纸浆间歇蒸煮参数优化方法研究
|
摘要
造纸的蒸煮过程将造纸原料变成纸浆,在很大程度上决定了纸张的质量。但同时,蒸煮过程也具有高能耗、高物耗、高污染的“三高”特点。在大力发展资源节约型、环境友好型社会的今天,如何实现蒸煮过程的节能、减排、降耗成为制浆造纸工业的重要课题。本文立足于节能降耗的观点,研究间歇蒸煮过程的参数优化问题,希望能达到保质、高产、节能、降耗的目的。本文的创新工作及贡献包括：
(1)在分析间歇蒸煮过程机理的基础上,建立了关于蒸煮过程的质量、产量和能耗模型。首先,利用支持向量机(SVM)原理,根据造纸工厂的日常数据,建立了关于纸浆kappa值的质量模型。仿真数据表明,该模型准确能地描述蒸煮参数与kappa值之间的数学关系。接着,根据Hatton的经验模型,并利用现场数据回归,建立了有关纸浆得率的产量模型。然后,分析蒸煮过程的能量消耗情况,建立了关于间歇蒸煮过程的蒸汽能耗模型。
(2)本文根据优化模型的特点,提出了一种基于改进遗传算法的间歇蒸煮优化方法,能在满足纸浆质量要求的前提下降低蒸煮过程的能耗和物耗。改进的遗传算法在基本遗传算法的基础上,融入小生境技术和自适应交叉技术,从而增强了整个算法的局部寻优和全局搜索能力。用日常生产数据进行的仿真实验表明,该方法优化效果明显,与现场实际情况相比,节约蒸汽3.52%,节约白液用量17.18%,硫化度减少0.37%。
(3)为了实现真正意义上的多目标优化,本文提出了第二种优化方法—一基于改进的NSGA-II的间歇蒸煮参数多目标优化方法。该种方法的优化模型在前者的基础上,多加入纸浆得率目标,实现在保证纸浆质量的同时,提高纸浆产量,降低蒸煮过程的能耗和物耗。改进的NSGA-II算法在NSGA-II的基础之上,引入一种适应度评价机制,采用自适应交叉变异算子,并加入了外来群体迁入机制,使得该算法相比NSGA-II,能够更好地保证解的收敛性和分布性。将改进的算法应用于间歇蒸煮多目标优化问题,优化效果明显,而且提供多个最优解,具有指导性。
Pulp cooking process turns papermaking feedstock into pulp and determines paper's quality to a great extent. Meanwhile, Pulp cooking process is characteristic of high energy consumption, high materials consumption and high pollution. Today, we are vigorously developing a resource-conserving and environment-friendly society, it is an important task for paper and pulp industry about how to realize saving energy, lowering consumption and reducing pollutants discharge. Considering the viewpoint of energy efficiency, optimization of batch digester parameters was researched. The innovation and contribution of this thesis are as follows:
(1) The mechanism of batch digester was analyzed, and the related batch digester parameter models were established, including quality model, yield model and energy consumption model. Firstly, according to the production data of one papermaking mill, a SVM model about kappa number was developed, which accurately reflect the relationship between kappa number and cooking parameters. Secondly, based on Hatton's empirical model, a model about pulp yield was developed. Thirdly, after analyzing batch digester's steam consumption, a model about batch digester's energy consumption was developed.
(2) Because it is difficult to use SVM model in conventional optimization approach, an improved Genetic Algorithm using niching technology and adaptive crossover technology was presented, which realizes energy conservation and consumption reduction on the premise of guaranteeing the pulp's quality. On the basis of Standard Genetic Algorithm, the improved Genetic Algorithm integrates niching technology and adaptive crossover technology to ensure solution's convergence and distribution, thereby enhance its ability of local and global search. This method was used on the optimization of one papermaking mill, the simulation results showed good performance. It saved 3.52% of steam,17.18% of white liquid dosage and 0.37% of sulfidity, comparing to real production data.
