齐敏芳,李晓恩,刘潇,王艺霏

• 1:北京低碳清洁能源研究院
• 2:北京科技大学土木与资源工程学院

摘要(Abstract)：

燃煤发电机组供电煤耗的高低是衡量机组节能降耗水平的主要指标。本文利用大数据分析技术对机组能耗相关历史数据进行分析,采用反向传播(BP)神经网络对不同负荷区间分别建立供电煤耗特性分析模型,计算各个负荷工况区间内各运行可控参数对供电煤耗的影响评价因子即敏感性系数,以及不同负荷区间内模型预测能力。结果表明:基于BP神经网络的供电煤耗特性分析模型的训练和预测精度均在±0.6%范围内,模型计算精度较高;各运行可控参数在不同负荷区间内对供电煤耗的影响存在差异,但具有一定规律;在实际运行中应重点调整敏感性系数大的特征参数。

关键词(KeyWords)： 大数据;燃煤机组;供电煤耗;神经网络;反向传播;评价因子;敏感性分析

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 齐敏芳,李晓恩,刘潇,王艺霏

DOI: 10.19666/j.rlfd.201905126

参考文献(References)：

• [1]国家发展改革委员会.煤电节能减排升级与改造行动计划(2014—2020年)[R].北京:国家能源局, 2014:1-8.National Development and Reform Commission. Action plan for upgrading and renovation of coal and electricity energy conservation and emission reduction(2014—2020)[R]. Beijing:National Energy Agency, 2014:1-8.
• [2]曾鸣.《电力发展“十三五”规划》解读[J].中国电力企业管理, 2017(1):14-16.ZENG Ming. Interpretation of 13th five-year plan for electric power development[J]. China Power Enterprise Management, 2017(1):14-16.
• [3]王宁玲.基于数据挖掘的大型燃煤发电机组节能诊断优化理论与方法研究[D].北京:华北电力大学, 2011:89-97.WANG Ningling. Theoretical research on data miningbased energy-saving diagnosis and optimization for large coal-fired power plants[D]. Beijing:North China Electric Power University, 2011:89-97.
• [4]朱龙飞.基于混合模型的热力系统能耗基准状态确定方法研究[D].北京:华北电力大学, 2015:10-17.ZHU Longfei. Method for determining energyconsumption benchmark state in the thermal system of coal-fired units based on hybrid model[D]. Beijing:North China Electric Power University, 2015:10-17.
• [5] VALERO A, CORREAS L, ZALETA A, et al. On the thermoeconomic approach to the diagnosis of energy system malfunctions[J]. Energy, 2004, 29(2):1889-1907.
• [6]齐敏芳.大数据技术及其在电站机组分析中的应用[D].北京:华北电力大学, 2016:79-90.QI Minfang. Big data technology and its application on the analysis of power plant units[D]. Beijing:North China Electric Power University, 2016:79-90.
• [7]王惠杰,张春发,宋之平.火电机组运行参数能耗敏感性分析[J].中国电机工程学报, 2008, 28(29):6-10.WANG Huijie, ZHANG Chunfa, SONG Zhiping.Sensitive analysis of energy consumption of operating parameters for coal-fired unit[J]. Proceedings of the CSEE, 2008, 28(29):6-10.
• [8]闫顺林.多元扰动下的热力系统能效分析模型及应用研究[D].北京:华北电力大学, 2011:30-70.YAN Shunlin. Method for determining energyconsumption benchmark state in the thermal system of coal-fired units based on hybird model[D]. Beijing:North China Electric Power University, 2011:30-70.
• [9]杨志平.大型燃煤发电机组能耗时空分布与节能研究[D].北京:华北电力大学, 2013:79-90.YANG Zhiping. The temporal-spacial distribution of energy consumption and energy saving of large coal-fired power units[D]. Beijing:North China Electric Power University, 2013:79-90.
• [10]刘炳含,付忠广,王鹏凯,等.大数据挖据技术在燃煤电站机组能耗分析中的应用研究[J].中国电机工程学报, 2018, 38(12):3578-3587.LIU Binghan, FU Zhongguang, WANG Pengkai, et al. Big data mining technology application in energy consumption analysis of coal-fired power plant units[J].Proceedings of the CSEE, 2018, 38(12):3578-3587.
• [11] SMREKAR J, ASSADI M, FAST M, et al. Development of artificial neural network model for a coal-fired boiler using real plant data[J]. Energy, 2009, 34(2):144-152.
• [12] LI J, ZHOU T, JU Z, et al. Sensitivity analysis of CHF parameters under flow instability by using a neural network method[J]. Annals of Nuclear Energy, 2014, 71:211-216.
