinjing, LIU Xuemin, et al. Mechanism study of lateral bed pressure wave of large scale CFB boilers[J]. Proceedings of the CSEE, 2013, 33(20):1-7.
• [2] CHEW J W, COCCO R A. Application of machine learning methods to understand and predict circulating fluidized bed riser flow characteristics[J]. Chemical Engineering Science, 2020, 217:115503.
• [3]韩义,张奇月,段伦博,等.基于机器学习的循环流化床机组出力预测[J].洁净煤技术, 2022, 28(6):199-205.HAN Yi, ZHANG Qiyue, DUAN Lunbo, et al.Performance prediction of circulating fluidized bed unit based on machine learning[J]. Clean Coal Technology,2022, 28(6):199-205.
• [4]王万良,张兆娟,高楠,等.基于人工智能技术的大数据分析方法研究进展[J].计算机集成制造系统, 2019,25(3):529-547.WANG Wanliang, ZHANG Zhaojuan, GAO Nan, et al.Progress of big data analytics methods based on artificial intelligence technology[J]. Computer Integrated Manufacturing Systems, 2019, 25(3):529-547.
• [5] CUI Y, ZHONG W, ZHOU Z, et al. Coupled simulation and deep-learning prediction of combustion and heat transfer processes in supercritical CO2 CFB boiler[J].Advanced Powder Technology, 2022, 33(1):103361.
• [6] GóRRIZ J M, RAMíREZ J, ORTíZ A, et al. Artificial intelligence within the interplay between natural and artificial computation:advances in data science, trends and applications[J]. Neurocomputing, 2020, 410:237-270.
• [7]包国强,顾维根,穆维国,等.基于机器学习的气固流化床最小流化速度预测[J].洁净煤技术, 2021, 27(5):25-31.BAO Guoqiang, GU Weigen, MU Weiguo, et al.Prediction of minimum fluidization velocity in gas-solid fluidized bed based on machine learning[J]. Clean Coal Technology, 2021, 27(5):25-31.
• [8] SHI X, LAN X, LIU F, et al. Effect of particle size distribution on hydrodynamics and solids back-mixing in CFB risers using CPFD simulation[J]. Powder Technology, 2014, 266:135-143.
• [9] CHEN X, WANG J, LI J. Coarse grid simulation of heterogeneous gas-solid flow in a CFB riser with polydisperse particles[J]. Chemical Engineering Journal,2013, 234:173-183.
• [10] CHEW J W, WOLZ J R, HRENYA C M. Axial segregation in bubbling gas-fluidized beds with Gaussian and lognormal distributions of Geldart Group B particles[J]. AIChE Journal, 2010, 56(12):3049-3061.
• [11] RASTEH M, FARHADI F, AHMADI G. Empirical models for minimum fluidization velocity of particles with different size distribution in tapered fluidized beds[J]. Powder Technology, 2018, 338:563-575.
• [12] KORKERD K, SOANUCH C, GIDASPOW D, et al.Artificial neural network model for predicting minimum fluidization velocity and maximum pressure drop of gas fluidized bed with different particle size distributions[J].South African Journal of Chemical Engineering, 2021,37:61-73.
• [13] FARIZHANDI A A K., ZHAO H, LAU R. Modeling the change in particle size distribution in a gas-solid fluidized bed due to particle attrition using a hybrid artificial neural network-genetic algorithm approach[J].Chemical Engineering Science, 2016, 155:210-220.
• [14]刘吉臻,秦天牧,杨婷婷,等.基于偏互信息的变量选择方法及其在火电厂SCR系统建模中的应用[J].中国电机工程学报, 2016, 36(9):2438-2443.LIU Jizhen, QIN Tianmu, YANG Tingting, et al. Variable selection method based on partial mutual information and its application in power plant SCR system modeling[J].Proceedings of the CSEE, 2016, 36(9):2438-2443.
• [15] YANG G, WANG Y, LI X. Prediction of the NO emissions from thermal power plant using long-short term memory neural network[J]. Energy, 2020, 192:116597.
