锅炉选择性催化还原(selective catalytic reduction,SCR)系统NOx排放测量存在实时性差、吹扫时测量异常的问题,精准的锅炉NOx排放预估可以提高测量的实时性和准确性.为此,提出了一种基于QSCSO-BLS和集成学习的锅炉NOx排放预估方法:在沙丘猫群算法(SCSO)中融合Lévy飞行策略和量子策略提出了改进沙丘猫群算法(QSCSO),对宽度学习系统(BLS)的权重、偏置进行优化,建立了QSCSO-BLS模型;采用QSCSO-BLS构造不同工况下的个体学习器,并使用参数回归方法将个体学习器输出和工况隶属度作为输入对结合器进行训练,得到BLS全工况NOx排放预估的集成学习模型.以某660 MW火电机组SCR系统运行数据为算例进行验证,结果表明,所提方法可以提高NOx预估的精度,为锅炉NOx排放预估提供了新方法.
The NOx emission measurement in the selective catalytic reduction(SCR)system of boiler has the problems of poor real-time performance and abnormal measurement during purging. Accurate prediction of boiler NOx emission can improve the real-time performance and accuracy of measurement. Therefore, a boiler NOx emission prediction method based on QSCSO-BLS and ensemble learning is proposed: By combining Lévy flight strategy and quantum strategy in the Dune Cat swarm algorithm(SCSO), an improved Dune Cat swarm algorithm(QSCSO)is proposed. The weight and bias of the width learning system(BLS)are optimized, and the QSCSO-BLS model is established. QSCSO-BLS was used to construct individual learner under different working conditions, and parametric regression method was used to train the combinator with individual learner output and working condition membership as inputs, and an integrated learning model for predicting NOx emission under all working conditions of BLS was obtained. The operation data of SCR system of a 660 MW thermal power unit is taken as an example. The results show that the proposed method can improve the accuracy of NOx prediction and provide a new method for boiler NOx emission prediction.
[1] LI X S, LI F J, ZHENG S J, et al. NOx concentration prediction with a flexible cascaded echo-state network in a cement clinker calcination system[J]. IEEE Trans Ind Inform, 2024, 20(7): 9644-9654. DOI: 10.1109/TII.2024.3386973.
[2] QIAO J F, ZHOU J L, MENG X. A multitask learning model for the prediction of NOx emissions in municipal solid waste incineration processes[J]. IEEE Trans Instrum Meas, 1809, 72: 2502214. DOI: 10.1109/TIM.2022.3225056.
[3] 闫来清.SCR烟气脱硝系统数据驱动建模与优化控制研究[D].北京:华北电力大学, 2020.
[4] 王珑宪,赵文杰.基于变量选择的电站燃煤锅炉NOx排放浓度预估[J].计量学报, 2023, 44(10): 1590-1596. DOI: 10.3969/j.issn.1000-1158.2023.10.15.
[5] HU B, LIU C, YANG Y, et al. Adaptive internal model control of SCR denitration system based on multi-objective optimization[J]. IEEE Access, 2022, 10: 24769-24785. DOI: 10.1109/ACCESS.2022.3154418.
[6] TANG Z H, WANG S K, CHAI X Y, et al. Auto-encoder-extreme learning machine model for boiler NOx emission concentration prediction[J]. Energy, 2022, 256: 124552. DOI: 10.1016/j.energy.2022.124552.
[7] 杨国田,刘凯,王英男.基于门控循环单元神经网络的NOx排放量预测[J].控制工程, 2022, 29(7): 1204-1209. DOI: 10.14107/j.cnki.kzgc.20200017.
[8] HAN Z Z, XIE Y, HOSSAIN M M, et al. A hybrid deep neural network model for NOx emission prediction of heavy oil-fired boiler flames[J]. Fuel, 2023, 333: 126419. DOI: 10.1016/j.fuel.2022.126419.
[9] PHILIP CHEN C L, LIU Z L. Broad learning system: an effective and efficient incremental learning system without the need for deep architecture[J]. IEEE Trans Neural Netw Learn Syst, 2018, 29(1): 10-24. DOI: 10.1109/TNNLS.2017.2716952.
[10] 杜康萍,隋璘,熊伟丽.基于自适应稀疏宽度学习系统的软测量建模[J].系统仿真学报, 2024, 17(8): 131-143. DOI: 10.16182/j.issn1004731x.joss.24-0096.
[11] 李苗苗,王秋萍,惠蕙.分数阶策略和带有Lévy飞行的螺旋蝙蝠算法[J].计算机工程与应用, 2021, 57(18): 75-81. DOI: 10.3778/j.issn.1002-8331.2008-0164.
[12] LU Y, SUN Y, LIU X D, et al. Control allocation for a class of morphing aircraft with integer constraints based on Lévy flight[J]. J Syst Eng Electron, 2020, 31(4): 826-840. DOI: 10.23919/JSEE.2020.000056.
[13] FERRARI D, CARRETTA S, AMORETTI M. A modular quantum compilation framework for distributed quantum computing[J]. IEEE Trans Quantum Eng, 2023, 4: 2500213. DOI: 10.1109/TQE.2023.3303935.
[14] 孙俊.量子行为粒子群优化算法研究[D].无锡:江南大学, 2009.
[15] WU X L, YU X D, XU R, et al. Nonlinear dynamic soft-sensing modeling of NOx emission of a selective catalytic reduction denitration system[J]. IEEE Trans Instrum Meas, 2022, 71: 2504911. DOI: 10.1109/TIM.2022.3141154.
[16] 吴家标,刘兴高.基于集成学习的CFB锅炉氮氧化物排放质量浓度在线建模研究[J].热力发电, 2021, 53(12): 86-92. DOI: 10.19666/j.rlfd.202404086.
[17] HUANG D, WANG C D, WU J S, et al. Ultra-scalable spectral clustering and ensemble clustering[J]. IEEE Trans Knowl Data Eng, 2020, 32(6): 1212-1226. DOI: 10.1109/TKDE.2019.2903410.
[18] DONG Z, JIANG W, SUN M, et al. Soft sensing of NOx emissions from thermal power units based on adaptive GMM two-step clustering algorithm and ensemble learning[J]. IEEE Trans Instrum Meas, 2023, 72: 2515719. DOI: 10.1109/TIM.2023.3279913.
[19] SHI Z Y, HUANG K, HONG S Z, et al. Estimating the lag time between flight arrivals and parking exit volumes at a major airport: a practical approach[J]. IEEE Access, 2024, 12: 63351-63360. DOI: 10.1109/ACCESS.2024.3396062. (
