用户名: 密码: 验证码:
1025t/h锅炉燃烧优化软件研究与开发
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
我国能源发展规划中提出要在“十一五”计划期间把电力工业中发电煤耗和厂用电率从原来的370g/kwh和5.9%分别降低到355g/kwh和4.5%,并对电力工业污染物排放提出了更加严格的要求。为响应国家“节能减排”的号召,并在期限内圆满完成“十一五”规划对电力工业所提要求,开发基于人工智能技术的锅炉燃烧优化软件对锅炉运行进行优化调整无疑是最有效、最直接的手段之一。
     要开发锅炉燃烧优化软件,就需要建立能够反映煤质、运行参数与锅炉经济性、环保性能指标的耦合关系模型。在此基础上,采用优化算法对锅炉燃烧进行优化。本文以一台1025t/h电站锅炉为研究对象,进行了现场实验,利用实验所采集的数据建立了针对该台锅炉的在线燃烧优化模型,并利用寻优算法对模型进行了优化仿真。通过对该台锅炉历史数据回归分析建立了针对该炉的煤质—锅炉性能耦合模型。
     基于锅炉在线燃烧模型和煤质—锅炉性能耦合模型,为该炉开发了一套燃烧优化软件。该软件有三个主要功能模块:(1)风粉在线监测模块,该模块可以对锅炉风、粉参数进行监测,并对所监测到的异常参数进行报警和故障诊断。(2)燃烧优化在线指导模块,模块依据不同优化目标(经济性、环保性、综合性)对锅炉燃烧进行在线优化。(3)煤质—锅炉性能评估模块,模块根据煤质变化提出相应运行指导意见,以提高锅炉的经济性和环保性。
In the report of the 11th Five-Year Plan for Energy Development, our country plan to decrease the coal consumption from 370g/kwh in 2005 to 355g/kwh in 2010,and reduce the power consumption from 5.9% in 2005 to 4.5% in 2010.The government always call on enterprise to save energy and reduce emission. To develop on-line system of combustion optimization based on artificial intelligence is one of the most direct and effective means to finish these tasks on time.
     The paper built the model which can reflect coupling relations between coal, the boiler operating parameters and boiler performance for the on-line system of combustion optimization. Then to use optimization algorithm get different optimized parameters. The paper gets data from field experiment on a utility boiler of 1025t/h, and build combustion optimization model based on the data. Then simulation of optimized the model used optimization algorithm. The paper uses the history data of the boiler to build the coupled model of coal-boiler performance.
     To build a software system of combustion optimization based on the two models in the previous section. The software has three functions: On-line monitoring module of wind and powder: The module monitors the parameters of wind and pulverized coal on-line. When the parameters are abnormal, the module will give an alarm and fault diagnosis. The module of combustion optimization on-line: the module give different optimized parameters when operation staff inputs different indicators which include economic、environmental and multi-objective. The evaluative module of coal-boiler performance: when burning coal remarkably changes, the system will give suggestion about operation.
引文
[1] 2008年全国煤炭工业统计快报中国煤炭,2009(1)
    [2]王研,李京文我国煤炭消费现状与未来煤炭需求预测中国人口资源与环境,2008,18(3):152 155
    [3]管卫华,顾朝林,林振山中国能源消费结构的变动规律研究自然资源学报,2006,21(3):401-406
    [4]王鑫,傅德黔,努丽亚NOx排放统计方法综述中国环境监测,2008,24(4):57.60
    [5] 2007~国环境状况公报http://www zhb gov cn/plan/zkgb/,2008
    [6]苏亚欣,毛玉如,徐璋燃煤氮氧化物排放控制技术北京:化学工业出版社,2005
    [7]能源发展”十一五”规划(下)中国水能及电气化,2007:60-63
    [8]周建新,樊征兵,司风琪等电站锅炉燃烧优化技术研究发展综述2008,39(5):33 36
    [9]周海珠,安恩科电站锅炉燃烧优化技术的发展趋势锅炉技术,2008,39(1):38.41
    [10]Techniques in process optimisation PACE-Process and Control Engineering,2002,55(10):14 15
    [11]Boyle R J,Pech J W,Patterson P D Reducing NOx while maintaining boiler performance at TVA’S Johnsonville steam plant using constrained sequential optimization 1995:2.1 157-1 163
    [12]Boyle R J,Pech J W,Patterson P D Simultaneous reduction of NOx and heat rate at TVA'S Johnsonville steam plant using sequential process optimization American Society ofMechanical Engineers,1995,1:37-45