• [16] XIE P, GAO M, ZHANG H, et al. Dynamic modeling for NOx emission sequence prediction of SCR system outlet based on sequence to sequence long short-term memory network[J]. Energy, 2020, 190:116482.
• [17] WANG C, LIU Y, ZHENG S, et al. Optimizing combustion of coal fired boilers for reducing NOx emission using Gaussian Process[J]. Energy, 2018, 153:149-158.
• [18] LI X, LIU J, NIU P. Least square parallel extreme learning machine for modeling NOx emission of a300MW circulating fluidized bed boiler[J]. IEEE Access,2020, 8:79619-79636.
• [19] MA Y, NIU P, YAN S, et al. A modified online sequential extreme learning machine for building circulation fluidized bed boiler’s NOx emission model[J]. Applied Mathematics and Computation, 2018, 334:214-226.
• [20] NIU P, MA Y, LI G. Model NOx emission and thermal efficiency of CFBB based on an ameliorated extreme learning machine[J]. Soft Computing, 2017, 22(14):4685-4701.
• [21] LI X, NIU P, LI G, et al. An adaptive extreme learning machine for modeling NOx emission of a 300 MW circulating fluidized bed boiler[J]. Neural Processing Letters, 2017, 46(2):643-662.
• [22] LI G Q, QI X B, CHAN K C, et al. Deep bidirectional learning machine for predicting NOx emissions and boiler efficiency from a coal-fired boiler[J]. Energy&Fuels, 2017, 31(10):11471-11480.
• [23] TAN P, XIA J, ZHANG C, et al. Modeling and reduction of NOx emissions for a 700 MW coal-fired boiler with the advanced machine learning method[J]. Energy, 2016,94:672-679.
• [24] LIUKKONEN M, H?LIKK?E, KUIVALAINEN R, et al. Modeling of nitrogen oxide emissions in fluidized bed combustion using artificial neural networks[J].International Journal of Data Engineering, 2010, 1(2):26-35.
• [25] LI S, MA S, WANG F. A Combined NOx emission prediction model based on semi-empirical model and black box model[J]. Energy, 2023, 264:126130.
• [26] CHEN J, HONG F, GAO M, et al. Prediction method of bed pressure based on deep learning[J]. SSRN Electronic Journal, 2021, 1:3901836.
• [27] ADAMS D, OH D H., KIM D W, et al. Prediction of SOx-NOx emission from a coal-fired CFB power plant with machine learning:Plant data learned by deep neural network and least square support vector machine[J].Journal of Cleaner Production, 2020, 270:122310.
• [28] KRZYWANSKI J, NOWAK W. Artificial intelligence treatment of SO2 emissions from CFBC in air and oxygen-enriched conditions[J]. Journal of Energy Engineering, 2016, 142(1):04015017.
• [29]曹歌瀚,黄亚继,徐文韬,等.基于机器学习的燃煤锅炉分工况建模与燃烧优化[J].锅炉技术, 2023, 54(5):41-47.CAO Gehan, HUANG Yaji, XU Wentao, et al. Modeling and online combustion optimization of coal-fired boiler under different working conditions based on machine learning[J]. Boiler Technology, 2023, 54(5):41-47.
• [30]任少君,朱保宇,翁琪航,等.基于物理信息神经网络的燃煤锅炉NOx排放浓度预测方法[J].中国电机工程学报, 2024, 44(20):8157-8166.REN Shaojun, ZHU Baoyu, WENG Qihang, et al.Forecasting method for NOx emission in coal fired boiler based on physics-informed neural network[J].Proceedings of the CSEE, 2024, 44(20):8157-8166.
• [31] WAN A, YANG J, CHEN T, et al. Dynamic pollution emission prediction method of a combined heat and power system based on the hybrid CNN-LSTM model and attention mechanism[J]. Environmental Science and Pollution Research, 2022, 29(46):69918-69931.
