基于在线优化技术的分层燃烧试验研究及应用
|
摘要
火电机组装机容量的快速增长造成燃煤资源的相对短缺,而煤燃烧生成的NOx和SO2等气态污染物造成了巨大的环保压力。国家因此也出台了一系列宏观调控政策：上调排污费和实行排污权交易来抑制企业盲目扩大生产；实行脱硫电价引导企业清洁生产；实行节能环保调度促使企业开发和引进先进的节能环保生产技术。本文在此背景下开展燃烧优化研究,从锅炉烟气排放连续监测、锅炉在线燃烧优化和煤粉分层燃烧三方面进行递进式研究。
烟气排放连续监测技术是实时掌握锅炉燃烧状况的重要工具,也是获得污染物排放浓度的手段。本文针对烟气高温、高粉尘浓度和腐蚀性强的特点以及烟气成份分布的不均匀,在烟气采样和预处理设备的开发上采用了先进技术,采用光谱分析原理监测烟气中CO、NOx、O2以及SO2等气体浓度,通过比对试验证实该连续监测技术准确度可靠性高,为在线燃烧优化技术研究作了必要的准备。
基于支持向量机建立锅炉效率、NOx排放浓度优化模型,利用遗传算法对模型参数寻优,为在线燃烧优化提供数学工具。本文依据当前锅炉结构及燃烧特性,在优化中考虑了锅炉高温腐蚀的影响,开发了在线高温腐蚀模型,可实时预测和监测高温腐蚀速率,定量监测炉膛受热面的安全状况。由上述三个模型组成的燃烧优化模型与烟气排放连续监测技术结合开发的在线燃烧优化系统具有高的预测精度和良好的工程应用效果,并克服了常规优化工具的不足,可实现煤质和负荷变化的实时跟踪。
分层燃烧技术实质是一种简便灵活的配煤技术,深受电厂欢迎,由于缺乏理论支持和监测手段,一般都停留在经验阶段。本文利用ANSYS三维燃烧计算软件对电厂锅炉的典型燃烧工况进行计算分析,定量获得锅炉在不同煤质分层方式下的燃烧特性。在燃烧计算指导下,应用锅炉在线燃烧优化系统进行分层燃烧技术试验研究,通过锅炉燃烧特性、结渣特性、积灰特性、NOx排放特性、锅炉效率影响特性等各方面对锅炉不同分层方式进行评估,获得最优分层燃烧方式,拓宽锅炉燃煤适应性,降低燃料成本,有效地提高锅炉效率和降低NOx排放浓度。
The capacity of thermal power units increase rapidly in our country in recent years, which cause the shortage of coal. And the gaseous pollutant made by coal combustion such as NOx and SO2create the serious environment problem. A serial macro-regulatory policies are issued by the government such as:increasing pollutant discharge fees to control the blindfold production expansion; applying the desulfurization electric power price to lead the clean production; carrying out energy-saving and environmental protection management to urge the research of advanced energy-saving and environmental protection technology. In this background the combustion optimization research is carried out in this article, including continuous gas emission monitoring, on-line combustion optimization and coal fine layered combustion.
The continuous gas emission monitoring is the important method to realize boiler combustion real-time parameters and pollutant discharging concentration. Because of the characteristic of gas such as high temperature, high fine concentration, strong causticity and distributing unevenness, some advanced technologies are applied on gas sample collection and pretreatment equipment. The gas concentration such as CO, NOτ, O2and SO2are monitored by using spectrum analysis principle. The contrast testing results show that the continuous monitoring technology have high accuracy and reliability and can applied for on-line combustion optimization.
In this article boiler efficiency and NOx discharging concentration models are built based on Support Vector Machine to offer the mathematical tool for on-line combustion optimization. According to boiler structure the combustion characteristic, an on-line high-temperature erosion model is built to predict the velocity of erosion and monitor the security of furnace heating surface quantificationally. The combustion optimization model composed by the above three models is combined with gas continuous monitoring technology to form the on-line combustion optimization, which have high precision accuracy and good engineering application and can vary well with the coal quality and unit load.
The layered combustion technology is a simple and flexible coal arrangement technology which is always carried out by. practice because theoretic support and monitoring method are absent. In this article the computer fluid dynamics software Ansys is used to analyse the typical combustion condition of boiler to obtain the combustion characteristic in different layered mode quantificationally. With the instruction of computed results, layered combustion experimental research is carried out applied with on-line combustion optimization system. The optimized combustion style is obtained through evaluating the influence of combustion, clinker, soot, NOx emission and boiler efficiency in different layered style, which can widen the coal adptability, reduce the fuel cost, increase boiler efficiency and decrease NOx emission concentration.
烟气排放连续监测技术是实时掌握锅炉燃烧状况的重要工具,也是获得污染物排放浓度的手段。本文针对烟气高温、高粉尘浓度和腐蚀性强的特点以及烟气成份分布的不均匀,在烟气采样和预处理设备的开发上采用了先进技术,采用光谱分析原理监测烟气中CO、NOx、O2以及SO2等气体浓度,通过比对试验证实该连续监测技术准确度可靠性高,为在线燃烧优化技术研究作了必要的准备。
基于支持向量机建立锅炉效率、NOx排放浓度优化模型,利用遗传算法对模型参数寻优,为在线燃烧优化提供数学工具。本文依据当前锅炉结构及燃烧特性,在优化中考虑了锅炉高温腐蚀的影响,开发了在线高温腐蚀模型,可实时预测和监测高温腐蚀速率,定量监测炉膛受热面的安全状况。由上述三个模型组成的燃烧优化模型与烟气排放连续监测技术结合开发的在线燃烧优化系统具有高的预测精度和良好的工程应用效果,并克服了常规优化工具的不足,可实现煤质和负荷变化的实时跟踪。
分层燃烧技术实质是一种简便灵活的配煤技术,深受电厂欢迎,由于缺乏理论支持和监测手段,一般都停留在经验阶段。本文利用ANSYS三维燃烧计算软件对电厂锅炉的典型燃烧工况进行计算分析,定量获得锅炉在不同煤质分层方式下的燃烧特性。在燃烧计算指导下,应用锅炉在线燃烧优化系统进行分层燃烧技术试验研究,通过锅炉燃烧特性、结渣特性、积灰特性、NOx排放特性、锅炉效率影响特性等各方面对锅炉不同分层方式进行评估,获得最优分层燃烧方式,拓宽锅炉燃煤适应性,降低燃料成本,有效地提高锅炉效率和降低NOx排放浓度。
The capacity of thermal power units increase rapidly in our country in recent years, which cause the shortage of coal. And the gaseous pollutant made by coal combustion such as NOx and SO2create the serious environment problem. A serial macro-regulatory policies are issued by the government such as:increasing pollutant discharge fees to control the blindfold production expansion; applying the desulfurization electric power price to lead the clean production; carrying out energy-saving and environmental protection management to urge the research of advanced energy-saving and environmental protection technology. In this background the combustion optimization research is carried out in this article, including continuous gas emission monitoring, on-line combustion optimization and coal fine layered combustion.
