基于小波变换和人工神经网络方法的煤热转化预测模型研究
|
摘要
基于我国总体能源资源消费结构特点及能源安全、环保要求,煤炭高效清洁转化利用已成为必然的发展趋势。但是煤炭转化利用常常是在高温、高压等苛刻的条件下操作,同时由于煤炭的复杂性导致煤炭清洁利用过程中影响因素繁多,这些都增加了研究过程的难度和实验工作量,大大增加了实验成本,并且得到的实验数据往往含有“噪音”,谱图时常出现重叠峰。为了解决这些问题,本文采用连续小波变换处理实验数据,采用改进BP神经网络方法建立预测模型,为煤转化过程的工艺设计与优化,催化剂的筛选等提供重要的依据与参考。
本文建立的第一个模型是基于改进BP神经网络的煤加氢热解过程预测模型,采用小波变换方法提取失重速率-温度图谱中的第一温峰和峰个数信息,模型选取碳氢比、灰分和挥发分作为网络输入,失重率、第一温峰和峰个数作为输出。预测结果为：多输出预测模型校验样本失重率和第一温峰预测平均相对误差为3.35%和0.54%,单输出预测模型的平均相对误差为2.26%和0.30%,失重速率峰个数预测模型无论训练样本还是校验样本预测值和实验值也都完全吻合。同时,与多输出预测模型相比,单输出预测模型训练速度快,信息学习全面,预测误差小,泛化能力强。基于建立好的各个单输入预测模型,发现碳氢比、灰分和挥发分对煤加氢热解都有着重要的影响,其中C/H的影响最大,这与我们的实际煤热解理论相符合。
第二个模型是基于改进BP神经网络的煤二氧化碳催化气化反应预测模型,输入选择碳氢比、灰分、挥发分、催化剂种类和催化剂含量5个影响因素,输出考察气化率、气化初始温度和最大气化速率所对应的温度。预测结果为：多输出预测模型校验样本气化率、气化初始温度和最大气化速率所对应的温度预测平均相对误差是2.68%、3.64%、1.99%,单输出预测模型的平均相对误差分别为1.70%、0.58%、0.55%,显著小于归回公式的预测误差。同时,单输出预测模型收敛快速,对这3个考察参数的预测效果明显优于多输出预测模型,预测精度高,泛化能力强。基于建立好的各个单输入预测模型,发现催化剂种类对煤二氧化碳催化气化反应有着极大地影响,因此筛选合适的催化剂对于提高煤气化反应效率来说是非常有效而且重要的工作。本文建立的预测模型对煤气化反应有着重要的指导作用,同时能够避免大量的重复实验过程。
According to the overall consumption structure of energy resources, safe and environmental requirements, clean coal conversion has become an inevitable trend. However, coal conversion is in the high temperature and high pressure. The reaction conditions are very harsh. Moreover, the complexity of coal leads to the result that there are many influence factors in coal conversion process. Those increase the research difficulty, experimental workload as well as cost. Meanwhile, the experimental data often contain noise and spectrum peaks overlap. Therefore, to solve these problems, we use continuous wavelet transform to process experimental data and the improved BP neural network to establish prediction model of coal conversion process. That will provide an important basis and reference for coal conversion process design, optimization, catalyst screening and so on.
In this paper, the first established model is prediction model of coal pyrolysis based on the improved BP neural network. We use the continuous wavelet transform to extract informations of the first temperature peak position and peak numbers from the weight loss rate-temperature figures. We select carbon and hydrogen ratio, ash, and volatile as inputs, weight loss, the first temperature peak position and peak numbers as outputs. The results are: in the multi-outputs prediction model, average relative errors of weight loss and the first temperature peak position for test samples are 3.35% and 0.54% respectively. In the single output prediction model, average relative errors are 2.26% and 0.30% respectively. And in the peak numbers prediction model, calculated and measured values are also same. Moreover, compared with the multi-outputs prediction model, single output prediction model has fast training speed, comprehensive study ability, small prediction error, strong generalization ability. Based on the established single output prediction model, it is found that carbon and hydrogen ratio, ash, and volatile all have important effects on the coal pyrolysis process, in which carbon and hydrogen ratio is greatest influence factor. That is consistent with actual theory of coal pyrolysis.