(3) To realize really multi-objective optimization, an improved NSGA-II algorithm for optimization of batch digester parameters method was presented. On the basis of former optimization model, this method adds in one more optimization goal, which is improving the pulp yield. So the purpose of the optimization method is to realize energy conservation and consumption reduction, improve pulp yield on the premise of guaranteeing the pulp's quality. As to the improved NSGA-II algorithm, a fitness assessment method which combines non-dominated front and crowding distance was introduced to describe the individual's quality. In order to generate better individuals, an adaptive crossover and mutation mechanism introduced by Srinivas was employed. Moreover, a foreign group immigration strategy was adopted to avoid falling into local Pareto optimal solution. Simulation results show the improved NSGA-II algorithm can better ensure the convergence and diversity of solutions, compared with NSGA-II. The improved NSGA-II algorithm was used on multi-objective optimization of batch digester parameters, and it received obvious good performance.
(1)在分析间歇蒸煮过程机理的基础上,建立了关于蒸煮过程的质量、产量和能耗模型。首先,利用支持向量机(SVM)原理,根据造纸工厂的日常数据,建立了关于纸浆kappa值的质量模型。仿真数据表明,该模型准确能地描述蒸煮参数与kappa值之间的数学关系。接着,根据Hatton的经验模型,并利用现场数据回归,建立了有关纸浆得率的产量模型。然后,分析蒸煮过程的能量消耗情况,建立了关于间歇蒸煮过程的蒸汽能耗模型。
(2)本文根据优化模型的特点,提出了一种基于改进遗传算法的间歇蒸煮优化方法,能在满足纸浆质量要求的前提下降低蒸煮过程的能耗和物耗。改进的遗传算法在基本遗传算法的基础上,融入小生境技术和自适应交叉技术,从而增强了整个算法的局部寻优和全局搜索能力。用日常生产数据进行的仿真实验表明,该方法优化效果明显,与现场实际情况相比,节约蒸汽3.52%,节约白液用量17.18%,硫化度减少0.37%。
(3)为了实现真正意义上的多目标优化,本文提出了第二种优化方法—一基于改进的NSGA-II的间歇蒸煮参数多目标优化方法。该种方法的优化模型在前者的基础上,多加入纸浆得率目标,实现在保证纸浆质量的同时,提高纸浆产量,降低蒸煮过程的能耗和物耗。改进的NSGA-II算法在NSGA-II的基础之上,引入一种适应度评价机制,采用自适应交叉变异算子,并加入了外来群体迁入机制,使得该算法相比NSGA-II,能够更好地保证解的收敛性和分布性。将改进的算法应用于间歇蒸煮多目标优化问题,优化效果明显,而且提供多个最优解,具有指导性。
Pulp cooking process turns papermaking feedstock into pulp and determines paper's quality to a great extent. Meanwhile, Pulp cooking process is characteristic of high energy consumption, high materials consumption and high pollution. Today, we are vigorously developing a resource-conserving and environment-friendly society, it is an important task for paper and pulp industry about how to realize saving energy, lowering consumption and reducing pollutants discharge. Considering the viewpoint of energy efficiency, optimization of batch digester parameters was researched. The innovation and contribution of this thesis are as follows:
(1) The mechanism of batch digester was analyzed, and the related batch digester parameter models were established, including quality model, yield model and energy consumption model. Firstly, according to the production data of one papermaking mill, a SVM model about kappa number was developed, which accurately reflect the relationship between kappa number and cooking parameters. Secondly, based on Hatton's empirical model, a model about pulp yield was developed. Thirdly, after analyzing batch digester's steam consumption, a model about batch digester's energy consumption was developed.
(2) Because it is difficult to use SVM model in conventional optimization approach, an improved Genetic Algorithm using niching technology and adaptive crossover technology was presented, which realizes energy conservation and consumption reduction on the premise of guaranteeing the pulp's quality. On the basis of Standard Genetic Algorithm, the improved Genetic Algorithm integrates niching technology and adaptive crossover technology to ensure solution's convergence and distribution, thereby enhance its ability of local and global search. This method was used on the optimization of one papermaking mill, the simulation results showed good performance. It saved 3.52% of steam,17.18% of white liquid dosage and 0.37% of sulfidity, comparing to real production data.