The continuous gas emission monitoring is the important method to realize boiler combustion real-time parameters and pollutant discharging concentration. Because of the characteristic of gas such as high temperature, high fine concentration, strong causticity and distributing unevenness, some advanced technologies are applied on gas sample collection and pretreatment equipment. The gas concentration such as CO, NOτ, O2and SO2are monitored by using spectrum analysis principle. The contrast testing results show that the continuous monitoring technology have high accuracy and reliability and can applied for on-line combustion optimization.
In this article boiler efficiency and NOx discharging concentration models are built based on Support Vector Machine to offer the mathematical tool for on-line combustion optimization. According to boiler structure the combustion characteristic, an on-line high-temperature erosion model is built to predict the velocity of erosion and monitor the security of furnace heating surface quantificationally. The combustion optimization model composed by the above three models is combined with gas continuous monitoring technology to form the on-line combustion optimization, which have high precision accuracy and good engineering application and can vary well with the coal quality and unit load.
The layered combustion technology is a simple and flexible coal arrangement technology which is always carried out by. practice because theoretic support and monitoring method are absent. In this article the computer fluid dynamics software Ansys is used to analyse the typical combustion condition of boiler to obtain the combustion characteristic in different layered mode quantificationally. With the instruction of computed results, layered combustion experimental research is carried out applied with on-line combustion optimization system. The optimized combustion style is obtained through evaluating the influence of combustion, clinker, soot, NOx emission and boiler efficiency in different layered style, which can widen the coal adptability, reduce the fuel cost, increase boiler efficiency and decrease NOx emission concentration.
引文
[1]马凯,驳“中国能源威胁论”http://www.ccra.org.cn/article/2/2006-11-02/155.htm.2006.
[2]史立山,《可再生能源法》的实施与行业发展的前景.国家信息中心06年行业发展报告会的嘉宾讲话系列十三,2006http://macdblog.blog.hexun.com/1 625634 d.html
[3]. http://www.cclv.cn/Print.asp?ArticleID=5603.2006
[4]唐炼,世界能源供需现现状与发展趋势[J].国际石油经济2005.13(1)：p.30-33.
[5]央视国际,我国发电行业节约煤炭潜力巨大http://www.cctv.com/program/jjxxlb/20060920/101399.shtml.2006.
[6]中国国家标准,火电厂大气污染物排放标准 GB13223-1996,2006.
[7]国家环保总局,火电厂烟气排放连续监测技术规范HJ/T 75-2001.,2001
[8]国家环保总局,固定污染源排放烟气连续监测系统技术要求及检测方法HJ/T 76-2001,2001.
[9]叭国家环保总局,火电厂烟气脱硫工程技术规范 石灰石/石灰-石膏法-HJ/T 179-2005,2005.
[10]霭家环保总局,污染源在线自动监控(监测)系统数据传输标准HJ/T212-2005,2005
[11]A. Toffolo,A. Lazzaretto, Evolutionary algorithms for multi-objective energetic and economic optimization in thermal system design[J]. Energy,2002.27:p.549-567..
[12]孔亮,张毅,丁艳军,吴占松,电站锅炉燃烧优化控制技术综述[J].电力设备,2006.7(2)：p.19-23.
[13]毛健雄,毛健全,赵树民编著,煤的清洁燃烧,科学出版社,1998；
[14]曾汉才,燃烧与污染,华中理工大学出版社,1992；
[15]曾汉才,姚斌,石烟煤与烟煤的混合燃烧特性与结渣特性研究[J].燃烧科学与技术,1996.2(2)：p.181-189.
[16]梁绍华,FT91型烟气排放连续监测装置，江苏省电力科学研究院企业标准,2005.唐黎华,王福明,朱学栋等.,燃焦中矿物质行为与灰熔融温度的关系[J].华东理工大学学报,2003.29(3)：p.243-247.
[17]梁绍华,胡为柏,鲁松林,烟气排放连续监测系统特性研究[J].江苏电机工程,2004.23(6)：p.2836-2839.
[18]王培红,李磊,人工智能在电站锅炉燃烧优化中的应用研究[J].中国电机工程学报,2004.24(4)：p184-187
[19]钟北京,傅维标,燃烧过程快速型氧化氮形成机理及其影响因素[J].燃烧科学与技术,1997.4.p388-393
[20]曾小敏,沙角A电厂5号锅炉低NOx排放分析[J].热力发电,2005.1：p.27-28.
[21]荆有印,齐永霞等,水平浓淡煤粉燃烧器内气固两相流的数值模拟[J] 中国动力工程学报,2005.25(19)：p.65-67.
[22]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-specific information on ash fusion temperatures (AFT) [J]. Fuel,2005.84:p.1768-1777.
[23]Nello Cristianini, John Shawe-Taylor著,李.王.增.译.,支持向量机导[M].北京：电子工业出版社,2004.
[24]Vapnik著.张学工译.,统计学习理论[M].北京：电子工业出版社,2004.
[25]王定成,唐毅等.,支持向量机回归理论与控制的综述[J].模式识别与人工智能,2003.2(16)： p.192-197.
[26]Peralta, Coal blend performance during pulverized-fuel combustion:estimation of relative reactivities by a bombcalorimeter test[J]. Fuel,2001.80(11):p.1623-1634.
[27]许昌,吕剑虹,基于生成机理的燃煤电站锅炉NOx排放量神经网络模型[J].中国电机工程学报,2004.24(10)：p.233-237.
[28]王新军,王飞等,用于电站煤粉锅炉NOx排放监测的BP神经网络试验研究[J].动力工程,2002,22(5)：p.1979-1982.
[29]Lolja S A, Haxhi H, Martin D. J., Correlations in the properties of Albanian coals[J]. Fuel,2002. 45(1):p.1095-1100.
[30]李永华,陈鸿伟等,煤粉燃烧排放特性数值模拟[J].中国电机工程学报,2003.23(3)：p.166-169.
[31]刘忠,阎维平等,煤种对超细煤粉再燃还原NO效率的影响[J].中国电机工程学报,2004.24(12)：p.273-276.
[32]Seggiani, M., Empirical correlations of the ash fusion temperatures and temperature of critical viscosity for coal and biomass ashes [J]. Fuel,1999.78(9):p.1121-1125.
[33]高岩,龚志豪.,锅炉燃烧系统的仿人智能控制[J].北京理工大学学报,2002.22(3)：p.315-317.
[34]艾红,锅炉效率动态模糊自寻优控制[J].c控制理论与应用,2002.21(4)：p.5-8.
[35]李凌,余岳峰,基于神经倒络的锅炉低NOx排放系统辨识[J].锅炉技术,2003.34(1)：p.68-71.