The second prediction model is prediction model of coal catalytic gasification based on the improved BP neural network. We select carbon and hydrogen ratio, ash, volatile, type and concentration of catalyst as inputs, gasification efficiency, the initial temperature of gasification and the temperature of maximum gasification rate as outputs. The results are:in the multi-outputs prediction model, average relative errors of gasification efficiency, the initial temperature of gasification and the temperature of maximum gasification rate are 2.68%,3.64% and 1.99% respectively, and, in the single output prediction model, average relative errors are 1.70%,0.58% and 0.55% respectively, which are much smaller than those predicted by regression equation. Moreover, in the single output prediction model, the convergence is fast, prediction results for three output parameters are superior to those of multi-outputs prediction model, prediction precision is high, and generalization ability is strong. Based on the established single output prediction model, it is found that the type of catalyst has a great influence on coal catalytic gasification reaction. Therefore, screening appropriate catalyst is very effectve and important work to improve the efficiency of coal gasification. In this paper, the established prediction models have an important guiding role in coal gasification process and avoid a large number of the repeated experiments.
本文建立的第一个模型是基于改进BP神经网络的煤加氢热解过程预测模型,采用小波变换方法提取失重速率-温度图谱中的第一温峰和峰个数信息,模型选取碳氢比、灰分和挥发分作为网络输入,失重率、第一温峰和峰个数作为输出。预测结果为：多输出预测模型校验样本失重率和第一温峰预测平均相对误差为3.35%和0.54%,单输出预测模型的平均相对误差为2.26%和0.30%,失重速率峰个数预测模型无论训练样本还是校验样本预测值和实验值也都完全吻合。同时,与多输出预测模型相比,单输出预测模型训练速度快,信息学习全面,预测误差小,泛化能力强。基于建立好的各个单输入预测模型,发现碳氢比、灰分和挥发分对煤加氢热解都有着重要的影响,其中C/H的影响最大,这与我们的实际煤热解理论相符合。
第二个模型是基于改进BP神经网络的煤二氧化碳催化气化反应预测模型,输入选择碳氢比、灰分、挥发分、催化剂种类和催化剂含量5个影响因素,输出考察气化率、气化初始温度和最大气化速率所对应的温度。预测结果为：多输出预测模型校验样本气化率、气化初始温度和最大气化速率所对应的温度预测平均相对误差是2.68%、3.64%、1.99%,单输出预测模型的平均相对误差分别为1.70%、0.58%、0.55%,显著小于归回公式的预测误差。同时,单输出预测模型收敛快速,对这3个考察参数的预测效果明显优于多输出预测模型,预测精度高,泛化能力强。基于建立好的各个单输入预测模型,发现催化剂种类对煤二氧化碳催化气化反应有着极大地影响,因此筛选合适的催化剂对于提高煤气化反应效率来说是非常有效而且重要的工作。本文建立的预测模型对煤气化反应有着重要的指导作用,同时能够避免大量的重复实验过程。
According to the overall consumption structure of energy resources, safe and environmental requirements, clean coal conversion has become an inevitable trend. However, coal conversion is in the high temperature and high pressure. The reaction conditions are very harsh. Moreover, the complexity of coal leads to the result that there are many influence factors in coal conversion process. Those increase the research difficulty, experimental workload as well as cost. Meanwhile, the experimental data often contain noise and spectrum peaks overlap. Therefore, to solve these problems, we use continuous wavelet transform to process experimental data and the improved BP neural network to establish prediction model of coal conversion process. That will provide an important basis and reference for coal conversion process design, optimization, catalyst screening and so on.
