大型电站锅炉配煤掺烧的NOx排放特性预测与优化运行
|
摘要
能源是当今世界经济发展的重要基础,随着能源消费的增长,我国污染物排放量持续增长,而煤燃烧的污染排放已成为中国最大的大气污染源,所以如何实现煤种变化、煤质波动情况下燃煤电站锅炉的高效低污染燃烧,是我国可持续发展的一个重要课题。本文围绕大型燃煤电站锅炉配煤掺烧优化运行开展研究,所提出的锅炉燃烧优化则是通过调整锅炉运行参数,以达到兼顾降低NOx排放和提高锅炉燃烧效率的目标,具有一定的现实意义。
首先,综述了燃煤电站锅炉NOx生成机理、人工神经网络和遗传算法,同时介绍了配煤掺烧技术及本文大型锅炉的掺烧方案,为后文建立模型提供了基础。
然后,在某台700MW四角切圆燃煤电站锅炉的NOx排放特性及锅炉效率多工况热态测试的基础上,应用人工神经网络建立大型四角切圆燃煤电站锅炉NOx特性及锅炉效率预测模型并进行预测,检验样本NOx和锅炉效率预测值与实测值的平均相对误差分别为3.63%和0.23%,证实模型的可行性。
最后,在所建立的700MW四角切圆燃煤电站锅炉配煤掺烧NOx排放特性和锅炉效率预测模型基础上,综合考虑NOx排放特性和锅炉燃烧效率两方面的影响,结合遗传算法建立了锅炉燃烧优化模型,并结合锅炉测试试验,分别以不掺烧第1组、掺烧比分别为1:4和2:3的第7和18组试验工况为例,利用该优化模型寻优。不掺烧的第1组优化后NOx浓度为421.44mg·m-3,降低了37.56%,锅炉效率为94.56%,提高了0.09%;掺烧C磨的第7组优化后NOx排放浓度为255.05mg·m-3,降低了29.43%,,同时锅炉效率为94.13%,提高了0.42%;掺烧B和C磨的第18组优化后NOx排放浓度为215.40mg·m-3,降低了30.56%,,同时锅炉效率为94.80%,提高了0.88%。
该模型可在掺烧非设计煤种情况下寻找出最优运行参数,降低锅炉NOx排放浓度并提高锅炉效率;同时结果表明国产煤掺烧印尼煤随掺烧比增大,NOx排放浓度降低,实际工程中掺烧情况复杂,降低NOx排放量的同时还必须考虑到锅炉效率等其他因素;当国产掺烧印尼煤,选择掺烧D磨煤机和E磨煤机有利于降低NOx排放量。
Energy is an important foundation for today's world economy, with the growth of energy consumption, emissions continue to grow in China, while the pollution from coal combustion has been the biggest pollution source in China, how to achieve boiler combustion with high efficiency and low pollutants emission in the condition changes in coal or fluctuation in coal quality becomes the very key task for our country’s sustainable development. This work was mainly involved in the technology about combustion optimization of large-scale mixed coal-fired boiler, boiler combustion optimization is to give attention to improve boiler efficiency and reduce nitrogen oxide emissions from boiler through adjustment of boiler operation parameters. It has great practical significance.
The paper mainly contains mechanisms of NOx formation,, artificial neural networks and some optimizing algorithms. This paper also introduced blending technology and large-scale boilers blending program. It provides a theoretical basis for the establishment of model.
In this paper, the NOx emission property and boiler efficiency of a 700MW utility tangentially firing coal burned boiler are experimentally investigated, an artificial neural network model on NOx emission property and boiler efficiency of large-scale boiler is developed to predict the NOx emission, and the predicted result indicates the mean relative error of NOx emission and boiler efficiency is 3.63% and 0.23% between experimental value and the calculated value, respectively , which proves the feasibility of the model.
