基于神经网络对配煤成浆性的预测研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
本文主要目的为提高水煤浆成浆性能和建立高精度的水煤浆配煤成浆性能预测模型,应用回归模型和神经网络模型等预测模型对水煤浆的制备与开发进行了一系列的基础性研究。
     首先,通过实验研究了煤种理化特性参数对煤成浆性的影响,考察了煤种的Mad、Aad和Oad等几种因素与煤种的成浆性之间的关系。由实验结果可以发现煤种的成浆性是由多种因素决定的,而且几种因素之间的关系又较为复杂,单独的用一种影响因素来分析一个煤种的成浆性是不科学的。
     由于各种单煤的性质不同,混合后的不同煤种在成浆过程中相互影响,相互制约,因此配煤成浆性不可能是各组分煤种特性的简单叠加,而是呈现出非常复杂的非线性特征,而日益兴起的神经网络技术正是解决配煤非线性问题的有效方法。
     通过分析煤种的各性质与成浆性能的相关性,选择了十种因素进行了回归分析的预测,来与神经网络模型进行对比。通过对十因子、九因子、五因子、四因子和三因子的线性和非线性分析,预测结果最好的是五因子的线性回归模型,预测结果的误差为1.69%。
     共进行了十因子、九因子、五因子、四因子和三因子的组合的煤种的成浆性能影响因素的神经网络预测分析。通过对比每种输入因子数的最佳模型参数和误差,发现其中五因子神经网络预测模型的结果最好,其预测结果的误差到了0.49%的水平,大大低于五因子线性回归模型,同时每种输入因子数的神经网络预测模型结果都比相对应的回归方程的结果要好。
The main purpose of this paper is to improve the performance of coal-water slurry and establish high-precision blending CWS performance prediction models, applicate regression models and neural network models and other forecasting models to research on the coal-water slurry preparation and development.
     First of all, through the experiment effects of the physical and chemical characteristics on coal slurry parameters have been researched, while coals Mad, Aad, and Oad several factors was investigated in coal slurry parameters. From the experimental results we can find that coal-forming slurry is determined by a variety of factors, and also the relationship between several factors is more complex, and a separate analysis of the impact factors of a coal-water slurry-is not scientific.
     A variety of single coal are different, mixed into a slurry of different coals in the process of mutual influence and·constraints, blending into a slurry of coal characteristics of each component can not be a simple sum, but it shows a very complex non-linear characteristics, while the increasing emergence of neural network technology to solve nonlinear problems is an effective way.
     By analyzing correlation between various natures of coal and coal slurry ability, 10 kinds of factors are selected for regression analysis prediction which is compared with the neural network model. Through the ten factors, nine factors, five factors, four factors and three factor linear and nonlinear analysis, the five factors is the best linear regression model, the error is 1.69%.
     The ten factors, nine factors, five factors, four factors and three factor the neural network models are analyzed. By comparing the number of optimal model parameters and errors, we fine a five-factor neural network prediction model is the best result, the error is 0.49%, while the number of each type of input factors of neural network prediction model results are better than the corresponding results of the regression equation.
引文
[1]吉登高,张丽娟,高明峰,丁志杰,陈志刚.我国水煤浆制备与燃烧技术的发展.选煤技术[J],2004(4):3-15.
    [2]张丽娜,李柯,贾静梅等.浅议水煤浆锅炉的技术特点及其应用.中国能源[J].2009;31(5):40-41.
    [3]曹征彦.中国洁净煤技术[M].北京:中国物资出版社,1998.
    [4]张传名,刘建忠,周俊虎,等.220t/h燃油锅炉改烧水煤浆技术及应用.热力发电[J].2006;35(5):30-33.
    [5]钱伯章.水煤浆制备及添加剂技术的发展.煤炭加工与综合利用[J].2004(03):4.
    [6]张荣曾.中国水煤浆制浆技术的进展.洁净煤技术[J].1999(5):13-18.
    [7]梁兴,詹隆,王国房等.水煤浆制备工艺的应用与发展,煤炭加工与综合利用[J].2006.5:51-55.