In this paper, the first established model is prediction model of coal pyrolysis based on the improved BP neural network. We use the continuous wavelet transform to extract informations of the first temperature peak position and peak numbers from the weight loss rate-temperature figures. We select carbon and hydrogen ratio, ash, and volatile as inputs, weight loss, the first temperature peak position and peak numbers as outputs. The results are: in the multi-outputs prediction model, average relative errors of weight loss and the first temperature peak position for test samples are 3.35% and 0.54% respectively. In the single output prediction model, average relative errors are 2.26% and 0.30% respectively. And in the peak numbers prediction model, calculated and measured values are also same. Moreover, compared with the multi-outputs prediction model, single output prediction model has fast training speed, comprehensive study ability, small prediction error, strong generalization ability. Based on the established single output prediction model, it is found that carbon and hydrogen ratio, ash, and volatile all have important effects on the coal pyrolysis process, in which carbon and hydrogen ratio is greatest influence factor. That is consistent with actual theory of coal pyrolysis.
The second prediction model is prediction model of coal catalytic gasification based on the improved BP neural network. We select carbon and hydrogen ratio, ash, volatile, type and concentration of catalyst as inputs, gasification efficiency, the initial temperature of gasification and the temperature of maximum gasification rate as outputs. The results are:in the multi-outputs prediction model, average relative errors of gasification efficiency, the initial temperature of gasification and the temperature of maximum gasification rate are 2.68%,3.64% and 1.99% respectively, and, in the single output prediction model, average relative errors are 1.70%,0.58% and 0.55% respectively, which are much smaller than those predicted by regression equation. Moreover, in the single output prediction model, the convergence is fast, prediction results for three output parameters are superior to those of multi-outputs prediction model, prediction precision is high, and generalization ability is strong. Based on the established single output prediction model, it is found that the type of catalyst has a great influence on coal catalytic gasification reaction. Therefore, screening appropriate catalyst is very effectve and important work to improve the efficiency of coal gasification. In this paper, the established prediction models have an important guiding role in coal gasification process and avoid a large number of the repeated experiments.
引文