    [13]Mcvay M,Jarc C Online dynamic optimization of cyclone units for NOx control and efficiency improvement at Illinois Power’S Baldwin station 1998
    [14]Patterson P,Krueger M S Optimization saves money,reduces NOx Power Engineering,1997,101(9):21-24
    [15]Eakle D L,Payson E P,Jarc C A On-line advisory system using dynamic optimization enables Allegheny Power to improve boiler efficiency and control NOx American Society of Mechanical Engineers,1997,5:45-50
    [16]Booth R C,Roland Jr W B Neural network-based combustion optimization reduces NOx emissions while improving performance 1998
    [17]周吴,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实时燃烧优化系统动力工程,2003,23(5):2665.2669
    [18]秦鹏,林中达基于改进型E1man神经网络和遗传算法的锅炉在线燃烧优化锅炉技术,2005,36(5):37.41
    [19]王春林,周吴,周樟华等基于支持向量机的大型电厂锅炉飞灰含碳量建模中国电机工程学报,2005,25(20):72 76
    [20]陈敏生,刘定平基于Ls sVM和sPEA2的电站锅炉燃烧多目标优化研究华东电力,2006,34(3):50-54
    [21]李素芬,吴祯祥,葛玉林电站锅炉N0x排放与效率的混合建模及优化热科学与技术,2007,6(1):26.31
    [22]郑立刚,周吴,王春林等变尺度混沌蚁群算法在N0x排放优化中的应用中国电机工程学报,2008,28(1 1):18.23
    [23]梁绍华,郑立刚,周吴等基于支持向量机与高斯分布估计的低N0x排放化工学报,2009,60(1):223 228
    [24]Boser B E,Guyon I M,Vapnik V N A training MgorRhm for optimal margin classifiers In Proceedings of the 5th atonal ACM Workshop on computation learning theory ACM Press 1992,144 152
    [25]田景文,高美娟人工神经网络算法研究及应用北京:北京理工大学出版社,2006
    [26]Abo-Khalil A G,Lee D MPPT control of wind generation systems based on estimated wind speed using SVR IEEE Transactions on Industrial Electronics,2008,55(3):1489-1490
    [27]Castro-Neto M,Jeong Y,Jeong M Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions Expert Systems with Applications,2009 36(3):6164 6173
    [28]Gandhi A B,Joshi J B,Kulkami A A,et al SVR-based prediction of point gas hold-up for bubble column reactor through recurrence quantification analysis of LDA time-series International Journal ofMutiphase Flow-,2008,34(12):1099-1107
    [29]Lin C,Wang S Fuzzy support vector machines IEEE Transactions on Neural Networks,2002,13(2):464 471
    [30]Zhang L,Zhou W,Jiao L Wavelet Support Vector Machine IEEE Transactions on Systems,Man,and Cybernetics,Part B:Cybernetics,2004,34(1):34 39
    [31]Suykens J A K,Vaaadewalle J Least Squares support vector machines classifiers Neural Processing Le~ers,1999,9(3):293 300
    [32]阎威武,邵惠鹤支持向量机和最小二乘支持向量机的比较及应用研究控制与决策,2003,18(3):358.360
    [33]雷英杰MATLAB遗传算法工具箱及应用西安:西安电子科技大学,2005
    [34]Gitizadeh M,Kalantar M Genetic algorithm-based fuzzy multi-objective approach to congestion management using FACTS devices Electrical Engineering,2009,90(8):539.549
    [35]Murphy L,Abdel-Aty-Zohdy H S,Hashem-Sherif M A genetic algorithm tracking model for product deployment in telecom services Midwest Symposium on Circuits and Systems,2005,2005:1729-1732
    [36]Matta M E A genetic algorithm for the proportionate mutiprocessor open shop Computers and Operations Research,2009,36(9):2601-2618
    [37]安恩科,宋饶,杨霞基于支持向量机和遗传算法的燃煤电站锅炉多目标燃烧优化节能,2008(10):22 25
    [38]霍罕妮支持向量机中参数选取的一个问题大连:大连理工大学,2007
    [39]樊玉泉等锅炉原理北京:中国电力出版社,2008
    [40]岑可法,周吴,池作和大型电站锅炉安全及优化运行技术北京:中国电力出版社,2003 1991(3):72 80
    [41]向军电站锅炉煤质影响模型及优化设计系统研究武汉:华中科技大学,2000
    [42]王雅勤煤质变化对锅炉运行安全性与经济性影响的分析华北电力学院学报,1991(3):72 80
    [43]熊友辉,孙学信煤质对发电厂运行和成本的影响河北电力技术,1999,18(4) 6-11
    [44]熊中奥,郭林,陈刚煤质变化对300Mw锅炉运行影响分析华中电力,1996 9(6):11-13
    [45]李永庆,程荣新,李世波风粉在线监测系统在锅炉上的应用东北电力技术2004(5):35-36
    [46]周守军,张冠敏电站锅炉一次风粉在线监测及诊断系统锅炉技术,2007 38(4):47-50

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700