    [8]焦红光,胡正彬.浅谈我国燃煤污染危害及其防治.选煤技术[J],2004,(02):3-6.
    [9]岑可法,邱坤赞,朱燕群.我国能源展望及新能源的开发利用[J].大众用电,2005,(01):3-4.
    [10]段清兵梁兴张胜局等.提高神华煤气化水煤浆浓度的可行性研究.洁净煤技术[J].2009(2):49-52.
    [11]刘志群.水煤浆技术应用现状及对策分析.环境保护科学[J].2006,(05):53-54.
    [12]钱伯章.水煤浆制备及添加剂技术的发展.煤炭加工与综合利用[J].2004,(03):4.
    [13]刘珊,赵光宇,白成志等.日本勿来电厂8号机组燃用水煤浆的实践.洁净煤技术[J].2003,(01):32-34.
    [14]岑可法,姚强,曹欣玉等.煤浆燃烧、流动、传热和气化的理论与应用技术[M]. 杭州:浙大出版社,1997.
    [15]崔秀玉,雷晓萍,杨向福.浅谈中国水煤浆技术的开发与应用.洁净煤技术[J].2002,8(4):13-16.
    [16]陶文生,荣绍斌.浅谈水煤浆的应用前景.煤炭技术[J].2002,6,21,(6):74-75.
    [17]张荣曾.水煤浆制浆技术[M].北京:科学出版社,1996.
    [18]Zeng Jiliang,Cao Xinyu,Zhao Xiang,etal.Application of CWS Combustion Techology to Power Plants in Guangdong Province of China.Proceeding of ICOPE-03,International Conference on Power Engineering03,2003.11.9,Kobe Japan,Volume 2,Published by the JSME,415-419.
    [19]Dincer H,Boylu F,Sirkeci AA,Atesok G.The effect of chemicals on the viscosity and stability of coal water slurries. Internation Journal of Mineral Processing[J].2003;70(1-4):41-51.
    [20]Malgarini G,et al.CWM Suitability for Injection into Blast Furface,Int.European Conf.on CWM[J],1983.
    [21]Tiwari KK,Basu SK,Bit KC,Banerjee S,Mishra KK.High-concentration coal-water slurry from India coals using newly developed additives.Fuel Processing Technology[J].2004;85(1):31-42.
    [22]Oxce Fuel Company.Coal.aqueous slurry[P].US 4645514,1987-02-24.
    [23]Yavuz, Reha; Kucukbayrak, Sadriye. Adsorption of an anionic dispersant on lignite[J]. Energy Conversion and Management. Volume:42, Issue:18, December,2001,pp.2129-2137.
    [24]Nat Distillers Chem Corp.Derivatives of polyether glycol eaters of poly-carboxylic acids as rheological additives for coal-water slurries[P]. CA1303353, 1992-06-16.
    [25]Karatepe, Nilgun. Adsorption of a non-ionic dispersant on lignite particle surfaces[J]. Energy Conversion and Management Volume:44, Issue:8, May,2003, pp. 1275-1284.
    [26]刘定平,叶向荣,邓华裕.基于LSSVM-MODE水煤浆生产优化控制.华南理工大学学报(自然科学版)[J].2009;37(2):158-164.
    [27]周寿祖,朱凤梅,张继臻.水煤浆加压气化装置的优化配煤.化肥设计[J].2003 (41):32-37.
    [28]纪明俊,李寒旭,燕春福.淮化Texaco气化配煤制取水煤浆的研究.安徽化工[J].2002(6):4-6.
    [29]汤永新,陈迎,纪明俊等.配煤对煤灰熔点和水煤浆性能影响的研究.煤炭技术[J].2002;21(11):67-72.
    [30]张继臻,黄长胜.优化制浆工艺及其管理来提高煤浆质量.化肥工业[J].2007;34(5):41-46.
    [31]叶向荣,李定平,陈其中等.粒度级配对混煤水浆浓度与黏度的影响.煤炭转化[J].2008;4:31(2):28-30.