[1]马丽萍,石炎福,余华瑞.小波分析及其在化工信号分析处理中的应用及展望[J].化工进展,2005,24(2)：147-153
[2]Zhou Hao, Qian Xinping, Cen Kefa, et al. Optimizing pulverized coal combustion performance based on ANN and GA[J]. Fuel Processing Technology,2003,85:113-124
[3]Javier Pallares, Inmaculada Arauzo, Enrique Teruel. Development of an engineering system for unburned carbon prediction[J]. Fuel,2009,88:187-194
[4]Zhu Q, Jones J M, Williams A, et al. The predictions of coal/char combustion rate using an artificial neural network approach[J]. Fuel,2009,78:1755-1762
[5]Patel Shagufta U, Jeevan Kumar B, Badhe Yogesh P, et al. Estimation of gross calorific value of coals using artificial neural networks [J]. Fuel,2007,86:334-344
[6]Abbas T, Awais M M, Lockwood F C. An artificial intelligence treatment of devolatilization for pulverized coal and biomass in co-fired flames [J]. Combustion and Flame,2003,132:305-318
[7]Zhou Hao, Cen Kefa, Fan Jianren. Modeling and optimization of the NOX emission characteristics of a tangentially fired boiler with artificial neural networks[J]. Energy,2004,29: 167-183
[8]吴成军,段钰锋.燃煤烟气中汞形态分布的神经网络预测研究[J].电站系统工程,2007,23(6)：15-18
[9]张东平,金余其,严建华,等.煤与垃圾流化床焚烧HC1排放及BP神经网络预测[J].煤炭学报,2004,29(3)：333-733
[10]Carsky M, Kuwornoo D K. Neural network modelling of coal pyrolysis[J]. Feul,2001,80: 1021-1027
[11]于敦喜,孙学信,胡松,等.RBF神经网络在煤的热解特性研究中的应用[J].华中科技大学学报,2001,29(6)：95-96
[12]Guo Bing, Shen Youting, Li Dingkai,et al. Modelling coal gasification with a hybrid neural network[J]. Feul,1997,76(12):1159-1164
[13]郭 兵,沈幼庭,李定凯,等.煤气化过程的神经网络直接辨识[J].燃烧科学与技术,1999,5(1)：83-90
[14]张 晓,吴诗勇,顾 菁,等.神经网络预测煤焦高温气化反应速率研究[J].煤炭转化, 2007,30(2)：31-62
[15]张立安,杨建丽,刘振宇,等.人工神经网络用于煤直接液化反应模拟的研究[J].计算机与应用化学,1999,16(6)：459-462
[16]李 颖,周俊虎.BP神经网络在优化配煤预测模型中的研究[J].煤炭转化,2002,25(2)：79-84
[17]Jorjani E, Chehreh Chelgani S, Mesroghli Sh. Application of artificial neural networks to predict chemical desulfurization of Tabas coal[J]. Fuel,2008,87:2727-2734
[18]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[J].燃料化学学报,2005,33(6)：666-670
[19]Bezerra E M, Bento M S, Rocco J A F F, et al. Artificial neural nerwork (ANN) prediction of kinetic parameters of (CRFC) composites [J]. Computational Materials Science,2008,44:656-663
[20]葛广军,王羲.智能煤质在线分析系统研究[J].平顶山工学院学报,2006,15(2)：33-35
[21]Perez-Fortes M, Bojarski A D, Velo E, et al. Conceptual model and evalution of generated power and emissions in an IGCC plant[J]. Energy,2009,34:1721-1732
[22]徐立军,李松云,龚立艳,等.原子力显微镜图像小波去噪方法的研究[J].电子显微学报,2009,28(2)：125-140
[23]Mehdi Nasria, Hossein Nezamabadi-pour. Image denoising in the wavelet domain using a new adaptive thresholding function[J]. Neurocomputing,2009,72(4-6):1012-1025
[24]张军华,陆基孟.小波变换方法在地震资料去噪和提高分辨率中的应用[J].石油大学学报(自然科学版),1997,21(1)：18-24
[25]Cao Siyuan, Chen Xiangpeng. The second-generation wavelet transform and its application in denoising of seismic data[J]. Applied Geophysics,2005,2(2):70-74