[36]安恩科,苏夏等,低NOx煤粉燃烧器的试验研究[J].锅炉技术,2005.36(1)：p.43-48.
[37]安恩科,周鸿权,电站锅炉燃烧特性的数值模拟[J].J同济大学学报(自然科学版),2004.32(8)：p.1042-1045.
[38]刘鸿,唐必光,锅炉高效低污染燃烧特性测试试验研究[J].四川电力技术,2002.3：p.7-9.
[39]金晶,李瑞阳等,超细煤粉还原NOx的试验研究[J].热能动力工程,2004.19(6)：p.582-586.
[40]王康丽,严河清,氮氧化物化学传感器[J].武汉大学学报(理学版),2003.49(4)：p.428-432.
[41]朱彤,李晓萍,炉膛结构对炉风NOx生成的影响[J].工业炉,2004.26(6)：p.1-4
[42]Fernando Rubiera, A. Arenillas, Borja Arias, Jose'J. Pis, Modification of combustion behaviour and NO emissions by coal blending[J]. fuel processing technology,2002.77-78:p.111-117.
[43]李永华,张志业,混煤对降低SO2排放的试验研究[J].华东电力,2003.1：p.1-2.
[44]Barnes, The Slagging Of Blends Of Power Station Coals [J]. Proceeding,effects of coal quality on power plants,1993:p.45-62.
[45]Douglas, Effects Of Increasing Coal Hardness And Volatility On Pilot-Scale Pulverization And Combustion Performance[J]. Seventh annual international Pittsburgh,1990:p.837-851.
[46]刘汉涛,工永征等,混煤燃烧氮析出特性试验研究[J].电站系统工程,2004：20(6)p.9-11.
[47]孙继德,张国军,煤粉燃烧降低NOx技术的试验研究[J].电站系统工程,1998：14(1)p.39-46.
[48]曾汉才,朱全利等,大型锅炉高效低NOx燃烧技术的研究[J].电站系统工程,1997.13(6)：p.40-44.
[49]Ozbyoglu G, Evren O M, A new approach for the prediction of ash fusion temperatures:A case study using Turkish lignitesfJJ. Fuel,2006.85(4):p.545-552.
[50]Stanislav V. Vassile, Kunihiro Kitano, Influence of mineral and chemical composition of coal ashes on their fusibility [J]. Fuel Processing Technology,1995.45(1):p.27-51.
[51]Lolja S A etal., Correlations in the properties of Albanian coals[J]. Fuel,2002.81(9):p. 1095-1100.
[52]Lolja Saimir A, Hajri H, et al., Correlation between ash fusion temperatures and chemical composition in Albanian coal ashes[J]. Fuel,2002.81(17):p.2257-2261.
[53]王春林,周吴,李国能,凌忠钱,基于遗传算法和支持向量机的低NOx燃烧优化[J].中国电机工程学报,2007.21(4)：p.79-84.
[54]Saimir A. Lolja, H.H., Rolanda Dhimitri, Spiro Drushku, Agim Malja, Correlation between ash fusion temperatures and chemical composition in Albanian coal ashes[J]. Fuel,2002.81(9):p. 2257-2261.
[55]石喜光,郑立刚,周.昊等,基于广义回归神经网络与遗传算法的煤灰熔点优化[J].浙江大学学报(工学版),2005.39(8)：p.1189-1192.
[56]S.K. Gupta, T.F. Wall, R.A. Creelman, R.P. Gupta, Ash fusion temperatures and the transformations of coal ash particles to slag[J]. Fuel Processing Technology,1998.56:p. 33-43.
[57]Chungen Yin, Z.L., Mingjiang Ni and Kefa Cen, Predicting coal ash fusion temperature with a backpropagation neural network model[J]. Fuel,1998.77(15):p.1777-1782.
[58]石喜光,郑立刚等,基于广义回归神经网络与贵传算法的煤灰熔点优化[J].浙江大学学报(工学版),2005.39(8)：p.1189-1192.
[59]廖艳芬,马茜,基于模糊神经网络的混沌优化算法在动力配煤中的应用[J].华南理工大学学报(自然科学版),2006.34(6)：p.117-123.
[60]Kalogirou S A, Artificial intelligence for the modeling and control of combustion processes; A review [J]. Progress in energy and combustion seience,2003.29(6):p.515-566.
[61]王春林,周昊,周樟华,基于支持向量机的大型电厂锅炉飞灰含碳量建模[J].中国电机工程学报,2005.25(20)：p.72-77
[62]Kang S G, Role Of Calcium In Coal And Sulfur Dioxide Emissions During Pulverized Coal[J] Combustion. Engineering Foundation conference on coal blending and switching of low sulfur western coals,1994:p.341-354.
[63]徐通模,燃媒自身CaO含量的脱硫效率研究[J].动力工程,1994.4.
[64]A.Arenillas, R.I.Backreedy, J.M. Jones, J.J. Pis, M. Pourkashanjan, F. Rubiera, modelling of NO formation in the combusion of coal blends [J]. Fuel,2002.81:p.627-636.
[65]Backreedy, Prediction of unburned carbon and NOx in a tangentially fired power station using single coals and blends[J]. Fuel,2005.84(17):p.2196-2203.
[66]翁安心,周吴,张力,岑可法,不同煤种混煤燃烧时NOx生成和燃尽特性的试验[J].热能动力工程,2004.19(3)：p.242-245.
[67]周昊,钱欣平,郑立刚,翁安心,岑可法,神经网络与模拟退火算法结合的锅炉低NOx燃烧优化[J].环境科学,2003.24(6)：p.63-68.
[68]C.E. Lee, C.B.Oh, J.H. Kim, Numerical and experimental investigations of the NOx emission characteristics of CH4-air coflow jet flames [J]. fuel,2004.83:p.2323-2334.
[69]李颖,周俊虎,BP经神网络在电厂优化配煤中预测性能的研究[J].电站系统工程,2002.18(3)：p.1-5.
[70]Booth, R.C. Roland W. B., Neural network-based combustion optimization reduces NO, emissions while improving performance[J]. Proc. Am. Power Conf.,,1998.60(2):p.667-672.
[71]王庆,NeuSIGHT神经网络闭环燃烧优化控制系统在沙角B电厂应用前景分析[J].河南电力,2005(3)：p.34-37.
[72]饶苏波,多目标进化算法在电站锅炉燃烧优化控制系统设计中的应用[J].广东电力,2006.19(4)：p.11-15.
[73]秦鹏,林中达,基于改进型El man神经网络和遗传算法的锅炉在线燃烧优化[J].锅炉技术,2005.36(5)：p.37-41.
[74]王培红,李磊磊,陈强,董益华,人工智能技术在电站锅炉燃烧优化中的应用研究[J].中国电机工程学报,2004.24(4)：p.184-188.