Finally, the boiler combustion optimization model based on the neural network prediction model of 700MW tangentially coal-fired boiler blending NOx emission and the boiler efficiency, considering the impact of the NOx emission characteristics and boiler combustion efficiency, combined with the genetic algorithm was established. This model combined with boiler tests is used to serch the optimization operating parameters of group 1 with no blending, group 7 with blending C and group 18 with blending B and C. The optimized NOx concentration of group 1 is 421.44 mg·m-3, decreased 37.56%, the boiler efficiency is 94.5%, increased 0.09%; the optimized NOx concentration of group 7 is 255.05 mg·m-3, decreased 29.43 %, the boiler efficiency is 94.13%, increased 0.42% and the optimized NOx concentration of group 18 is 215.40 mg·m-3, decreased 30.56%, the boiler efficiency is 94.80%, increased 0.88%.
The result shows that the combustion optimization model can be used to reduce boiler NOx emissions and improve boiler efficiency through adjustment of boiler operation parameters when the boiler blending non-design coals; and shows that when domestic coals blending Indonesian coals, more the mixing ratio, less the NOx emission; the actual blending project is much more complicated,so reducing NOx emissions must also take into account other factors such as boiler efficiency; and Blending D and E coal mill is helpful to reduce NOx when domestic coals blending Indonesian coals.
首先,综述了燃煤电站锅炉NOx生成机理、人工神经网络和遗传算法,同时介绍了配煤掺烧技术及本文大型锅炉的掺烧方案,为后文建立模型提供了基础。
然后,在某台700MW四角切圆燃煤电站锅炉的NOx排放特性及锅炉效率多工况热态测试的基础上,应用人工神经网络建立大型四角切圆燃煤电站锅炉NOx特性及锅炉效率预测模型并进行预测,检验样本NOx和锅炉效率预测值与实测值的平均相对误差分别为3.63%和0.23%,证实模型的可行性。
最后,在所建立的700MW四角切圆燃煤电站锅炉配煤掺烧NOx排放特性和锅炉效率预测模型基础上,综合考虑NOx排放特性和锅炉燃烧效率两方面的影响,结合遗传算法建立了锅炉燃烧优化模型,并结合锅炉测试试验,分别以不掺烧第1组、掺烧比分别为1:4和2:3的第7和18组试验工况为例,利用该优化模型寻优。不掺烧的第1组优化后NOx浓度为421.44mg·m-3,降低了37.56%,锅炉效率为94.56%,提高了0.09%;掺烧C磨的第7组优化后NOx排放浓度为255.05mg·m-3,降低了29.43%,,同时锅炉效率为94.13%,提高了0.42%;掺烧B和C磨的第18组优化后NOx排放浓度为215.40mg·m-3,降低了30.56%,,同时锅炉效率为94.80%,提高了0.88%。
该模型可在掺烧非设计煤种情况下寻找出最优运行参数,降低锅炉NOx排放浓度并提高锅炉效率;同时结果表明国产煤掺烧印尼煤随掺烧比增大,NOx排放浓度降低,实际工程中掺烧情况复杂,降低NOx排放量的同时还必须考虑到锅炉效率等其他因素;当国产掺烧印尼煤,选择掺烧D磨煤机和E磨煤机有利于降低NOx排放量。
Energy is an important foundation for today's world economy, with the growth of energy consumption, emissions continue to grow in China, while the pollution from coal combustion has been the biggest pollution source in China, how to achieve boiler combustion with high efficiency and low pollutants emission in the condition changes in coal or fluctuation in coal quality becomes the very key task for our country’s sustainable development. This work was mainly involved in the technology about combustion optimization of large-scale mixed coal-fired boiler, boiler combustion optimization is to give attention to improve boiler efficiency and reduce nitrogen oxide emissions from boiler through adjustment of boiler operation parameters. It has great practical significance.
The paper mainly contains mechanisms of NOx formation,, artificial neural networks and some optimizing algorithms. This paper also introduced blending technology and large-scale boilers blending program. It provides a theoretical basis for the establishment of model.
In this paper, the NOx emission property and boiler efficiency of a 700MW utility tangentially firing coal burned boiler are experimentally investigated, an artificial neural network model on NOx emission property and boiler efficiency of large-scale boiler is developed to predict the NOx emission, and the predicted result indicates the mean relative error of NOx emission and boiler efficiency is 3.63% and 0.23% between experimental value and the calculated value, respectively , which proves the feasibility of the model.