[26]关 伟.基于小波变换的地震信息去噪方法研究与模拟[D].北京：中国地质大学,2008
[27]赵青峰,韩能润,郑福荣,等.小波变换及其在地震资料去噪中的应用[J].石油仪器,2010,24(2)：73-74
[28]石岩峻.地震资料的小波去噪方法[J].内蒙古石油化工,2010,(6)：47-48
[29]钟 剑,陈科贵,王洪芳,等.小波去噪在全波列测井资料气层识别中的应用[J].石油天然气学报,2010,32(2)：280-283
[30]赵小强,王新明.基于小波去噪的FVS-KPCA故障检测方法[J].化工自动化及仪表,2010,37(1)：20-24
[31]邵学广,孙培艳,蔡文生,等.小波变换及其在色谱重叠峰解析中的应用[J].化学通报,1997,(8)：59-62
[32]邵学广,侯树泉,赵贵文.小波变换用于重色谱叠峰组分信息的提取[J].分析化学研究报告,1998,26(12)：1428-1431
[33]王国庆,马 威,孙雨安,等.连续小波变换-纯变量法解析气象色谱-质谱重叠信号[J].郑州轻工业学院学报(自然科学版),2006,21(1)：12-15
[34]邵学广,虞正亮.小波变换-免疫算法用于重叠分析化学信号的解析[J].计算机与应用学,2002,19(3)：242-244
[35]孙晓琦,李井会,于洪梅,等.小波分析和人工神经网络方法用于重叠色谱峰的解析[J].鞍山科技大学学报,2004,27(5)：321-323
[36]熊智新,,路文初,胡上序.小波变换和RBF网络用于模式法分解重叠色谱峰[J].浙江大学学报(工学版),2005,39(4)：516-521
[37]王佩佩,宋晓峰,杨平.利用基于小波特征提取的网络模型解析色谱重叠峰[J].计算机与应用化学,2007,24(5)：673-677
[38]胡 松,孙学信,熊友辉,等.小波分析在热重实验数据处理中的应用[J].化工学报,2002,53(12)：1276-1280
[39]曹 明,林星春,刘 刚.小波分解在空气污染指数分析中的应用[J].研究进展,2006,10：13-17
[40]杨 虎,陈虹,马 燮,等.小波分析在气固流化床中颗粒碰撞压力信号分析中的应用[J].化学反应工程与工艺,2006,22(4)：423-723
[41]岑 为,杨世峰,薛 蓉,等.基于小波变换模极大法的聚乙烯催化剂表面分形分析[J].国家科学,2007,37(4)：374-379
[42]谭志昌,吴正方,史正涛MATLAB在长春多尺度气候诊断中的应用研究[J].山西师范大学学报(自然科学版),2007,21(3)：76-79
[43]Wu Shouguo, Nie Lei, Wang Jianwei, et al. Flip shift subtraction method:a new tool for separating the overlapping voltammetric peaks on the basis of finding the peak positions through the continuous wavelet transform[J]. Journal of Electroanalytical Chemistry,2001,508:11-27
[44]王永骥,涂健.神经元网络控制[M].北京：机械工业出版社,1998：23-67
[45]Hornik K. Approximation capabilities of multilayer feedforward networks[J]. Neural Networks, 1991,4:251-257
[46]飞思科技产品研发中心.神经网络理论与MATLAB7实现[M].北京：电子工业出版社,2005：30-77
[47]Fredric M.Ham, Ivica Kostanic神经计算原理(英文版)[M].北京：机械工业出版社,2003：112-140
[48]Shimodaria H. A weight value initialization method for improved learning performance of the back propagation algorithm in neural networks[J]. Proc. of the 6th international conference on tools with artificial intelligence,1994,2:854
[49]闻新,周露,李翔,等MATLAB神经网络仿真与应用[M].北京：科学出版社,1989：282
[50]Wu W, Walczak B, Massart D L, et al. Artificial neural networks in classification of NIR spectral data:design of the training set[J]. Chemometrics and Intelligent Labotatory Systems,1996,33:35-46
[51]罗进成.中国西部五种典型煤的热解及催化加氢热解行为热重研究[D].西安：西北大学,2008
[52]刘建平,赵钦强.煤的热分解及其影响因素[J].大众标准化,2005,(8)：34-37
[53]朱学栋,朱子彬,唐黎华,等.煤的热解研究II.煤化程度对氢气气氛下热解的影响[J].华东理工大学学报,1998,24(3)：262-266
[54]Wanzl W, Bitter D. Experiments on pyrolysis behaviour of different coals[J]. Fuel Proc Tech, 1990,24:11-17
[55]殷宏彦,王美君,王俊宏,等.钙、钠添加剂对平朔煤热解特性的影响[J].转化利用,2010,3：31-35
[56]赵娅鸿,林建英,常丽萍,等.矿物质对煤热解气化过程中NH3形成的影响[J].环境化学,2004,23(1)：26-30
[57]景晓霞,常丽萍.矿物质对煤中硫氮在热解气化过程中迁移变化的催化作用[J].工业催化,2004,12(10)：13-17
[58]李 文,于惠梅,陈皓侃,等.矿物质脱除对煤中硫在氢气热解中逸出的影响[J].中国矿业大学学报,2003,32(6)：646-649