[75]王军,章正林,姜书敏,SmartProcess燃烧优化系统及其应用[J].电力设备,2006.7(2)：p.28-30.
[76]董均华,徐向东,基于煤种辨识的锅炉燃烧优化系统[J].热能动力工程,2006.21(2)：p.121-138.
[77]Vladimir Havlena, Jirj Findejsa, Application of model predictive control to advanced combustion control[J]. Control Engineering Practice,2005.13:p.671-680.
[78]许昌,吕剑虹,郑源,以效率和低NOx排放为目标的锅炉燃烧整体优化[J].中国电机工程学报,2006.26(4)：p.46-50.
[79]李智,蔡九菊,郭宏等,基于神经原网络的电厂锅炉燃烧谎化黍统[J].中国电力,2004.37(6)：p.75-77.
[80]周昊,朱洪波,曾庭华,基于人工神经网络大型电厂飞灰含碳量建模[J].中国电机工程学报,2002.6：p.96-100.
[81]zhou hao, Cen ke.-fa., Mao jian-bo, combinning Neual network and Genetic algorithms to optimize low NOx pulverized coal combustion[J]. fuel,2001.80(15):p.2163-2169.
[82]zhou hao, Cen ke-fa, Fan jian-ren, Modeling and optimization of the NOx emission characteristics of atangentially fired boiler with artificial neualnetwork[J]. energy,2004. 29(1):p.167-183.
[83]zhou hao, qin xin-ping, cen ke-fa, fan jian-ren, Optimizing puoverized coal combustion performance base on ANN and GA[J]. fuel Processing technology,2004.85(2):p.113-124.
[84]侯向阳,燃煤锅炉燃烧优化的调整试验研究[J].电力建设,2006.27(6)：p.35-39.
[85]Khesin M.et al., Combustion optimization using MPV combustion diagnostic and optimization systems-application experience[J]. Proc.-Annu. Int. Pittsburgh Coal Con(?),2000.17:p. 224-243.
[86]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,2006.33(1)：p.72-77.
[87]周国民,李宝仪,龚家猷,燃煤锯炉NO排放特性及其燃烧优化[J].锅炉技术,2006.37(3)：p.77-81.
[88]程伟良,夏国栋等,锅炉分级燃烧优化技术的研究[J].动力工程,2004.24(3)：p.337-341.
[89]赵宁,曹洪涛,李晓金,张春发,基于O2和CO信号修正的燃烧优化控制[J].电力科学与工程,2004.3(23-26).
[90]沈跃云,高小涛,锅炉低NOx燃烧优化技术试验分析[J].洁净煤燃烧与发电技术,2005：p.35-39.
[91]成庆刚,李争起,滕玉强,庄前玉,贾自臣,张寅,庄国中,果志明,低NO排放燃烧技术及燃烧优化的试验研究[J].锅炉技术,2005.36(5)：p.33-39.
[92]沈跃良,廖宏楷,周.昊等,风煤在线测量的锅炉燃烧优化系统[J].动力工程,2005.25(4)：p.561-565.
[93]Carsky M, K.D.K., Neural network modelling of coal pyroly-sis[J]. Fuel 2001.80(7):p. 1021-1027.
[94]Zhu Q, Jones J.M., Williams A, et al., The predictions of coal/char combustion rate using an artificial neural network approach[J]. Fuel 1999.78(14):p.1755-1762.
[95]Robert R. Jensen, Shankar Karki., Hossein Salehfar, Artificial neural network-based estimation of mercury speciation in combustion flue gases[J]. Fuel processing technology 2004. 85(451-462.).
[96]王培红,李磊磊,陈强,董益华,电站锅炉高效低污染燃烧优化算法研究[J].动力工程，2004.24(4)：p.466-470.
[97]Rong he, Toshiyuki Suda, et al, Analysis of low NO emission in high temperature air combustion for pulverized coal[J]. Fuel,2004.86:p.1133-1141.
[98]Robert Pieter van de Lans, Per Glarborg, et al, Influence of coal quality on combustion performance[J]. Fuel 1998.12(77):p.1317-1328.
[99]Fernado Rubiera, Ana Arenillas, et al, Modification of combustion behaviour and NO emissions by coal blendingfJJ. Fuel Processing Technology,2002.77-78:p.111-117.
[100]Havlena, V., Combustion optimization in a coal-fired boiler by controlling the air/fuel ratio[J]. PCT Int. Appl.,2002.27:p.883,167.
[101]Karel Svoboda, Michael Pohorely, Influence of operating conditions and coal properties on NOx and N2O emissions in pressurized fluidized bed combustion of subbituminous CoalsfJJ. Fuel,2004.83:p.1095-1103.
[102]R.P. Van der lans, P. Glarborg, K. Dam-Johansen, Influence of process parameters on nitrogen oxide formation in pulverized coal burners[J]. Prog. Energy Combust. Sci.,1997.23:p. 349-377.
[103]L. Armesto, H. Boerrigter, et al, N2O emissions from fluidized bed combustion. The effect of fuel characteristics and operating conditions[J]. Fuel,2003.82:p.1845-1850.
[104]Ryoichi Kurose, Michitaka Ikeda, et al, Pulverized coal combustion characteristics of high-fuel-ratio coalsfJJ. Fuel,2004.83:p.1777-1785.
[105]Christof Schylz, Volker Sick, Tracer-LIF diagnostics:quantitative measurement of fuel concentration, temperature and fuel/air ratio in practical combustion systems [J]. Progress in energy and combustion science,2005.31:p.75-121.
[106]Kiga T, Hanaoka R, Nakamura M, et al, Combustion characteristics of pulverized coal using high temperature air[J]. Reprinted AIAA,1999:p.99-0730.
[107]周怀春,肖旭东,韩元才.,煤粉燃烧诊断专家系统的研究[J].热力发电,1993.6：p.43-47.
[108]Robert R. Jensen, Shankaa Karki, Hossein Salehfar., Artificial neural network-based estimation of mercury speciation in combustion flue gases[J]. Fuel processing technology 2004.85:p. 451-462.
[109]Chu Li-zheng, Shieh Shyan-Shu, Lang Shi-Shang, et al, Constrained optimization of combustion in a simulated coal-fired boiler using artificial neural network model and information analysis[J]. Fuel,2003.82(6):p.693-703.
[110]孙巧玲,沈炯,李益国,基于遗传算法的燃煤电站锅炉整体燃烧优化方法研究[J].热能动力工程,2004.19(1)：p.85-89.
[111]Klaus Kruger, Rudiger Franke, Manfred Rode, Optimization of boiler start-up using a nonlinear boiler model and hard constraints [J]. Energy,2004.29:p.2239-2251.
[112]Mei Gong, Optimization of industrial energy systems by incorporating feedback loops into the MIND method[J]. Energy 2003.28:p.1655-1669.
[113]B.R. Stanmore, S.P.Visona, Prediction of NO emissions from a number of coal-fired power station boilers [J]. Fuel Processing Technology,2000.64:p.25-46.