    [32]周俊虎,李艳昌,程军等.人工神经网络预测煤炭成浆浓度的研究.燃料化学学报[J].2005;12:33(6):666-671.
    [33]李颖,周俊虎.BP神经网络在优化配煤预测模型中的研究.煤炭转化[J].2002;4:25(2):79-85.
    [34]阮伟,张伟宁,周俊虎等.电厂优化配煤多模表机会约束数学模型的建立.动力工程[J].2001;2:21(1):1090-1092.
    [35]刘猛,陈良勇,段钰锋.煤浆浓度和粒度分布对煤浆黏度预测的影响.燃料化学学报[J].2009;6:37(3):266-270.
    [1]谢克昌,煤的结构与反应性[M].北京:科学出版社,2002.
    [2]李珊珊,程军,李艳昌等.水煤浆黏度的几种影响因素分析.煤炭转化[J].2006;29(1):23-26.
    [3]傅丛,李英华,孙刚.水煤浆稳定性测定方法的研究与标准制定.洁净煤技术[J].2002;8(4):20-23.
    [4]刘红缨,朱书全,王奇.矿物对水煤浆稳定性的影响研究.中国矿业大学学报[J].2004;33(3):4:283.
    [5]杨国荣.浅议中国神木煤煤质特性及工业利用方向.煤化工[J].1994(4):5:31.
    [6]支献华.水煤浆稳定性的影响因素及评定方法.煤炭加工及综合利用[J].2000;1:2:38.
    [7]吴家珊,吉庆军,郝爱明等.神木煤主要性质对其水煤浆特性的影响.煤炭转化[J].1992;15(4):7:69.
    [8]Grime W R.The physical structure of coal[A].Coal Science Vol.1 [C].N Y:Academic Press,1982.21-42.
    [9]Raffi M.Turian,Jamel F.Attall,Properties and rheology of coal-water mixtures using different coals.Fuel[J].2002.81.16.
    [10]N.S.Roh,D.H.Shin,D.C.Kim,Rheological behavior of coal water mixtures:2. Effect of surfactants and temperature,fuel[J].74(1995)1313-1 318.
    [11]Ahmet Gurese An investigation on effects of various parameters on viscosities of coal-water mixture prepared with Erzurum-Askle lignite coal 2006
    [12]朱书全,刘红缨,刘利等.3种难溶性矿物对成浆性的影响.中国矿业大学学报[J].2003,32(2):115-118.
    [13]乔英云,田元宇,黄伟.水煤浆制浆技术的研究进展.山西能源与节能[J],2006.
    [14]G Atesok,F Boylu,A A Sirkeci,etal.The effect of coal properties on the viscosity of coal water slurries.Fuel[J].2002,(81):1855-1858.
    [15]S K Mishra,P K Senapati,D Panda.Rheological of coal water slurry.Energy Sources,2002,24:159-167.
    [16]于敦喜,徐厚明,刘小伟等.燃煤可磨性指数的人工神经网络预测.煤炭技术[J].2003;22(9):3:91.
    [17]谢克昌.煤的结构与反应[M].北京:科学出版社,2002.
    [18]李珊珊,程军,李艳昌等.水煤浆黏度的几种影响因素分析.煤炭转化[J].2006;29(1):23-26.
    [1]洪楠,候军,SAS for Windows.统计分析系统教程[M].北京:电子工业出版社,2001.
    [2]胡良平,Windows SAS for 6.12&8.0.实用统计教程[M].北京:军事医学科学出版社,2001.
    [3]沈其军,SAS统计分析[M].南京:东南大学出版社,2001.
    [4]Mishra S. K. Senapati P. K., Panda D., Rheological behavior of coal-water slurry, Energy Sources,2002,24(2):159-167.
    [5]Turian R M, Attal J F, Sung D J, etal. Properties and rheolo of coal-water mixtures using different coals. Fuel[J],2002,81(16);2019-2033.
