作者：刘千1, 王东风1,2, 韩璞1,2
作者单位：1. 河北省发电过程仿真与优化控制工程技术研究中心(华北电力大学), 河北 保定 071003;
2. 华北电力大学自动化系, 河北 保定 071003
关键词：电站锅炉;参数测量;燃烧评价;支持向量机
摘要：
电站锅炉燃烧的稳定性和经济性是锅炉燃烧状况评价的重要组成部分,及时准确地评价能指导燃烧优化运行。为此,该文提出一种基于炉膛参数场测量和支持向量机的电站锅炉燃烧状况评价方法,通过分析炉膛参数对锅炉燃烧稳定性和经济性的影响,建立电站锅炉燃烧的稳定性和经济性评判支持向量机模型,并根据炉膛参数测量数据对模型进行校验。以某680 MW燃烧机组锅炉为例进行实测,结果表明:该方法能够对任意工况下的锅炉燃烧稳定性和经济性进行客观有效地评判,计算速度快,能够在线指导锅炉燃烧的优化运行。
Evaluation on combustion condition of power plant boiler based on furnace parameters measurement and support vector machine
LIU Qian1, WANG Dongfeng1,2, HAN Pu1,2
1. Hebei Engineering Research Center of Simulation & Optimized Control for Power Generation, North China Electric Power University, Baoding 071003, China;
2. Department of Automation, North China Electric Power University, Baoding 071003, China
Abstract: The stability and economy of a power plant boiler combustion is important for boiler combustion evaluation. Timely and accurate evaluation can effectively guide the combustion optimization.An comprehensive evaluation strategy for the operating condition of boiler combustion, based on furnace parameters measurement and support vector machine, was proposed. Through analyzing the effects of furnace parameters on combustion stability and economy of a power plant boiler. A support vector machine model for the stability and economy of boiler combustion was developed and verified. Good predicting performance was achieved with the data from furnace parameters measurement. A 680 MW coal-fired boiler is taken as an example. The results show that the evaluation of the stability and economy of boiler combustion can be effectively completed by the method proposed under different working conditions with a higher calculation speed, which can be used for guiding of boiler combustion optimization.
Keywords: power plant boiler;parameters measurement;combustion evaluation;support vector machine
2015, 41(9): 6-10 收稿日期: 2015-3-2;收到修改稿日期: 2015-4-13
基金项目: 中央高校基本科研业务费专项(2014MS139)
作者简介: 刘千(1985-),男,河南郸城县人,博士研究生,研究方向为电站锅炉燃烧优化控制。
参考文献
[1] 蒋敏华,黄斌. 燃煤发电技术发展展望[J]. 中国电机工程学报,2012,32(29):1-8.
[2] Zhou H, Zhao J P, Zheng L G, et al. Modeling NOx emissions from coal-fired utility boilers using support vector regression with ant colony optimization [J]. Engineering Applications of Artificial Intelligence,2012,25(1):147-158.
[3] 蔡小舒,季琨,苏明旭,等. 基于光谱分析的煤粉火焰复合判据和燃烧诊断研究[J]. 中国电机工程学报,2004,24(1):211-215.
[4] 马骏,余岳峰,范浩杰. 基于频谱分析和自组织神经网络的火焰燃烧诊断研究[J]. 动力工程,2004,24(6):852-856.
[5] 刘禾. 基于火焰图像和模糊神经网络的锅炉燃烧稳定性判别[J]. 仪器仪表学报,2008,29(6):1280-1284.
[6] 谢刚,王理飞,谢克明. 基于火焰图像特征和粗糙集理论的燃烧诊断系统[J]. 测试技术学报,2006,20(3):230-235.
[7] Bae H, Kim S, Wang B H,et al. Flame detection for the steam boiler using neural networks and image information in the Ulsan steam power generation plant[J]. IEEE Transactions on Industrial Electronics,2006,53(1):338-348.
[8] 刘吉臻,牛成林,李建强,等. 锅炉经济性分析及最优氧量的确定[J]. 动力工程,2009,29(3):245-249.
[9] 王东风,刘千,赵文杰,等. 基于炉膛参数场测量的电站锅炉燃烧稳定性和经济性状态模糊综合评判[J]. 动力工程学报,2015,35(6):76-83.
[10] 胡主宽. 锅炉炉膛温度场测量技术研究现状与发展趋势探讨[J]. 中国测试,2015,41(4):5-9.
[11] 王东风,刘千. 电站锅炉炉膛温度测量技术发展[J]. 中国测试,2014,40(3):8-12.
[12] Li N, Weng C S. Gas concentration and temperature reconstruction by genetic simulated annealing algorithm based on multi-wavelengths diode laser absorption spectroscopy[J].Acta Physica Sinica,2010,59(10):6914-6920.
[13] 王春林,周昊,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[J]. 中国电机工程学报,2005,25(20):72-76.
[14] Gu Y P, Zhao W J, Wu Z S. Online adaptive least squares support vector machine and its application in utility boiler combustion optimization systems[J]. Journal of Process Control,2011,21(7):1040-1048.
[15] 赵四化,王琪. 支持向量机在电机转子故障诊断识别中的应用[J]. 中国测试,2009,35(3):121-124.
[16] Lü Y, Liu J Z, Yang T T, et al. A novel least squares support vector machine ensemble model for NOx emission prediction of a coal-fired boiler[J]. Energy,2013(55):319-329.
[17] 邱东,符营营,张楠,等. 支持向量机脱磷效率与炉渣碱度测试模型研究[J]. 中国测试,2014,40(1):1-4.