[114]K J Hughes, A S Tomlin, et al, An Investigation of Important Gas-Phase Reactions of Nitrogenous Species from the Simulation of Experimental Measurements in combustion system[J]. Combustion and Flame,2001.124:p.573-589
[115]Jason Makansi, plants gain xonnfidence in optimization sofeware[J]. power,1998.9(10):p. 59-64.
[116]Peter Patterson, Micheal S. Krueger, Optimization saves money, reduces NOxfJJ. Power engineering,1997.9:p.21-23.
[117]Levy, E.et.al., Combustion optimization using an expert system and neural networks [J]. Proceedings of the International Joint Power Generation Conference, Volume 1: Environmental Control/Fuels and Combustion Technologies,1996.1:p.411-419.
[118]李雪亮,杨延龄,电站锅炉燃烧分析专家系统[J].中国电力,1997.30(3)：p.29-32.
[119]陈鸿伟,杨中其,周志萍,吉云,基于风粉在线监测锅炉燃烧优化控制[J].锅炉技术,2005.36(6)：p.36-40.
[120].李智,蔡九菊,郭宏等,基于神经元网络的电厂锅炉燃烧优化系统[J].中国电力,2004.37(6)：p.75-78.
[121]陈敏生,刘定平,电站锅炉飞灰含碳量的优化[J].动力工程,2005.25(4)：p.545-550.
[122]李智,蔡九菊,郭宏,丁艳军,程芳真,基于神经元网络的电厂锅炉燃烧优化系统[J].中国电力,2004.37(6)：p.75-78.
[123]张海,吕俊复等,我国燃电站锅炉NOx排放的现状分析和应对措施[J].中国电机工程学报,2005：25(1)：p.125-130.
[124]Go, Coal blend combustion fusibility ranking from mineral matter composition [J]. Fuel,2003. 82(15-17):p.2087-2095.
[125]Sonia Helle, A.G., Guillermo AIfaro,Ximena Garcia, Claudia Ulloa, Coal blend combustion: link between unburnt carbon in fly ashes and maceral composition[J]. Fuel,2003.80:p. 209-223.
[126]萧嵘,王继承,张福炎.,支持向量机理论综述[J].计算机科学,2000.3(27)：p.1-3.
[127]王景雷,吴景社,孙景生等.,支持向量机在地下水位预报中的应用研究[J].水力学报,2003.5：p.122-129.
[128]John H. Pavlish, April A.Aenderson, using the CQIM to Evaluate switching to western low-sulfur coals [J]. Engineering Foundation conference on coal blending and switching of tow-sulfur western coals,1994:p.421-440.
[129]成庆刚,李争起,滕玉强,庄前玉等,低NO排放燃烧技术及燃烧优化的试验研究[J].锅炉技术,2005.36(5)：p.32-38.
[130]王庆,NeuSIGHT神经网络闭环燃烧优化控制系统在沙角B电厂应用前景分析[J] 河南电力,2005.3：p.34-39.
[131]王.军,章正林,姜书敏,SmartProcess燃烧优化系统及其应用[J].电力设备,2006.7(2)：p.28-31.
[132]Keerthi K, Lin C J, Asymptotic behaviors of support vector machines with Gaussian kernel[J]. Neural Computation,2003.15(3):p.1667-1689.
[133]Lin H T, Lin CJ, A study on sigmoid kernels for SVM and the training of non-PSD Kernels by SMO-type methods[EB]. http://www.csie.ntu.edu.tw/-cjlin/papers.Html,2003,March.
[134]周昊,朱洪波,曾庭华等,基于有工神经网络大型电厂飞灰含碳量建模[J].中国电机工程学报,2002.6：p.96-100.
[135]徐正中.,燃煤硫排放系数的研究及脱硫要求的确定[J].热力发电,1994.3：p.5-15..
[136]Yanpeng Liu, Mingguang Wu, Jixin Qian, Predicting coal ash fusion temperature based on its chemical composition using ACO-BP neural network[J]. Thermochimica Acta,2006.10(26): p.1016.
[137]Christopher J. Montgomery, et al, REDUCED CHEMICAL KINETIC MECHANISMS FOR HYDROCARBON FUELS[J].
[138]Jennifer P. Spinti, David W.Pershing, The fate of char-N at pulverized coal conditions [J]. Combustion and flame,2003.135:p.299-313.
[2]史立山,《可再生能源法》的实施与行业发展的前景.国家信息中心06年行业发展报告会的嘉宾讲话系列十三,2006http://macdblog.blog.hexun.com/1 625634 d.html
[3]. http://www.cclv.cn/Print.asp?ArticleID=5603.2006
[4]唐炼,世界能源供需现现状与发展趋势[J].国际石油经济2005.13(1)：p.30-33.
[5]央视国际,我国发电行业节约煤炭潜力巨大http://www.cctv.com/program/jjxxlb/20060920/101399.shtml.2006.
[6]中国国家标准,火电厂大气污染物排放标准 GB13223-1996,2006.
[7]国家环保总局,火电厂烟气排放连续监测技术规范HJ/T 75-2001.,2001
[8]国家环保总局,固定污染源排放烟气连续监测系统技术要求及检测方法HJ/T 76-2001,2001.
[9]叭国家环保总局,火电厂烟气脱硫工程技术规范 石灰石/石灰-石膏法-HJ/T 179-2005,2005.
[10]霭家环保总局,污染源在线自动监控(监测)系统数据传输标准HJ/T212-2005,2005
[11]A. Toffolo,A. Lazzaretto, Evolutionary algorithms for multi-objective energetic and economic optimization in thermal system design[J]. Energy,2002.27:p.549-567..
[12]孔亮,张毅,丁艳军,吴占松,电站锅炉燃烧优化控制技术综述[J].电力设备,2006.7(2)：p.19-23.
[13]毛健雄,毛健全,赵树民编著,煤的清洁燃烧,科学出版社,1998；
[14]曾汉才,燃烧与污染,华中理工大学出版社,1992；
[15]曾汉才,姚斌,石烟煤与烟煤的混合燃烧特性与结渣特性研究[J].燃烧科学与技术,1996.2(2)：p.181-189.
[16]梁绍华,FT91型烟气排放连续监测装置，江苏省电力科学研究院企业标准,2005.唐黎华,王福明,朱学栋等.,燃焦中矿物质行为与灰熔融温度的关系[J].华东理工大学学报,2003.29(3)：p.243-247.
[17]梁绍华,胡为柏,鲁松林,烟气排放连续监测系统特性研究[J].江苏电机工程,2004.23(6)：p.2836-2839.
[18]王培红,李磊,人工智能在电站锅炉燃烧优化中的应用研究[J].中国电机工程学报,2004.24(4)：p184-187
[19]钟北京,傅维标,燃烧过程快速型氧化氮形成机理及其影响因素[J].燃烧科学与技术,1997.4.p388-393
[20]曾小敏,沙角A电厂5号锅炉低NOx排放分析[J].热力发电,2005.1：p.27-28.