    [6]Li Yong-Xin,Li Bao-Qing. Study on the ultrasonic irradiation of coal water slurry. Fuel[J].2000,79(3-4);235-241.
    [7]张荣曾.中国水煤浆制浆技术的进展[M].北京:中国矿业大学北京校区,1999.9.
    [8]SchefTee R S, Skolnik E G, Rossmeissl N P, Further development and evaluation of coal-water mixture technology[A].4th International Symposiumon.Coal Slurry Combustion[C].Japan,1982.
    [1]林海军,张礼勇,任殿义等.基于Wiener核和BP神经网络的非线性模拟电路故障诊断.仪器仪表学报[J].2009(9):1946-1949.
    [2]梁国华,习树峰,王本德等.基于BP神经网络的旬降雨径流相关预报模型.水力发电[J].2009(8):10-12.
    [3]王卓,贾利民,秦勇等.铁路行车事故预测方法分析与比较.中国安全科学学报[J].2009(8):34-39.
    [4]邵波,曹志彤,陈宏平等.基于BP神经网络的永磁直线同步电机齿槽力预估计器.浙江大学学报(工学版)[J].2006:40:4:(4):1281-1286.
    [5]王钟羡,李慧梅.基于BP神经网络算法的断裂参数预测.应用力学学报[J].2009(2):379-382.
    [6]殷春根,骆仲泱,倪明江等.煤的工业分析至元素分析的BP神经网络预测模型燃料化学学报[J].1999:27(5):7:408-413.
    [7]彭辉,文友先,王巧华.基于小波变换和BP神经网络的蛋壳破损检测。农业机械学报[J].2009(2):170-174.
    [8]李红霞,赵新华,迟海燕等.基于改进BP神经网络模型的地面沉降预测与分析.天津大学学报[J].2009:42(1):60-64.
    [9]潘毅,杨成,林佣军等.基于BP神经网络的FRP加固凝混土柱承载力预测.西南交通大学学报[J].2008:43(6):736-739.
    [10]于国强,李占斌,张霞等.地下水动态的BP神经网络模型及改进的灰色斜率关联分析.西安建筑科技大学学报:自然科学版[J].2009:(41),4:566-570.
    [11]刘振宇,郭玉明.应用BP神经网络预测高压脉冲电场对果蔬干燥速率的影响。农业工程学报[J].2009:25(2):235-239.
    [12]杨建刚.人工神经网络实用教程[M].杭州:浙江大学出版社,2001
    [13]焦李成,神经网络计算[M].西安:西安电子科技大学出版社,1993.
    [14]Hagan TM, Demuth BH, Beale HM,(戴葵译),Neural Network design[M].北京:机械工业出版社,2002.
    [15]阎平凡,张长凡.人工神经网络与模拟进化计算[M].北京:清华大学出版社,2001.
    [16]周俊虎,李艳昌,程军等.人工神经网络预测煤炭成浆浓度的研究。燃料化学学报[J].2005:33(6):5:666-670.
    [1]梁兴,詹隆,王国房等.水煤浆制备工艺的应用与发展.煤炭加工与综合利用[J].2006(5):5:51-55.
    [2]Dincer H,Boylu F,Sirkeci AA,Atesok G.The effect of chemicals on the viscosity and stability of coal slurries.Internation Journal of Mineral Processing[J]. 2003;70(1-4):41-51.
    [3]Turian RM,Attal JF,Sung D-J.Properties and rheology of coal-water mixtures using different coals.Fuel[J].2002;81(16):2019-2033.
    [4]Atesok QBoylu F,Sirkeci AA,Dincer H.The effect of coal properties on the viscosity of coal-water slurries.Fuel[J].2002;81(14):1855-1858.
    [5]Logos C,Nguyen QD.Effect of particle size on the flow properties of a South Australian coal-water slurry.Power Technology[J].1996;88(1):55-58.
    [6]周俊虎,李艳昌,程军等.人工神经网络预测煤种成浆浓度的研究.燃料化学学报[J].2005,33(6):666-670.