(3) To realize really multi-objective optimization, an improved NSGA-II algorithm for optimization of batch digester parameters method was presented. On the basis of former optimization model, this method adds in one more optimization goal, which is improving the pulp yield. So the purpose of the optimization method is to realize energy conservation and consumption reduction, improve pulp yield on the premise of guaranteeing the pulp's quality. As to the improved NSGA-II algorithm, a fitness assessment method which combines non-dominated front and crowding distance was introduced to describe the individual's quality. In order to generate better individuals, an adaptive crossover and mutation mechanism introduced by Srinivas was employed. Moreover, a foreign group immigration strategy was adopted to avoid falling into local Pareto optimal solution. Simulation results show the improved NSGA-II algorithm can better ensure the convergence and diversity of solutions, compared with NSGA-II. The improved NSGA-II algorithm was used on multi-objective optimization of batch digester parameters, and it received obvious good performance.
引文
[1]陈嘉翔,李元禄等.制浆原理与工程[M].北京：中国轻工业出版社,1992：91-96
[2]陆浩.硫酸盐制浆蒸煮过程的建模与控制.杭州,浙江大学,2003
[3]单鸿亮.间歇蒸煮过程的模型辨识与监控.杭州,浙江大学,2004
[4]张建.提高制浆蒸煮过程纸浆Kappa值软测量精度的研究.广东,华南理工大学,2004
[5]陈诗隆.微波预处理在制浆蒸煮工艺中的应用研究.武汉,湖北工业大学,2007
[6]福建林学院主编.木材制浆工艺学[M].北京：中国林业出版社,1986,39-41
[7]单鸿亮,王文海,孙优贤.间歇蒸煮过程软测量建模综述[J].中国造纸学报,2003,18(2),195—200
[8]Maciel Filho, R. Aguiar, H. C. Modeling and Analysis of a Continuous Indestrial Kraft Pulping Digester [Z].50th Canadian Engineering. Conference, Montreal, October 15-18,2000.http://www.csche 2000.ca/Abstracts/abstractss 123.pdf
[9]严文俊,孙优贤.间歇蒸煮过程的硬度控制策略.中国造纸学报,1993,8：25
[10]罗琪,刘焕彬,朱学峰.木片硫酸盐法蒸煮过程的建模.中国学术期刊文摘,1998(1)：1
[11]李向阳,朱学峰.硫酸盐法蒸煮过程卡伯值预测模型的研究与应用.广东造纸,2000(5)：23
[12]金福江,王慧,李平.间歇蒸煮过程的分层多目标优化[J].中国造纸学报,2002,17(1)：86-89
[13]Chimmiri V, Kota Gangiah. Dynamic modeling and optimal state estimation using extended kalman filter for a kraft pulping digester. American Chemical Society, 1992,31:848
[14]Lee J H, Data A K. No linear inferential control of pulp digesters.Process System Engineering,1994,40(1):50
[15]Datta AK, Lee J H. Model-based monitoring and control ofbatchpulp digester.Proceeding of A. C. C.,1994,6:500
[16]Kesavan P, Lee J H. Partial least(PLS) based monitoring and control ofbatch digesters. Journal of Process Contro1,2000,10(2) 229
[17]吴新生,刘焕彬,谢益民等.基于人工神经网络方法的间歇硫酸盐法蒸煮纸浆硬度的H-因子控制[J].广东造纸,1998,2：5
[18]朱学峰,黄道平,刘焕彬.间歇纸浆蒸煮终点预测方法.计算机与应用化学.2001,18(2)：17
[19]Helena Cristina,I.L.Aguiar,Rubens MacielFilho. Modeling and Optimization of Pulp and Paper using Neutrual Networks [J]. Computer chem.Engng.1998,22: 981-984