[59]Wu Z, Sugimoto Y, Kawashima H. The influence of mineral matter and catalyst on nitrogen release during slow pyrolysis of coal and related material:a comparative study[J]. Energy & Fuel, 2002,16(2):451-456
[60]Wu Z, Sugimoto Y, Kawashima H. Effect of demineralization and catalyst addition on N2 formation during coal pyrolysis and on char gasification[J]. Fuel,2003,82(15-17):2057-2064
[61]Matsumoto S, Walker P L Jr. Char gasification in steam at 1123K catalyzed by K, Na, Ca and Fe-effect of H2, H2S and COS[J]. Carbon,1986,24(3):277-283
[62]Semra K. Desulfurization of a Turkish lignite at various gas atmospheres by pyrolysis:effect of mineral matter[J]. Fuel,2003,82(12):1509-1516
[63]赵娅鸿.矿物质对煤热解/气化过程中氮迁移的影响[D].太原：太原理工大学,2003
[64]Tsubouchi N, Ohtsuka Y. Nitrogen release during high temperature pyrolysis of coals and catalytic role of calcium in N2 formation[J]. Fuel,2002,81(18):2335-2342
[65]朱廷钰,刘丽鹏,王洋,等.氧化钙催化煤温和气化研究[J].燃料化学学报,2000,28(1)：36-39
[66]Franklin H D, Cosway R G, Peters W A, et al. Effects of cations on the rapid pyrolysis of a Wyodak subbituminous coal[J]. Ind. Eng. Chem. Proc. Res. Dev,1983,22(1):39-42
[67]Friebel J, Koepsel R F W. The fate of nitrogen during pyrolysis of German low rank coals-a parameter study[J]. Fuel,1999,78(8):923-932
[68]朱廷钰,汤忠,黄戒介,等.煤温和气化特性的热重研究[J].燃料化学学报,1999,27(5)：420-423
[69]刘艳.利用热重分析仪研究煤的催化气化[D].西安：西北大学,2007
[70]赵新法,杨黎燕,石振海.煤中矿物质在气化反应中的催化作用分析[J].煤碳技术,2005,1(24)：103-104
[2]Zhou Hao, Qian Xinping, Cen Kefa, et al. Optimizing pulverized coal combustion performance based on ANN and GA[J]. Fuel Processing Technology,2003,85:113-124
[3]Javier Pallares, Inmaculada Arauzo, Enrique Teruel. Development of an engineering system for unburned carbon prediction[J]. Fuel,2009,88:187-194
[4]Zhu Q, Jones J M, Williams A, et al. The predictions of coal/char combustion rate using an artificial neural network approach[J]. Fuel,2009,78:1755-1762
[5]Patel Shagufta U, Jeevan Kumar B, Badhe Yogesh P, et al. Estimation of gross calorific value of coals using artificial neural networks [J]. Fuel,2007,86:334-344
[6]Abbas T, Awais M M, Lockwood F C. An artificial intelligence treatment of devolatilization for pulverized coal and biomass in co-fired flames [J]. Combustion and Flame,2003,132:305-318
[7]Zhou Hao, Cen Kefa, Fan Jianren. Modeling and optimization of the NOX emission characteristics of a tangentially fired boiler with artificial neural networks[J]. Energy,2004,29: 167-183
[8]吴成军,段钰锋.燃煤烟气中汞形态分布的神经网络预测研究[J].电站系统工程,2007,23(6)：15-18
[9]张东平,金余其,严建华,等.煤与垃圾流化床焚烧HC1排放及BP神经网络预测[J].煤炭学报,2004,29(3)：333-733
[10]Carsky M, Kuwornoo D K. Neural network modelling of coal pyrolysis[J]. Feul,2001,80: 1021-1027
[11]于敦喜,孙学信,胡松,等.RBF神经网络在煤的热解特性研究中的应用[J].华中科技大学学报,2001,29(6)：95-96
[12]Guo Bing, Shen Youting, Li Dingkai,et al. Modelling coal gasification with a hybrid neural network[J]. Feul,1997,76(12):1159-1164