• [32] OLORUNTOBA A, ZHANG Y, XIAO H. Study on effect of gas distributor in fluidized bed reactors by hydrodynamics-reaction-coupled simulations[J]. Chemical Engineering Research and Design, 2022, 177:431-447.
• [33] OLORUNTOBA A, ZHANG Y, XIAO H. Hydrodynamics-reaction-coupled simulations in a low-scale batch FCC regenerator:comparison between an annular and a free-bubbling fluidized beds[J]. Powder Technology,2022, 407:117608.
• [34] XIAO H, ZHANG Y, HUA Y, et al. Quantitative comparison of measurement quality of cross-correlation based particle velocity instruments in different gas fluidization regimes[J]. Advanced Powder Technology,2021, 32(10):3915-3926.
• [35] XIAO H, ZHANG Y, WANG J. Virtual error quantification of cross-correlation algorithm for solids velocity measurement in different gas fluidization regimes[J]. Chemical Engineering Science, 2021, 246:117013.
• [36] XIAO H, ZHANG Y, WANG J. Correlating measurement qualities of cross-correlation based solids velocimetry with solids convection-mixing competing mechanism in different gas fluidization regimes[J]. Chemical Engineering Science, 2022, 253:117602.
• [37]刘吉臻,洪烽,吕游,等.循环流化床锅炉床温动态模型[J].中国电机工程学报, 2016, 36(8):2168-2174.LIU Jizhen, HONG Feng, LYU You, et al. Dynamic modeling on bed temperature of circulating fluidized bed boiler[J]. Proceedings of the CSEE, 2016, 36(8):2168-2174.
• [38]张殿朝,李俊峰,王义俊.基于PSO-LSSVM的循环流化床锅炉多目标燃烧优化[J].广东电力, 2022, 35(7):98-106.ZHANG Dianchao, LI Junfeng, WANG Yijun.Multi-objective combustion optimization of circulating fluidized bed boiler based on PSO-LSSVM[J].Guangdong Electric Power, 2022, 35(7):98-106.
• [39] LV Y, HONG F, YANG T, et al. A dynamic model for the bed temperature prediction of circulating fluidized bed boilers based on least squares support vector machine with real operational data[J]. Energy, 2017, 124:284-294.
• [40] GROCHOWALSKI J, JACHYMEK P, ANDRZEJCZYK M, et al. Towards application of machine learning algorithms for prediction temperature distribution within CFB boiler based on specified operating conditions[J].Energy, 2021, 237:121538.
• [41] ZHANG Y, ZHANG B, WU Z. Multi-model modeling of CFB boiler bed temperature system based on principal component analysis[J]. IEEE Access, 2019, 8:389-399.
• [42] FARIDI I K, TSOTSAS E, HEINEKEN W, et al.Spatio-temporal prediction of temperature in fluidized bed biomass gasifier using dynamic recurrent neural network method[J]. Applied Thermal Engineering, 2023,219:119334.
• [43] HONG F, LONG D, CHEN J, et al. Modeling for the bed temperature 2D-interval prediction of CFB boilers based on long-short term memory network[J]. Energy, 2020,194:116733.
• [44] ASHRAF W M, UDDIN G M, ARAFAT S M, et al.Strategic-level performance enhancement of a 660 MWe supercritical power plant and emissions reduction by AI approach[J]. Energy Conversion and Management, 2021,250:114913.
• [45] LIAO W, JUANNING S, YAN G. Bed temperature modeling of circulating fluidized bed boiler based on PCA and neural network[C]. 2010 2nd International Conference on Future Computer and Communication,Wuhan, China, 2010.
• [46] CHEW J W, LAMARCHE W C Q, COCCO R A. 100years of scaling up fluidized bed and circulating fluidized bed reactors[J]. Powder Technology, 2022, 409:117813.
• [47] KONG D, WANG S, YU J, et al. Investigation of non-uniform characteristics in a 300 MWth circulating fluidized bed with different coal feeding modes[J].Advanced Powder Technology, 2023, 34(7):104036.