• [13] FARJAM A, OMID M, AKRAM A, et al. A neural network based modeling and sensitivity analysis of energy inputs for predicting seed and grain corn yields[J]. Journal of Agricultural Science&Technology, 2014, 16(4):767-778.
• [14] MONTANO J, PALMER A. Numeric sensitivity analysis applied to feedforward neural networks[J]. Neural Computing&Applications, 2003, 12(2):119-125.
• [15] PALMER A, MONTA?O J, FRANCONETTI F.Sensitivity analysis applied to artificial neural networks for forecasting time series[J]. Methodology, 2008, 4(2):80-86.
• [16] LOTUFO A D P, LOPES M L M, MINUSSI C R.Sensitivity analysis by neural networks applied to power systems transient stability[J]. Electric Power Systems Research, 2007, 77(7):730-738.
• [17] YUSOFF A R B, AZIZ I A. Sensitivity analysis via artificial neural network of biomass boiler emission[J].Journal Mekanikal, 2004, 18:66-77.
• [18] REUTER U, MEHMOOD Z, GEBHARDT C. Efficient classification based methods for global sensitivity analysis[J]. Computers&Structures, 2012, 110/111(0):79-92.
• [19] CORTEZ P, EMBRECHTS M J. Using sensitivity analysis and visualization techniques to open black box data mining models[J]. Information Sciences, 2013, 225:1-17.
• [20]唐文勇,周佳,朱荣成.基于人工神经网络方法的舰船参数灵敏度分析[J].舰船科学技术, 2006, 28(6):111-114.TANG Wenyong, ZHOU Jia, ZHU Rongcheng.Parametric sensitivity analysis of ships based on artificial neural network method[J]. Ship Science and Technology,2006, 28(6):111-114.
• [21] HASHEM S. Sensitivity analysis for feedforward artificial neural networks with differentiable activation functions[C]. International Joint Conference on Neural Networks. 1992:419-424.
• [22] LU M, ABOURIZK S, HERMANN U. Sensitivity analysis of neural networks in spool fabrication productivity studies[J]. Journal of Computing in Civil Engineering, 2001, 15(4):299-308.
• [23] SHOJAEEFARD M H, AKBARI M, TAHANI M, et al.Sensitivity analysis of the artificial neural network outputs in friction stir lap joining of aluminum to brass[J].Advances in Materials Science and Engineering, 2013,2013(1):1-7.
• [24]陈太聪,韩大建,苏成.参数灵敏度分析的神经网络方法及其工程应用[J].计算力学学报, 2004, 21(6):752-756.CHEN Taicong, HAN Dajian, SU Cheng. Neural network method in parameter sensitivity analysis and its application in engineering[J]. Chinese Journal of Computational Mechanics, 2004, 21(6):752-756.
• [25]肖宝兰,俞小莉,韩松,等.基于神经网络的换热器翅片参数灵敏度分析[J].浙江大学学报(工学版), 2011,45(1):122-125.XIAO Baolan, YU Xiaoli, HAN Song, et al. Parameter sensitivity analysis of fin based on neural network in heat exchanger[J]. Journal of Zhejiang University(Engineering Science), 2011, 45(1):122-125.
• [26] VGB PowerTech. Application of data reconciliation in accordance with VDI 2048:VGB-S-009-S-00[S]. Essen,Germany:VGB PowerTech e.V, 2012:20.
• [27] GUO S S, LIU P, LI Z. Enhancement of performance monitoring of a coal-fired power plant via dynamic data reconciliation[J]. Energy, 2018, 151:203-210.
• [28] QI M F, FU Z G, CHEN F. Outliers detection method of multiple measuring points of parameters in power plant units[J]. Applied Thermal Engineering, 2015, 85:297-303.