[21]荆有印,齐永霞等,水平浓淡煤粉燃烧器内气固两相流的数值模拟[J] 中国动力工程学报,2005.25(19)：p.65-67.
[22]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-specific information on ash fusion temperatures (AFT) [J]. Fuel,2005.84:p.1768-1777.
[23]Nello Cristianini, John Shawe-Taylor著,李.王.增.译.,支持向量机导[M].北京：电子工业出版社,2004.
[24]Vapnik著.张学工译.,统计学习理论[M].北京：电子工业出版社,2004.
[25]王定成,唐毅等.,支持向量机回归理论与控制的综述[J].模式识别与人工智能,2003.2(16)： p.192-197.
[26]Peralta, Coal blend performance during pulverized-fuel combustion:estimation of relative reactivities by a bombcalorimeter test[J]. Fuel,2001.80(11):p.1623-1634.
[27]许昌,吕剑虹,基于生成机理的燃煤电站锅炉NOx排放量神经网络模型[J].中国电机工程学报,2004.24(10)：p.233-237.
[28]王新军,王飞等,用于电站煤粉锅炉NOx排放监测的BP神经网络试验研究[J].动力工程,2002,22(5)：p.1979-1982.
[29]Lolja S A, Haxhi H, Martin D. J., Correlations in the properties of Albanian coals[J]. Fuel,2002. 45(1):p.1095-1100.
[30]李永华,陈鸿伟等,煤粉燃烧排放特性数值模拟[J].中国电机工程学报,2003.23(3)：p.166-169.
[31]刘忠,阎维平等,煤种对超细煤粉再燃还原NO效率的影响[J].中国电机工程学报,2004.24(12)：p.273-276.
[32]Seggiani, M., Empirical correlations of the ash fusion temperatures and temperature of critical viscosity for coal and biomass ashes [J]. Fuel,1999.78(9):p.1121-1125.
[33]高岩,龚志豪.,锅炉燃烧系统的仿人智能控制[J].北京理工大学学报,2002.22(3)：p.315-317.
[34]艾红,锅炉效率动态模糊自寻优控制[J].c控制理论与应用,2002.21(4)：p.5-8.
[35]李凌,余岳峰,基于神经倒络的锅炉低NOx排放系统辨识[J].锅炉技术,2003.34(1)：p.68-71.
[36]安恩科,苏夏等,低NOx煤粉燃烧器的试验研究[J].锅炉技术,2005.36(1)：p.43-48.
[37]安恩科,周鸿权,电站锅炉燃烧特性的数值模拟[J].J同济大学学报(自然科学版),2004.32(8)：p.1042-1045.
[38]刘鸿,唐必光,锅炉高效低污染燃烧特性测试试验研究[J].四川电力技术,2002.3：p.7-9.
[39]金晶,李瑞阳等,超细煤粉还原NOx的试验研究[J].热能动力工程,2004.19(6)：p.582-586.
[40]王康丽,严河清,氮氧化物化学传感器[J].武汉大学学报(理学版),2003.49(4)：p.428-432.
[41]朱彤,李晓萍,炉膛结构对炉风NOx生成的影响[J].工业炉,2004.26(6)：p.1-4
[42]Fernando Rubiera, A. Arenillas, Borja Arias, Jose'J. Pis, Modification of combustion behaviour and NO emissions by coal blending[J]. fuel processing technology,2002.77-78:p.111-117.
[43]李永华,张志业,混煤对降低SO2排放的试验研究[J].华东电力,2003.1：p.1-2.
[44]Barnes, The Slagging Of Blends Of Power Station Coals [J]. Proceeding,effects of coal quality on power plants,1993:p.45-62.
[45]Douglas, Effects Of Increasing Coal Hardness And Volatility On Pilot-Scale Pulverization And Combustion Performance[J]. Seventh annual international Pittsburgh,1990:p.837-851.
[46]刘汉涛,工永征等,混煤燃烧氮析出特性试验研究[J].电站系统工程,2004：20(6)p.9-11.
[47]孙继德,张国军,煤粉燃烧降低NOx技术的试验研究[J].电站系统工程,1998：14(1)p.39-46.
[48]曾汉才,朱全利等,大型锅炉高效低NOx燃烧技术的研究[J].电站系统工程,1997.13(6)：p.40-44.
[49]Ozbyoglu G, Evren O M, A new approach for the prediction of ash fusion temperatures:A case study using Turkish lignitesfJJ. Fuel,2006.85(4):p.545-552.
[50]Stanislav V. Vassile, Kunihiro Kitano, Influence of mineral and chemical composition of coal ashes on their fusibility [J]. Fuel Processing Technology,1995.45(1):p.27-51.
[51]Lolja S A etal., Correlations in the properties of Albanian coals[J]. Fuel,2002.81(9):p. 1095-1100.
[52]Lolja Saimir A, Hajri H, et al., Correlation between ash fusion temperatures and chemical composition in Albanian coal ashes[J]. Fuel,2002.81(17):p.2257-2261.
[53]王春林,周吴,李国能,凌忠钱,基于遗传算法和支持向量机的低NOx燃烧优化[J].中国电机工程学报,2007.21(4)：p.79-84.
[54]Saimir A. Lolja, H.H., Rolanda Dhimitri, Spiro Drushku, Agim Malja, Correlation between ash fusion temperatures and chemical composition in Albanian coal ashes[J]. Fuel,2002.81(9):p. 2257-2261.
[55]石喜光,郑立刚,周.昊等,基于广义回归神经网络与遗传算法的煤灰熔点优化[J].浙江大学学报(工学版),2005.39(8)：p.1189-1192.
[56]S.K. Gupta, T.F. Wall, R.A. Creelman, R.P. Gupta, Ash fusion temperatures and the transformations of coal ash particles to slag[J]. Fuel Processing Technology,1998.56:p. 33-43.
[57]Chungen Yin, Z.L., Mingjiang Ni and Kefa Cen, Predicting coal ash fusion temperature with a backpropagation neural network model[J]. Fuel,1998.77(15):p.1777-1782.
[58]石喜光,郑立刚等,基于广义回归神经网络与贵传算法的煤灰熔点优化[J].浙江大学学报(工学版),2005.39(8)：p.1189-1192.
[59]廖艳芬,马茜,基于模糊神经网络的混沌优化算法在动力配煤中的应用[J].华南理工大学学报(自然科学版),2006.34(6)：p.117-123.
[60]Kalogirou S A, Artificial intelligence for the modeling and control of combustion processes; A review [J]. Progress in energy and combustion seience,2003.29(6):p.515-566.