[13]郭 兵,沈幼庭,李定凯,等.煤气化过程的神经网络直接辨识[J].燃烧科学与技术,1999,5(1)：83-90
[14]张 晓,吴诗勇,顾 菁,等.神经网络预测煤焦高温气化反应速率研究[J].煤炭转化, 2007,30(2)：31-62
[15]张立安,杨建丽,刘振宇,等.人工神经网络用于煤直接液化反应模拟的研究[J].计算机与应用化学,1999,16(6)：459-462
[16]李 颖,周俊虎.BP神经网络在优化配煤预测模型中的研究[J].煤炭转化,2002,25(2)：79-84
[17]Jorjani E, Chehreh Chelgani S, Mesroghli Sh. Application of artificial neural networks to predict chemical desulfurization of Tabas coal[J]. Fuel,2008,87:2727-2734
[18]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[J].燃料化学学报,2005,33(6)：666-670
[19]Bezerra E M, Bento M S, Rocco J A F F, et al. Artificial neural nerwork (ANN) prediction of kinetic parameters of (CRFC) composites [J]. Computational Materials Science,2008,44:656-663
[20]葛广军,王羲.智能煤质在线分析系统研究[J].平顶山工学院学报,2006,15(2)：33-35
[21]Perez-Fortes M, Bojarski A D, Velo E, et al. Conceptual model and evalution of generated power and emissions in an IGCC plant[J]. Energy,2009,34:1721-1732
[22]徐立军,李松云,龚立艳,等.原子力显微镜图像小波去噪方法的研究[J].电子显微学报,2009,28(2)：125-140
[23]Mehdi Nasria, Hossein Nezamabadi-pour. Image denoising in the wavelet domain using a new adaptive thresholding function[J]. Neurocomputing,2009,72(4-6):1012-1025
[24]张军华,陆基孟.小波变换方法在地震资料去噪和提高分辨率中的应用[J].石油大学学报(自然科学版),1997,21(1)：18-24
[25]Cao Siyuan, Chen Xiangpeng. The second-generation wavelet transform and its application in denoising of seismic data[J]. Applied Geophysics,2005,2(2):70-74
[26]关 伟.基于小波变换的地震信息去噪方法研究与模拟[D].北京：中国地质大学,2008
[27]赵青峰,韩能润,郑福荣,等.小波变换及其在地震资料去噪中的应用[J].石油仪器,2010,24(2)：73-74
[28]石岩峻.地震资料的小波去噪方法[J].内蒙古石油化工,2010,(6)：47-48
[29]钟 剑,陈科贵,王洪芳,等.小波去噪在全波列测井资料气层识别中的应用[J].石油天然气学报,2010,32(2)：280-283
[30]赵小强,王新明.基于小波去噪的FVS-KPCA故障检测方法[J].化工自动化及仪表,2010,37(1)：20-24
[31]邵学广,孙培艳,蔡文生,等.小波变换及其在色谱重叠峰解析中的应用[J].化学通报,1997,(8)：59-62
[32]邵学广,侯树泉,赵贵文.小波变换用于重色谱叠峰组分信息的提取[J].分析化学研究报告,1998,26(12)：1428-1431
[33]王国庆,马 威,孙雨安,等.连续小波变换-纯变量法解析气象色谱-质谱重叠信号[J].郑州轻工业学院学报(自然科学版),2006,21(1)：12-15
[34]邵学广,虞正亮.小波变换-免疫算法用于重叠分析化学信号的解析[J].计算机与应用学,2002,19(3)：242-244
[35]孙晓琦,李井会,于洪梅,等.小波分析和人工神经网络方法用于重叠色谱峰的解析[J].鞍山科技大学学报,2004,27(5)：321-323
[36]熊智新,,路文初,胡上序.小波变换和RBF网络用于模式法分解重叠色谱峰[J].浙江大学学报(工学版),2005,39(4)：516-521
[37]王佩佩,宋晓峰,杨平.利用基于小波特征提取的网络模型解析色谱重叠峰[J].计算机与应用化学,2007,24(5)：673-677
[38]胡 松,孙学信,熊友辉,等.小波分析在热重实验数据处理中的应用[J].化工学报,2002,53(12)：1276-1280
[39]曹 明,林星春,刘 刚.小波分解在空气污染指数分析中的应用[J].研究进展,2006,10：13-17
[40]杨 虎,陈虹,马 燮,等.小波分析在气固流化床中颗粒碰撞压力信号分析中的应用[J].化学反应工程与工艺,2006,22(4)：423-723
[41]岑 为,杨世峰,薛 蓉,等.基于小波变换模极大法的聚乙烯催化剂表面分形分析[J].国家科学,2007,37(4)：374-379
[42]谭志昌,吴正方,史正涛MATLAB在长春多尺度气候诊断中的应用研究[J].山西师范大学学报(自然科学版),2007,21(3)：76-79
[43]Wu Shouguo, Nie Lei, Wang Jianwei, et al. Flip shift subtraction method:a new tool for separating the overlapping voltammetric peaks on the basis of finding the peak positions through the continuous wavelet transform[J]. Journal of Electroanalytical Chemistry,2001,508:11-27