[20]于玲,祝和云.神经元网络用于纸浆的高锰酸钾值(P值)的软测量.自动化理论、技术与应用(第四卷)[A].1997：379
[21]罗琪,刘焕彬.人工神经网络在硫酸盐间歇蒸煮过程纸浆硬度建模中的应用[J].广东造纸,1997(5-6)：94,114
[22]Belarbi K, Bettou K, Mezaache A. Fuzzy neural networks for estimation and fuzzy controller design:simulation study for a pulp batch digeater. Journal of Process Control,2000,10(1)35
[23]Musavi M T, Domnisoru C, Smith G, et al. A neuron fuzzy system for prediction of pulp digester K-number.International Joint Conference on Neural Networks.1999.4253
[24]Nomikos P, MacGregor J F. Monitoring of bacth processes using Multi-way Principal Component Analysis J. AICHE,1994,40:1361
[25]MacGregor J F, Jaeckle C, et aLMornitoring and Diagnosis of process operating performance by Multi-block Partial Least Sauares methods with application to low density polyethylene production. J. AICHE,1994,40:826
[26]李友明,H-m.Chang,H. Jameel硫化度对RDH蒸煮脱木素选择性的影响[J].中国造纸学报,1999,4：1-5
[27]刘秉钺,李淋,杨大成.稻草亚铵法优化蒸煮工艺条件[J].黑龙江造纸,2003,4：12-14
[28]何忠良,何广钊.低浓亚硫酸氢盐法蒸煮竹浆[J].Paper Science & Technology, 2001,20(2):49-51
[29]肖兰,王慧,李平.基于过程建模与优化技术的清洁生产策略[J].浙江大学学报(自然科学版),1998,5：777-780
[30]肖兰,王慧,李平.基于过程建模与优化技术的清洁生产策略[J].浙江大学学报 (自然科学版),1998,5：777—780
[31]Helena Cristina,I.L.Aguiar,Rubens MacielFilho. Neural network and hybrid mod el-a discussion about different modeling techniques to predict pulping degree with industrial data [J]. Chemical Engineering Science.2001,56:565-570
[32]鄢烈祥,聂青.神经网络降维分析法用于制浆蒸煮工艺条件的优化[J].中国造纸学报,2000,15：10-13
[33]许向阳,于玲,祝和云,孙优贤等.间歇蒸煮过程计算机优化控制系统[J].中国造纸学报,2000,15：98-102
[34]金福江,王慧,李平.间歇蒸煮过程的分层多目标优化[J].中国造纸学报,2002,17(1)：86-89
[35]SIDRAK, YL. Model-based optimization of kamyr digester operation.. TECH ASS NPULP PAPER IND INC,TAPPI JOURNAL 1998,78:93-98
[36]杨春节,何川,宋执环.基于近红外光谱与支持向量机的纸浆卡伯值在线测量[J].光谱学与光谱分析,2008,28(8)：1795
[37]杜树新,吴铁军.用于回归估计的支持向量机方法[J].系统仿真学报,2003,15(11)：1580-1586
[38]白鹏,张喜斌,张斌等.支持向量机理论及工程应用实例[M].西安：西安电子科技大学出版社,2008
[39]唐发明.基于统计学习理论的支持向量机算法研究.武汉,华中科技大学,2005
[40]Yorston, F.H.,& Liebergott, N.(1965). Correlation of the rate of sulphite pulping with temperature and pressure. Pulp and Paper Magazine of Cananda,66(5),272
[41]Hagberg, B.,&Schoon,.N.H.(1973). Kinetical aspects of the acid sulfite cooking process. Part 1:Rates of dissolution of lignin and hemicelluloses. Svensk Papperstidning,76(15),127-130
[42]Philip de Vaal, Carl Sandrock. Control of a Batch pulp digester using a Simplified Mechanistic Model to predict Degree of Polymerisation[J]. Computer and Science Engineering.2007(31):1222-1230
[43]Francis, J. Doyle III, Ferhan, Kayihan. Reaction Profile Control of the Continious Pulp Digester[J]. Chemical Engineering Science 1994.54:2679-2688
[44]K. Belarbi, K. Bettou, A. Mezaache. Fuzzy Neural Networks for Estimation and Fuzzy Controller Design-simulation Study For a Pulp Batch Digester[J]. Journal of Process Control,2000,10:35-41