• [48] ASGHAR A B, FAROOQ S, KHURRAM M S, et al.Estimation of the solid circulation rate in circulating fluidized bed system using adaptive neuro-fuzzy algorithm[J]. Energies, 2021, 15(1):211.
• [49]陈鸿伟,梁锦俊,宋杨凡,等.基于不同ANN模型对流化床颗粒内循环量的预测研究[J].华北电力大学学报, 2021, 48(5):113-120.CHEN Hongwei, LIANG Jinjun, SONG Yangfan, et al.Prediction of internal circulation of particles in fluidized bed based on different ANN models[J]. Journal of North China Electric Power University, 2021, 48(50):113-120.
• [50] WANG J. Continuum theory for dense gas-solid flow:a state-of-the-art review[J]. Chemical Engineering Science,2020, 215:115428.
• [51] YANG Z, ZHANG Y, OLORUNTOBA A, et al. MP-PIC simulation of the effects of spent catalyst distribution and horizontal baffle in an industrial FCC regenerator. Part I:Effects on hydrodynamics[J]. Chemical Engineering Journal, 2021, 412:128634.
• [52] KOTTEDA V K, KOMMU A, KUMAR V. A data-driven framework for uncertainty quantification of a fluidized bed[C]. 2019 IEEE High Performance Extreme Computing Conference(HPEC), Waltham, USA, 2019.
• [53] JIANG Y, KOLEHMAINEN J, GU Y, et al.Neural-network-based filtered drag model for gas-particle flows[J]. Powder Technology, 2019, 346:403-413.
• [54] ZHU L T, TANG J X, LUO Z H. Machine learning to assist filtered two-fluid model development for dense gas-particle flows[J]. AIChE journal, 2020, 66(6):e16973.
• [55] OUYANG B, ZHU L T, LUO Z H. Machine learning for full spatiotemporal acceleration of gas-particle flow simulations[J]. Powder Technology, 2022, 408:117701.
• [56] OUYANG B, ZHU L T, SU Y H, et al. A hybrid mesoscale closure combining CFD and deep learning for coarse-grid prediction of gas-particle flow dynamics[J].Chemical Engineering Science, 2022, 248:117268.
• [57] OUYANG B, ZHU L T, LUO Z H. Data-driven modeling of mesoscale solids stress closures for filtered two-fluid model in gas-particle flows[J]. AIChE Journal, 2021,67(7):e17290.
• [58] NIKOLOPOULOS A, SAMLIS C, ZENELI M, et al.Introducing an artificial neural network energy minimization multi-scale drag scheme for fluidized particles[J]. Chemical Engineering Science, 2021, 229:116013.
• [59]李天宇,陈曦,钟文琪.基于CFD与POD的煤粉锅炉三维速度场快速预测[J].东南大学学报(自然科学版),2022, 52(4):641-649.LI Tianyu, CHEN Xi, ZHONG Wenqi. Rapid prediction of three-dimensional velocity field of pulverized coal boiler based on CFD and POD[J]. Journal of Southeast University(Natural Science Edition), 2022, 52(4):641-649.
• [60]付颜,潘蕾,王钱超.基于机器学习的锅炉送风控制系统仿真及优化[J].工程热物理学报, 2022, 43(7):1777-1782.FU Yan, PAN Lei, WANG Qianchao. Simulation and optimization of boiler air supply control system based on machine learning[J]. Journal of Engineering Thermophysics, 2022, 43(7):1777-1782.
• [61]张维,刘吉臻,高明明.基于数据挖掘的循环流化床锅炉辅机故障预警[J].动力工程学报, 2019, 39(10):826-833.ZHANG Wei, LIU Jizhen, GAO Mingming. Early fault warning of auxiliary equipment for circulating fluidized bed boilers based on data mining[J]. Journal of Chinese Society of Power Engineering, 2019, 39(10):826-833.