Finally, the boiler combustion optimization model based on the neural network prediction model of 700MW tangentially coal-fired boiler blending NOx emission and the boiler efficiency, considering the impact of the NOx emission characteristics and boiler combustion efficiency, combined with the genetic algorithm was established. This model combined with boiler tests is used to serch the optimization operating parameters of group 1 with no blending, group 7 with blending C and group 18 with blending B and C. The optimized NOx concentration of group 1 is 421.44 mg·m-3, decreased 37.56%, the boiler efficiency is 94.5%, increased 0.09%; the optimized NOx concentration of group 7 is 255.05 mg·m-3, decreased 29.43 %, the boiler efficiency is 94.13%, increased 0.42% and the optimized NOx concentration of group 18 is 215.40 mg·m-3, decreased 30.56%, the boiler efficiency is 94.80%, increased 0.88%.
The result shows that the combustion optimization model can be used to reduce boiler NOx emissions and improve boiler efficiency through adjustment of boiler operation parameters when the boiler blending non-design coals; and shows that when domestic coals blending Indonesian coals, more the mixing ratio, less the NOx emission; the actual blending project is much more complicated,so reducing NOx emissions must also take into account other factors such as boiler efficiency; and Blending D and E coal mill is helpful to reduce NOx when domestic coals blending Indonesian coals.
引文
[1]周小川.利用金融市场支持节能减排工作.权威论坛,财富,2007
[2]何伯述,陈梅倩,林江等,污染物的脱除率对燃煤电站生态效率的影响,北方交通大学学报.2003(2):1-5
[3]魏辉.燃煤电站锅炉低NOx燃烧优化运行策略的研究[D].上海:上海交通大学, 2008.
[4]朱法华,王圣,郑有飞.火电NOx排放现状与预测及控制对策[J].能源环境保护.2004,18(1):1-5
[5] Andreas R, John P. B, Hendrik N,et al. Increase in tropospheric nitrogen dioxide over China observed from space[J]. Nature, 2005, 437(1): 129-132.
[6]何育东,雷兆团,柳宏刚等,一项降低电厂NOx排放量的技术,电力环境保护2002(9):16-18
[7]周昊,朱洪波,曾庭华,等.大型四角切圆燃烧锅炉NOx排放特性的神经网络模型[J].中国电机工程学报,2002,22(1):33-37
[8]郭建民,刘石,姜凡,等.基于SVM的对冲燃煤锅炉NOx排放特性[J].燃烧科学与技术,2006,12(3):243-247
[9]王春波,李永华,陈鸿伟.混煤燃烧特性研究(英文)[J].中国电机工程学报,2005,25(18):97-103
[10]杨冬,路春美,王永征.不同种类煤粉燃烧NOx排放特性试验研究[J].中国电机工程学报,2007,27(5):18-21
[11]金晶,张忠孝,李瑞阳.煤粉燃烧炉膛沿程NOx释放规律的研究[J].中国电机工程学报,2006,26(1):35-39
[12]郑立刚.大型电站锅炉优化运行与气固两相流光学波动法测量[D].杭州:浙江大学. 2004
[13]万文军,优化算法及火电厂若干优化问题的研究[D].南京:东南大学,2005.
[14] Pao Y.H. A computational intelligence perspective on process monitoring and optimization. Valencia: IFAC Artificial Intelligence in Real Time Control,1994,25-30.
[15]万军.基于广义知识优化方法的研究和应用[D].北京:北京科技大学,2001.
[16]周明,孙树栋.遗传算法原理及应用.北京:国防工业出版社,1999.
[17] Holland J.H. Adaptation in Nature and Artificial System(2nd ed.).MA:MIT Press,1992.
[18] Locatelli M. Convergence of a simulated annealing algorithm for continuous global optimization[J]. Journal of Global Optimization, 2000,18(3):219-234.