[61]王春林,周昊,周樟华,基于支持向量机的大型电厂锅炉飞灰含碳量建模[J].中国电机工程学报,2005.25(20)：p.72-77
[62]Kang S G, Role Of Calcium In Coal And Sulfur Dioxide Emissions During Pulverized Coal[J] Combustion. Engineering Foundation conference on coal blending and switching of low sulfur western coals,1994:p.341-354.
[63]徐通模,燃媒自身CaO含量的脱硫效率研究[J].动力工程,1994.4.
[64]A.Arenillas, R.I.Backreedy, J.M. Jones, J.J. Pis, M. Pourkashanjan, F. Rubiera, modelling of NO formation in the combusion of coal blends [J]. Fuel,2002.81:p.627-636.
[65]Backreedy, Prediction of unburned carbon and NOx in a tangentially fired power station using single coals and blends[J]. Fuel,2005.84(17):p.2196-2203.
[66]翁安心,周吴,张力,岑可法,不同煤种混煤燃烧时NOx生成和燃尽特性的试验[J].热能动力工程,2004.19(3)：p.242-245.
[67]周昊,钱欣平,郑立刚,翁安心,岑可法,神经网络与模拟退火算法结合的锅炉低NOx燃烧优化[J].环境科学,2003.24(6)：p.63-68.
[68]C.E. Lee, C.B.Oh, J.H. Kim, Numerical and experimental investigations of the NOx emission characteristics of CH4-air coflow jet flames [J]. fuel,2004.83:p.2323-2334.
[69]李颖,周俊虎,BP经神网络在电厂优化配煤中预测性能的研究[J].电站系统工程,2002.18(3)：p.1-5.
[70]Booth, R.C. Roland W. B., Neural network-based combustion optimization reduces NO, emissions while improving performance[J]. Proc. Am. Power Conf.,,1998.60(2):p.667-672.
[71]王庆,NeuSIGHT神经网络闭环燃烧优化控制系统在沙角B电厂应用前景分析[J].河南电力,2005(3)：p.34-37.
[72]饶苏波,多目标进化算法在电站锅炉燃烧优化控制系统设计中的应用[J].广东电力,2006.19(4)：p.11-15.
[73]秦鹏,林中达,基于改进型El man神经网络和遗传算法的锅炉在线燃烧优化[J].锅炉技术,2005.36(5)：p.37-41.
[74]王培红,李磊磊,陈强,董益华,人工智能技术在电站锅炉燃烧优化中的应用研究[J].中国电机工程学报,2004.24(4)：p.184-188.
[75]王军,章正林,姜书敏,SmartProcess燃烧优化系统及其应用[J].电力设备,2006.7(2)：p.28-30.
[76]董均华,徐向东,基于煤种辨识的锅炉燃烧优化系统[J].热能动力工程,2006.21(2)：p.121-138.
[77]Vladimir Havlena, Jirj Findejsa, Application of model predictive control to advanced combustion control[J]. Control Engineering Practice,2005.13:p.671-680.
[78]许昌,吕剑虹,郑源,以效率和低NOx排放为目标的锅炉燃烧整体优化[J].中国电机工程学报,2006.26(4)：p.46-50.
[79]李智,蔡九菊,郭宏等,基于神经原网络的电厂锅炉燃烧谎化黍统[J].中国电力,2004.37(6)：p.75-77.
[80]周昊,朱洪波,曾庭华,基于人工神经网络大型电厂飞灰含碳量建模[J].中国电机工程学报,2002.6：p.96-100.
[81]zhou hao, Cen ke.-fa., Mao jian-bo, combinning Neual network and Genetic algorithms to optimize low NOx pulverized coal combustion[J]. fuel,2001.80(15):p.2163-2169.
[82]zhou hao, Cen ke-fa, Fan jian-ren, Modeling and optimization of the NOx emission characteristics of atangentially fired boiler with artificial neualnetwork[J]. energy,2004. 29(1):p.167-183.
[83]zhou hao, qin xin-ping, cen ke-fa, fan jian-ren, Optimizing puoverized coal combustion performance base on ANN and GA[J]. fuel Processing technology,2004.85(2):p.113-124.
[84]侯向阳,燃煤锅炉燃烧优化的调整试验研究[J].电力建设,2006.27(6)：p.35-39.
[85]Khesin M.et al., Combustion optimization using MPV combustion diagnostic and optimization systems-application experience[J]. Proc.-Annu. Int. Pittsburgh Coal Con(?),2000.17:p. 224-243.
[86]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,2006.33(1)：p.72-77.
[87]周国民,李宝仪,龚家猷,燃煤锯炉NO排放特性及其燃烧优化[J].锅炉技术,2006.37(3)：p.77-81.
[88]程伟良,夏国栋等,锅炉分级燃烧优化技术的研究[J].动力工程,2004.24(3)：p.337-341.
[89]赵宁,曹洪涛,李晓金,张春发,基于O2和CO信号修正的燃烧优化控制[J].电力科学与工程,2004.3(23-26).
[90]沈跃云,高小涛,锅炉低NOx燃烧优化技术试验分析[J].洁净煤燃烧与发电技术,2005：p.35-39.
[91]成庆刚,李争起,滕玉强,庄前玉,贾自臣,张寅,庄国中,果志明,低NO排放燃烧技术及燃烧优化的试验研究[J].锅炉技术,2005.36(5)：p.33-39.
[92]沈跃良,廖宏楷,周.昊等,风煤在线测量的锅炉燃烧优化系统[J].动力工程,2005.25(4)：p.561-565.
[93]Carsky M, K.D.K., Neural network modelling of coal pyroly-sis[J]. Fuel 2001.80(7):p. 1021-1027.
[94]Zhu Q, Jones J.M., Williams A, et al., The predictions of coal/char combustion rate using an artificial neural network approach[J]. Fuel 1999.78(14):p.1755-1762.
[95]Robert R. Jensen, Shankar Karki., Hossein Salehfar, Artificial neural network-based estimation of mercury speciation in combustion flue gases[J]. Fuel processing technology 2004. 85(451-462.).
[96]王培红,李磊磊,陈强,董益华,电站锅炉高效低污染燃烧优化算法研究[J].动力工程，2004.24(4)：p.466-470.
[97]Rong he, Toshiyuki Suda, et al, Analysis of low NO emission in high temperature air combustion for pulverized coal[J]. Fuel,2004.86:p.1133-1141.
[98]Robert Pieter van de Lans, Per Glarborg, et al, Influence of coal quality on combustion performance[J]. Fuel 1998.12(77):p.1317-1328.
[99]Fernado Rubiera, Ana Arenillas, et al, Modification of combustion behaviour and NO emissions by coal blendingfJJ. Fuel Processing Technology,2002.77-78:p.111-117.
[100]Havlena, V., Combustion optimization in a coal-fired boiler by controlling the air/fuel ratio[J]. PCT Int. Appl.,2002.27:p.883,167.