[44]王永骥,涂健.神经元网络控制[M].北京：机械工业出版社,1998：23-67
[45]Hornik K. Approximation capabilities of multilayer feedforward networks[J]. Neural Networks, 1991,4:251-257
[46]飞思科技产品研发中心.神经网络理论与MATLAB7实现[M].北京：电子工业出版社,2005：30-77
[47]Fredric M.Ham, Ivica Kostanic神经计算原理(英文版)[M].北京：机械工业出版社,2003：112-140
[48]Shimodaria H. A weight value initialization method for improved learning performance of the back propagation algorithm in neural networks[J]. Proc. of the 6th international conference on tools with artificial intelligence,1994,2:854
[49]闻新,周露,李翔,等MATLAB神经网络仿真与应用[M].北京：科学出版社,1989：282
[50]Wu W, Walczak B, Massart D L, et al. Artificial neural networks in classification of NIR spectral data:design of the training set[J]. Chemometrics and Intelligent Labotatory Systems,1996,33:35-46
[51]罗进成.中国西部五种典型煤的热解及催化加氢热解行为热重研究[D].西安：西北大学,2008
[52]刘建平,赵钦强.煤的热分解及其影响因素[J].大众标准化,2005,(8)：34-37
[53]朱学栋,朱子彬,唐黎华,等.煤的热解研究II.煤化程度对氢气气氛下热解的影响[J].华东理工大学学报,1998,24(3)：262-266
[54]Wanzl W, Bitter D. Experiments on pyrolysis behaviour of different coals[J]. Fuel Proc Tech, 1990,24:11-17
[55]殷宏彦,王美君,王俊宏,等.钙、钠添加剂对平朔煤热解特性的影响[J].转化利用,2010,3：31-35
[56]赵娅鸿,林建英,常丽萍,等.矿物质对煤热解气化过程中NH3形成的影响[J].环境化学,2004,23(1)：26-30
[57]景晓霞,常丽萍.矿物质对煤中硫氮在热解气化过程中迁移变化的催化作用[J].工业催化,2004,12(10)：13-17
[58]李 文,于惠梅,陈皓侃,等.矿物质脱除对煤中硫在氢气热解中逸出的影响[J].中国矿业大学学报,2003,32(6)：646-649
[59]Wu Z, Sugimoto Y, Kawashima H. The influence of mineral matter and catalyst on nitrogen release during slow pyrolysis of coal and related material:a comparative study[J]. Energy & Fuel, 2002,16(2):451-456
[60]Wu Z, Sugimoto Y, Kawashima H. Effect of demineralization and catalyst addition on N2 formation during coal pyrolysis and on char gasification[J]. Fuel,2003,82(15-17):2057-2064
[61]Matsumoto S, Walker P L Jr. Char gasification in steam at 1123K catalyzed by K, Na, Ca and Fe-effect of H2, H2S and COS[J]. Carbon,1986,24(3):277-283
[62]Semra K. Desulfurization of a Turkish lignite at various gas atmospheres by pyrolysis:effect of mineral matter[J]. Fuel,2003,82(12):1509-1516
[63]赵娅鸿.矿物质对煤热解/气化过程中氮迁移的影响[D].太原：太原理工大学,2003
[64]Tsubouchi N, Ohtsuka Y. Nitrogen release during high temperature pyrolysis of coals and catalytic role of calcium in N2 formation[J]. Fuel,2002,81(18):2335-2342
[65]朱廷钰,刘丽鹏,王洋,等.氧化钙催化煤温和气化研究[J].燃料化学学报,2000,28(1)：36-39
[66]Franklin H D, Cosway R G, Peters W A, et al. Effects of cations on the rapid pyrolysis of a Wyodak subbituminous coal[J]. Ind. Eng. Chem. Proc. Res. Dev,1983,22(1):39-42
[67]Friebel J, Koepsel R F W. The fate of nitrogen during pyrolysis of German low rank coals-a parameter study[J]. Fuel,1999,78(8):923-932
[68]朱廷钰,汤忠,黄戒介,等.煤温和气化特性的热重研究[J].燃料化学学报,1999,27(5)：420-423
[69]刘艳.利用热重分析仪研究煤的催化气化[D].西安：西北大学,2007
[70]赵新法,杨黎燕,石振海.煤中矿物质在气化反应中的催化作用分析[J].煤碳技术,2005,1(24)：103-104