[19]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京:清华大学出版社, 2006: 1-90
[20] Kalogirou, Soteris A,Artificial intelligence for the modeling and control of combustion proeesses:a review[J]. Progress in Energy & Combusion Science: 2003(29):515-566
[21] D.L.Yu ,J.B.Gomm, Enhanced Neural Network Modelling for a Real Multivariable Chemical Process Neural[J]. Comput & Applic (2002)10:289-299.
[22] JieZhang, Improved on-line Proeess Fault Diagnosis Using Stacked Neura1 Networks Proeeeding of the 2002 IEEE International Conference on Control Applieations 2002(9):689-694.
[23] HaiwenYe,Rainer Nicolai,Lothar Reh,A Bayesian-Gaussian neural network and its applieations in proeess engineering. Chemieal Engineering and Proeessing. 37(1998):439-449.
[24] Mehrzad Kaiadi, Artificial Neural Networks Modeling for Monitoring and Performance Analysis of a Heat and Power Plant[D].Sweden: Lund University, 2006
[25] G.Lrwin M.Brown H.Hogg etc. Neural network modeling of a 200MW boiler system 529-536.
[26] A DOE Assessment. Big Bend Power Station Neural Network-Sootblower Optimization. U.S. Department of Energy, 2006.
[27]王斌忠,吴占松.用模糊神经网络方法预测煤灰的结渣特性[J].清华大学学报,1999,39:103-107.
[28]周昊,朱洪波,曾庭华等.基于人工神经网络的大型电站锅炉飞灰含碳量建模[J].中国电机工程学报,2001,1: 96-100.
[29]孔亮,张毅.电站锅炉燃烧优化控制技术综述[J].电力设备,2006,7(2).
[30] Southern Company Services. 500MW DEMONSTRATION OF ADVANCED WALL-FIRED COMBUTION TECHNIQUES FOR THE REDUCTION OF NITROGEN OXIDE(NOx) EMISSIONS FROM COAL-FIRED BOILERS [R]. U.S: Department of Energy, 1998
[31]王凌.智能优化算法及应用[M],北京:清华大学出版社,2001.
[32]席裕庚,柴天佑,挥为民.遗传算法综述[J].控制理论与应用, 1996,13: 697-708.
[33] Holland J.H. Adaptation in Nature and Artificial System (2nd ed.).MA: MIT Press,1992.
[34] Locatelli M. Convergence of a simulated annealing algorithm for continuous global optimization. Journal of Global Optimization, 2000, 18(3):219-234.
[35] Eberhart R.C. Shi Yuhui. Particle swarm optimization: Developments, Applications and Resources. Proceedings of the 2001 Congress on Evolutionary Computation, 2001, 1:81-86.
[36]李兵,蒋慰孙.混沌优化方法及其应用[J].控制理论与应用,1997,14:613-615.
[37] Sung-Hwan Min. Hybrid genetic algorithms and support vector machines for bankruptcy prediction. Expert Systems with Applications,2006,31:652-660.
[38]佟刚,张国忠.基于遗传算法优化的神经网络及其在机械故障诊断中的应用[J].机械与电子. 2006, 6:13-15.
[39]李小青.基于神经网络与遗传算法的传动部件设计优化[J].计算机测量与控制,2006,14(2): 253-255.
[40]邹逸桥.关于我国电煤供应形势的分析[J].中国电力报. 2008,4: 1-2
[41]罗卫红,优化配煤应用于燃煤电厂的燃烧试验研究[J].动力工程,2003.23(6): 2836-2839.
[42]唐黎华,王福明,朱学栋等,煤焦中矿物行为与灰熔融温度的关系[J].华东理工大学学报,2003.29(3): 243-247.
[43] C. Ulloa, A.G Borrego, S. Helle, A.L. Gordon, X. Garci’a,Char characterrzation and DTF assays as tools to predict burnout of coal blends in power plants [J]. Fuel, 2005, 84: 247-257.
[44] J. C. van Dyk, L.L.Baxter, J.H.P. van Heerden, R.L.J. Coetzer, Chemical fractionation tests on South African coal sources to obtain species-specfic information on ash fusion temperatures (AFT)[J]. Fuel, 2005, 84: 1768-1777.