[101]Karel Svoboda, Michael Pohorely, Influence of operating conditions and coal properties on NOx and N2O emissions in pressurized fluidized bed combustion of subbituminous CoalsfJJ. Fuel,2004.83:p.1095-1103.
[102]R.P. Van der lans, P. Glarborg, K. Dam-Johansen, Influence of process parameters on nitrogen oxide formation in pulverized coal burners[J]. Prog. Energy Combust. Sci.,1997.23:p. 349-377.
[103]L. Armesto, H. Boerrigter, et al, N2O emissions from fluidized bed combustion. The effect of fuel characteristics and operating conditions[J]. Fuel,2003.82:p.1845-1850.
[104]Ryoichi Kurose, Michitaka Ikeda, et al, Pulverized coal combustion characteristics of high-fuel-ratio coalsfJJ. Fuel,2004.83:p.1777-1785.
[105]Christof Schylz, Volker Sick, Tracer-LIF diagnostics:quantitative measurement of fuel concentration, temperature and fuel/air ratio in practical combustion systems [J]. Progress in energy and combustion science,2005.31:p.75-121.
[106]Kiga T, Hanaoka R, Nakamura M, et al, Combustion characteristics of pulverized coal using high temperature air[J]. Reprinted AIAA,1999:p.99-0730.
[107]周怀春,肖旭东,韩元才.,煤粉燃烧诊断专家系统的研究[J].热力发电,1993.6：p.43-47.
[108]Robert R. Jensen, Shankaa Karki, Hossein Salehfar., Artificial neural network-based estimation of mercury speciation in combustion flue gases[J]. Fuel processing technology 2004.85:p. 451-462.
[109]Chu Li-zheng, Shieh Shyan-Shu, Lang Shi-Shang, et al, Constrained optimization of combustion in a simulated coal-fired boiler using artificial neural network model and information analysis[J]. Fuel,2003.82(6):p.693-703.
[110]孙巧玲,沈炯,李益国,基于遗传算法的燃煤电站锅炉整体燃烧优化方法研究[J].热能动力工程,2004.19(1)：p.85-89.
[111]Klaus Kruger, Rudiger Franke, Manfred Rode, Optimization of boiler start-up using a nonlinear boiler model and hard constraints [J]. Energy,2004.29:p.2239-2251.
[112]Mei Gong, Optimization of industrial energy systems by incorporating feedback loops into the MIND method[J]. Energy 2003.28:p.1655-1669.
[113]B.R. Stanmore, S.P.Visona, Prediction of NO emissions from a number of coal-fired power station boilers [J]. Fuel Processing Technology,2000.64:p.25-46.
[114]K J Hughes, A S Tomlin, et al, An Investigation of Important Gas-Phase Reactions of Nitrogenous Species from the Simulation of Experimental Measurements in combustion system[J]. Combustion and Flame,2001.124:p.573-589
[115]Jason Makansi, plants gain xonnfidence in optimization sofeware[J]. power,1998.9(10):p. 59-64.
[116]Peter Patterson, Micheal S. Krueger, Optimization saves money, reduces NOxfJJ. Power engineering,1997.9:p.21-23.
[117]Levy, E.et.al., Combustion optimization using an expert system and neural networks [J]. Proceedings of the International Joint Power Generation Conference, Volume 1: Environmental Control/Fuels and Combustion Technologies,1996.1:p.411-419.
[118]李雪亮,杨延龄,电站锅炉燃烧分析专家系统[J].中国电力,1997.30(3)：p.29-32.
[119]陈鸿伟,杨中其,周志萍,吉云,基于风粉在线监测锅炉燃烧优化控制[J].锅炉技术,2005.36(6)：p.36-40.
[120].李智,蔡九菊,郭宏等,基于神经元网络的电厂锅炉燃烧优化系统[J].中国电力,2004.37(6)：p.75-78.
[121]陈敏生,刘定平,电站锅炉飞灰含碳量的优化[J].动力工程,2005.25(4)：p.545-550.
[122]李智,蔡九菊,郭宏,丁艳军,程芳真,基于神经元网络的电厂锅炉燃烧优化系统[J].中国电力,2004.37(6)：p.75-78.
[123]张海,吕俊复等,我国燃电站锅炉NOx排放的现状分析和应对措施[J].中国电机工程学报,2005：25(1)：p.125-130.
[124]Go, Coal blend combustion fusibility ranking from mineral matter composition [J]. Fuel,2003. 82(15-17):p.2087-2095.
[125]Sonia Helle, A.G., Guillermo AIfaro,Ximena Garcia, Claudia Ulloa, Coal blend combustion: link between unburnt carbon in fly ashes and maceral composition[J]. Fuel,2003.80:p. 209-223.
[126]萧嵘,王继承,张福炎.,支持向量机理论综述[J].计算机科学,2000.3(27)：p.1-3.
[127]王景雷,吴景社,孙景生等.,支持向量机在地下水位预报中的应用研究[J].水力学报,2003.5：p.122-129.
[128]John H. Pavlish, April A.Aenderson, using the CQIM to Evaluate switching to western low-sulfur coals [J]. Engineering Foundation conference on coal blending and switching of tow-sulfur western coals,1994:p.421-440.
[129]成庆刚,李争起,滕玉强,庄前玉等,低NO排放燃烧技术及燃烧优化的试验研究[J].锅炉技术,2005.36(5)：p.32-38.
[130]王庆,NeuSIGHT神经网络闭环燃烧优化控制系统在沙角B电厂应用前景分析[J] 河南电力,2005.3：p.34-39.
[131]王.军,章正林,姜书敏,SmartProcess燃烧优化系统及其应用[J].电力设备,2006.7(2)：p.28-31.
[132]Keerthi K, Lin C J, Asymptotic behaviors of support vector machines with Gaussian kernel[J]. Neural Computation,2003.15(3):p.1667-1689.
[133]Lin H T, Lin CJ, A study on sigmoid kernels for SVM and the training of non-PSD Kernels by SMO-type methods[EB]. http://www.csie.ntu.edu.tw/-cjlin/papers.Html,2003,March.
[134]周昊,朱洪波,曾庭华等,基于有工神经网络大型电厂飞灰含碳量建模[J].中国电机工程学报,2002.6：p.96-100.
[135]徐正中.,燃煤硫排放系数的研究及脱硫要求的确定[J].热力发电,1994.3：p.5-15..
[136]Yanpeng Liu, Mingguang Wu, Jixin Qian, Predicting coal ash fusion temperature based on its chemical composition using ACO-BP neural network[J]. Thermochimica Acta,2006.10(26): p.1016.
[137]Christopher J. Montgomery, et al, REDUCED CHEMICAL KINETIC MECHANISMS FOR HYDROCARBON FUELS[J].
[138]Jennifer P. Spinti, David W.Pershing, The fate of char-N at pulverized coal conditions [J]. Combustion and flame,2003.135:p.299-313.