• [62] KIM M, JUNG S, KIM B, et al. Fault detection method via k-nearest neighbor normalization and weight local outlier factor for circulating fluidized bed boiler with multimode process[J]. Energies, 2022, 15(17):6146.
• [63] JIA X, SANG Y, LI Y, et al. Short-term forecasting for supercharged boiler safety performance based on advanced data-driven modelling framework[J]. Energy,2022, 239:122449
• [64]谭厚章,周上坤,杨文俊,等.氨燃料经济性分析及煤氨混燃研究进展[J].中国电机工程学报, 2023, 43(1):181-191.TAN Houzhang, ZHOU Shangkun, YANG Wenjun, et al.Economic analysis of ammonia and research progress of coal-ammonia co-firing[J]. Proceedings of the CSEE,2023, 43(1):181-191.
• [65]肖红亮,吕俊复,张扬,等.基于循环流化床燃烧的多元废弃物处理技术研究进展[J].锅炉技术, 2024,55(6):1-11.XIAO Hongliang, LYU Junfu, ZHANG Yang, et al.Research progress on multi-waste treatment technology based on circulating fluidized bed combustion[J]. Boiler Technology, 2024, 55(6):1-11.
• [66]张维,高明明,洪烽,等.基于BP-SVM模糊信息粒化掺烧煤泥循环流化床经济性建模[J].中国电机工程学报, 2018, 38(4):1093-1100.ZHANG Wei, GAO Mingming, HONG Feng, et al.Energy cost modeling for circulating fluidized bed boiler mix-burning coal slime based on BP-SVM and fuzzy information granulation[J]. Proceedings of the CSEE,2018, 38(4):1093-1100.
• [67]张维,高明明.掺烧煤泥循环流化床机组经济性优化运行研究[J].中国电机工程学报, 2018, 38(6):4807-4810.ZHANG Wei, GAO Mingming. Economic optimization study of mix-burning coal slime circulating fluidized bed boiler[J]. Proceedings of the CSEE, 2018, 38(6):4807-4810.
• [68] SUN L, YOU F. Machine learning and data-driven techniques for the control of smart power generation systems:an uncertainty handling perspective[J].Engineering, 2021, 7(9):1239-1247.
• [69] AZALI S, SHEIKHAN M. Intelligent control of photovoltaic system using BPSO-GSA-optimized neural network and fuzzy-based PID for maximum power point tracking[J]. Applied Intelligence, 2015, 44(1):88-110.
• [70] SUN L, LI D, HU K, et al. On tuning and practical implementation of active disturbance rejection controller:a case study from a regenerative heater in a 1 000 MW power plant[J]. Industrial&Engineering Chemistry Research, 2016, 55(23):6686-6695.
• [71] NIU P, SUN L, MA Y, et al. A novel control strategy for circulating fluidized bed boiler combustion processes:dealing with coupling and uncertainties in complex environments[J]. Journal of Coupled Systems and Multiscale Dynamics, 2015, 3(4):341-350.
• [72] DEEPA S N, BARANILINGESAN I. Optimized deep learning neural network predictive controller for continuous stirred tank reactor[J]. Computers&Electrical Engineering, 2018, 71:782-797.
• [73]王万召,王红阁,谭文.智能解耦控制器在循环流化床锅炉燃烧系统中的应用[J].动力工程, 2009, 29(8):757-760.WANG Wanzhao, WANG Hongge, TAN Wen.Application of intelligent decoupling controller in circulating fluidized bed boiler combustion system[J].Journal of Power Engineering, 2009, 29(8):757-760.
• [74]柯希玮,蔡润夏,吕俊复,等.钙基脱硫剂对循环流化床NOx排放影响研究进展[J].洁净煤技术, 2019,25(1):1-11.KE Xiwei, CAI Runxia, LYU Junfu, et al. Research progress of the effects of Ca-based sorbents on the NOx reaction in circulating fluidized bed boilers[J]. Clean Coal Technology, 2019, 25(1):1-11.