[45] ulloa, Distribution of activation energy model applied to the rapid pyrolysis of coal blends[J]. Fuel, 2004, 71(2): 465-483.
[46] Qiu, Grey clustering prediction for slagging potential of coal blends combustion [J]. combustion science and technology,2002,174(3): 51-70.
[47]王春林.大型电站锅炉配煤及燃烧优化的支持向量机建模与实验研究[D].杭州:浙江大学. 2007
[48]陈晓梅,马晓茜,基于改进BP神经网络的锅炉结渣预测模型[J].华东电力,2005,33(7):42-45.
[49]周昊,朱洪波,岑可法.基于人工神经网络和遗传算法的火电厂锅炉适时燃烧优化系统[J].动力工程,2003,23(5):2665-2669.
[50] Yao H M, Vuthaluru* H B, Tade′M O, et al. Artificial neural network-based prediction of hydrogen content of coal in power station boilers [J]. Fuel, 2005, 84(12): 1535-1542.
[51] Liu* Y P., Wu M G., Qian J X. Predicting coal ash fusion temperature based on its chemical composition using ACO-BP neural network[J], 2007,454(1):64-68.
[52] Yin Chungen, Luo Zhongyang, Zhou Junhu, et al. A novel non-linear programming-based coal blending technology for power plants [J].Chemical engineering research and design, 2000, 78(1):118-124.
[53]廖宁放,高雅允. BP神经网络用于函数逼近的最佳隐层结构[J].北京理工大学学报, 1998(8): 476-480.
[54]焦李成.神经网络系统理论[M].西安:西安电子科技大学出版社,1996, 241-251
[55]邱广明,张慧娟,阎志勇.燃煤锅炉低NOx燃烧技术研究[J].环境保护. 2000(4):10-12
[56]曹焰,薛益鸣,赵宗让.电站燃煤锅炉控制NOx排放的技术策略[J].热力发电. 1999(6):2-5
[57]应剑,徐旭,王新龙.基于神经网络的电站锅炉燃烧优化系统研究[J].华东电力. 2007, 35(1):69-72.
[58]闰志勇,魏恩宗,张慧娟.煤粉锅炉分级燃烧降低NOx排放的试验结果分析[J].热力发电. 2001(1):34-26
[59]任建兴,翟晓敏,傅坚刚等.火电厂氮氧化物的生成和控制[J].上海电力学院学报. 2002(18):19-23
[60]温智勇,宋景慧.锅炉燃烧调整对氮氧化物排放的影响[J].广东电力,2004,17(4):25-28.
[61] A.K.Ouazzanea, J.L.Castagnerb, A.R. Jonesb, S.Ellahi Design of an optical instrument to measure the carbon content of fly ash. Fuel 81(2002):l907-l9ll
[62] Sonia Helle, Alfredo Gordon, Guillermo Alfaro, Ximena Garcia, Claudia Ulloa. Coal blend combustion: link between unburt carbonin fly ashes and maceral composition. Fuel Processing Technology 80(2003):209-223
[63] M.Ikeda, H.Makino, H.Morinaga. K.Higashiyama, Y.Kozai. Emission charactcristics of NOx and Unbumed carbon in fly ash during combustion of blends of bitominou/sub-bituminous coals. Fuel 82(2003):1851-1857
[64] F.Yangl,P.Pranda,V.HIavacek Recovery of fly ash carbon by carbochlorination via Phosgene route. Powder Technology 131(2003):206-211.
[65] McMahan L. Gray,Kenneth J. Champagne,Yee Soong,Richard P. Killmeyer,M. Mercedes Maroto-Valer, John M. Andre’sen,Miehael V. Ciocco, Paul H. Zandhuis. Physical cleaning of high carbon fly ash. Fuel ProeessingTechnology 76(2002):11-21.
[66] R.I.Backreedy, J.M.Jones, M. Pourkashanian, A.Williams; Bum-out of Pulverised coal and biomass chars. Fue l82(2003):2097-2105
[67]张文修,梁怡.遗传算法的数学基础[M].西安:西安交通大学出版社,2000:1-12
[68] He Yaohua, Hui Chiwai. A rule-based genetic algorithm for the scheduling of single-stage multi-product batch plants with parallel units [J]. Computers and Chemical Engineering, 2008, 32(12): 3067–3083.
[69] Chaibakhsh * A, Ghaffari A, Moosavian S A. A simulated model for a once-through boiler by parameter adjustment based on genetic algorithms [J].Simulation Modelling Practice and Theory.2007, 15(9):1029-1051.
[70] Gupta V, Mohanty M, Mahajan A, et al. Genetic algorithms -A novel technique to optimize coal preparation plants [J]. International Journal of Mineral Processing, 2007,84(1):133-143.
[71]苑希民,李鸿雁,刘树坤,等.神经网络和遗传算法在水科学领域的应用[M].北京:中国水利水电出版社, 2002
[2]何伯述,陈梅倩,林江等,污染物的脱除率对燃煤电站生态效率的影响,北方交通大学学报.2003(2):1-5
[3]魏辉.燃煤电站锅炉低NOx燃烧优化运行策略的研究[D].上海:上海交通大学, 2008.
[4]朱法华,王圣,郑有飞.火电NOx排放现状与预测及控制对策[J].能源环境保护.2004,18(1):1-5
[5] Andreas R, John P. B, Hendrik N,et al. Increase in tropospheric nitrogen dioxide over China observed from space[J]. Nature, 2005, 437(1): 129-132.
[6]何育东,雷兆团,柳宏刚等,一项降低电厂NOx排放量的技术,电力环境保护2002(9):16-18
[7]周昊,朱洪波,曾庭华,等.大型四角切圆燃烧锅炉NOx排放特性的神经网络模型[J].中国电机工程学报,2002,22(1):33-37
[8]郭建民,刘石,姜凡,等.基于SVM的对冲燃煤锅炉NOx排放特性[J].燃烧科学与技术,2006,12(3):243-247
[9]王春波,李永华,陈鸿伟.混煤燃烧特性研究(英文)[J].中国电机工程学报,2005,25(18):97-103
[10]杨冬,路春美,王永征.不同种类煤粉燃烧NOx排放特性试验研究[J].中国电机工程学报,2007,27(5):18-21
[11]金晶,张忠孝,李瑞阳.煤粉燃烧炉膛沿程NOx释放规律的研究[J].中国电机工程学报,2006,26(1):35-39
[12]郑立刚.大型电站锅炉优化运行与气固两相流光学波动法测量[D].杭州:浙江大学. 2004
[13]万文军,优化算法及火电厂若干优化问题的研究[D].南京:东南大学,2005.
[14] Pao Y.H. A computational intelligence perspective on process monitoring and optimization. Valencia: IFAC Artificial Intelligence in Real Time Control,1994,25-30.
[15]万军.基于广义知识优化方法的研究和应用[D].北京:北京科技大学,2001.
[16]周明,孙树栋.遗传算法原理及应用.北京:国防工业出版社,1999.
[17] Holland J.H. Adaptation in Nature and Artificial System(2nd ed.).MA:MIT Press,1992.
[18] Locatelli M. Convergence of a simulated annealing algorithm for continuous global optimization[J]. Journal of Global Optimization, 2000,18(3):219-234.
[19]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京:清华大学出版社, 2006: 1-90
[20] Kalogirou, Soteris A,Artificial intelligence for the modeling and control of combustion proeesses:a review[J]. Progress in Energy & Combusion Science: 2003(29):515-566
[21] D.L.Yu ,J.B.Gomm, Enhanced Neural Network Modelling for a Real Multivariable Chemical Process Neural[J]. Comput & Applic (2002)10:289-299.
[22] JieZhang, Improved on-line Proeess Fault Diagnosis Using Stacked Neura1 Networks Proeeeding of the 2002 IEEE International Conference on Control Applieations 2002(9):689-694.
[23] HaiwenYe,Rainer Nicolai,Lothar Reh,A Bayesian-Gaussian neural network and its applieations in proeess engineering. Chemieal Engineering and Proeessing. 37(1998):439-449.
[24] Mehrzad Kaiadi, Artificial Neural Networks Modeling for Monitoring and Performance Analysis of a Heat and Power Plant[D].Sweden: Lund University, 2006
[25] G.Lrwin M.Brown H.Hogg etc. Neural network modeling of a 200MW boiler system 529-536.
[26] A DOE Assessment. Big Bend Power Station Neural Network-Sootblower Optimization. U.S. Department of Energy, 2006.
[27]王斌忠,吴占松.用模糊神经网络方法预测煤灰的结渣特性[J].清华大学学报,1999,39:103-107.
[28]周昊,朱洪波,曾庭华等.基于人工神经网络的大型电站锅炉飞灰含碳量建模[J].中国电机工程学报,2001,1: 96-100.
[29]孔亮,张毅.电站锅炉燃烧优化控制技术综述[J].电力设备,2006,7(2).
[30] Southern Company Services. 500MW DEMONSTRATION OF ADVANCED WALL-FIRED COMBUTION TECHNIQUES FOR THE REDUCTION OF NITROGEN OXIDE(NOx) EMISSIONS FROM COAL-FIRED BOILERS [R]. U.S: Department of Energy, 1998
[31]王凌.智能优化算法及应用[M],北京:清华大学出版社,2001.
[32]席裕庚,柴天佑,挥为民.遗传算法综述[J].控制理论与应用, 1996,13: 697-708.
[33] Holland J.H. Adaptation in Nature and Artificial System (2nd ed.).MA: MIT Press,1992.
[34] Locatelli M. Convergence of a simulated annealing algorithm for continuous global optimization. Journal of Global Optimization, 2000, 18(3):219-234.
[35] Eberhart R.C. Shi Yuhui. Particle swarm optimization: Developments, Applications and Resources. Proceedings of the 2001 Congress on Evolutionary Computation, 2001, 1:81-86.
[36]李兵,蒋慰孙.混沌优化方法及其应用[J].控制理论与应用,1997,14:613-615.
[37] Sung-Hwan Min. Hybrid genetic algorithms and support vector machines for bankruptcy prediction. Expert Systems with Applications,2006,31:652-660.
[38]佟刚,张国忠.基于遗传算法优化的神经网络及其在机械故障诊断中的应用[J].机械与电子. 2006, 6:13-15.
[39]李小青.基于神经网络与遗传算法的传动部件设计优化[J].计算机测量与控制,2006,14(2): 253-255.
[40]邹逸桥.关于我国电煤供应形势的分析[J].中国电力报. 2008,4: 1-2
[41]罗卫红,优化配煤应用于燃煤电厂的燃烧试验研究[J].动力工程,2003.23(6): 2836-2839.
[42]唐黎华,王福明,朱学栋等,煤焦中矿物行为与灰熔融温度的关系[J].华东理工大学学报,2003.29(3): 243-247.
[43] C. Ulloa, A.G Borrego, S. Helle, A.L. Gordon, X. Garci’a,Char characterrzation and DTF assays as tools to predict burnout of coal blends in power plants [J]. Fuel, 2005, 84: 247-257.
[44] J. C. van Dyk, L.L.Baxter, J.H.P. van Heerden, R.L.J. Coetzer, Chemical fractionation tests on South African coal sources to obtain species-specfic information on ash fusion temperatures (AFT)[J]. Fuel, 2005, 84: 1768-1777.
[45] ulloa, Distribution of activation energy model applied to the rapid pyrolysis of coal blends[J]. Fuel, 2004, 71(2): 465-483.
[46] Qiu, Grey clustering prediction for slagging potential of coal blends combustion [J]. combustion science and technology,2002,174(3): 51-70.
[47]王春林.大型电站锅炉配煤及燃烧优化的支持向量机建模与实验研究[D].杭州:浙江大学. 2007
[48]陈晓梅,马晓茜,基于改进BP神经网络的锅炉结渣预测模型[J].华东电力,2005,33(7):42-45.
[49]周昊,朱洪波,岑可法.基于人工神经网络和遗传算法的火电厂锅炉适时燃烧优化系统[J].动力工程,2003,23(5):2665-2669.
[50] Yao H M, Vuthaluru* H B, Tade′M O, et al. Artificial neural network-based prediction of hydrogen content of coal in power station boilers [J]. Fuel, 2005, 84(12): 1535-1542.
[51] Liu* Y P., Wu M G., Qian J X. Predicting coal ash fusion temperature based on its chemical composition using ACO-BP neural network[J], 2007,454(1):64-68.
[52] Yin Chungen, Luo Zhongyang, Zhou Junhu, et al. A novel non-linear programming-based coal blending technology for power plants [J].Chemical engineering research and design, 2000, 78(1):118-124.
[53]廖宁放,高雅允. BP神经网络用于函数逼近的最佳隐层结构[J].北京理工大学学报, 1998(8): 476-480.
[54]焦李成.神经网络系统理论[M].西安:西安电子科技大学出版社,1996, 241-251
[55]邱广明,张慧娟,阎志勇.燃煤锅炉低NOx燃烧技术研究[J].环境保护. 2000(4):10-12
[56]曹焰,薛益鸣,赵宗让.电站燃煤锅炉控制NOx排放的技术策略[J].热力发电. 1999(6):2-5
[57]应剑,徐旭,王新龙.基于神经网络的电站锅炉燃烧优化系统研究[J].华东电力. 2007, 35(1):69-72.
[58]闰志勇,魏恩宗,张慧娟.煤粉锅炉分级燃烧降低NOx排放的试验结果分析[J].热力发电. 2001(1):34-26
[59]任建兴,翟晓敏,傅坚刚等.火电厂氮氧化物的生成和控制[J].上海电力学院学报. 2002(18):19-23
[60]温智勇,宋景慧.锅炉燃烧调整对氮氧化物排放的影响[J].广东电力,2004,17(4):25-28.
[61] A.K.Ouazzanea, J.L.Castagnerb, A.R. Jonesb, S.Ellahi Design of an optical instrument to measure the carbon content of fly ash. Fuel 81(2002):l907-l9ll
[62] Sonia Helle, Alfredo Gordon, Guillermo Alfaro, Ximena Garcia, Claudia Ulloa. Coal blend combustion: link between unburt carbonin fly ashes and maceral composition. Fuel Processing Technology 80(2003):209-223
[63] M.Ikeda, H.Makino, H.Morinaga. K.Higashiyama, Y.Kozai. Emission charactcristics of NOx and Unbumed carbon in fly ash during combustion of blends of bitominou/sub-bituminous coals. Fuel 82(2003):1851-1857
[64] F.Yangl,P.Pranda,V.HIavacek Recovery of fly ash carbon by carbochlorination via Phosgene route. Powder Technology 131(2003):206-211.
[65] McMahan L. Gray,Kenneth J. Champagne,Yee Soong,Richard P. Killmeyer,M. Mercedes Maroto-Valer, John M. Andre’sen,Miehael V. Ciocco, Paul H. Zandhuis. Physical cleaning of high carbon fly ash. Fuel ProeessingTechnology 76(2002):11-21.
[66] R.I.Backreedy, J.M.Jones, M. Pourkashanian, A.Williams; Bum-out of Pulverised coal and biomass chars. Fue l82(2003):2097-2105
[67]张文修,梁怡.遗传算法的数学基础[M].西安:西安交通大学出版社,2000:1-12
[68] He Yaohua, Hui Chiwai. A rule-based genetic algorithm for the scheduling of single-stage multi-product batch plants with parallel units [J]. Computers and Chemical Engineering, 2008, 32(12): 3067–3083.
[69] Chaibakhsh * A, Ghaffari A, Moosavian S A. A simulated model for a once-through boiler by parameter adjustment based on genetic algorithms [J].Simulation Modelling Practice and Theory.2007, 15(9):1029-1051.
[70] Gupta V, Mohanty M, Mahajan A, et al. Genetic algorithms -A novel technique to optimize coal preparation plants [J]. International Journal of Mineral Processing, 2007,84(1):133-143.
[71]苑希民,李鸿雁,刘树坤,等.神经网络和遗传算法在水科学领域的应用[M].北京:中国水利水电出版社, 2002