[45]李向阳,朱学峰,刘焕彬.工业过程混合建模方法研究及应用[J].计算机工程与应用.2001(3)：31-35
[46]郑启富.制浆蒸煮过程卡伯值测定的研究[J].中国造纸学报,2002,17(2)：92-93
[47]鄢烈祥,聂青.神经网络降维分析法用于制浆蒸煮工艺条件的优化[J].中国造纸学报,2000,15：10-13
[48]吴新生,谢益民,詹怀宇.人工神经网络方法在蒸煮工艺条件优化中的应用[J]. Paper Science & Technology,2005,24(2):25-27
[49]肖兰,王慧,李平.基于过程建模与优化技术的清洁生产策略[J].浙江大学学报(自然科学版),1998,5：777-780
[50]王慧,肖兰,李平.面向清洁生产的制浆过程建模与优化方法.中国造纸学报.2000,15：88-92
[51]金福江.制浆生产蒸煮过程多目标优化控制[J].华侨大学学报(自然科学版),2001,22(4)：422-427
[52]Bagley, J. D. The Behavior of Adaptive Systems Which Employ Genetic and Correlation Algorithm. Dissertation Abtracts International,1967,28(12)
[53]Holland J H. Adaption in Natural and Artificial Systems. MI:University of Michigan Press.1975
[54]De Jong K A. The Analysis of the Behavior of a Class of Genetic Adaptive Systems [D]. Depart of Computer and Communication Sciences, University of Michigan, Ann Arbor,1975
[55]Cavicchio D J. Adaptive search using simulated evolution[D]. Ann Arbor: University of Michigan,1970
[56]Cavicchio D J. Reproductive adaptive plans[C]//Proc of the ACM 1972 Annual Conf Boston:Association of Commuting Machinery,1972:1-11
[57]D E Goldberg. Genetic Algorithm with Sharing for multimodal Function Optimization [M]//Grefenstette J J. Proceeding of the Second International Conference on Genetic Algorithm. Hillscale:Lawrence Erlbaum Associates,1987: 41-49
[58]Bethke, A.D. Genetic Algorithm as Function Optimizers (Ph. D. dissertation). University of Michigan, No.8106101,1980
[59]Smith, S. E. A Learning System based on Genetic Adaptive Algorithms(Ph. D. dissertation). University of Pittsburgh,1980
[60]Goldberg D E. Genetic Algorithms in Search Optimization and Machine Learning. Addison Wesley Publishing Company,1989
[61]Davis, L.,(ed) Handbook of Genetic Algorithms. Van Nostrand Reingold, New York,1991
[62]Grefenstette, J. J. Optimization of Control Parameters for Genetic Algorithms. IEEE Transaction on Systems, Man, and Cybernetics,1986,16(1):122-128
[63]Bauer, R J. Genetic Algorithm and Investment Strategies. New York:John Wiley & Sons, Inc.,1994
[64]M. Srinivas, L, M. Patnaik. Adaptive Probabilities of Crossover and Mutation in Genetic Algorithms [J].IEEE Trans on System, Man, and Cybemetics,1994,24 (4): 656-667
[65]Koza, J.R. Genetic Programming 1.Cambridge, MA:The MIT Press,1992
[66]Koza, J.R. Genetic Programming 2. Cambridge, MA:The MIT Press,1994
[67]陆青,梁昌勇,杨善林,张俊岭.面向多模态函数优化的自适应小生境遗传算法.[J].模式识别与人工智能,2005,22(1)91-100
[68]陈娟,徐立鸿.动态小生境遗传算法在多模函数优化中的应用.[J].同济大学学报(自然科学版),2006,34(5)：684-688
[69]朱筱蓉,张兴华.基于小生境遗传算法的多峰函数全局优化研究.[J].南京工业大学学报,2006,28(5)：39-43
[70]黄聪明,陈湘秀.小生境遗传算法的改进.[J].北京理工大学学报,2004,24(8)：675-678
[71]李敏强,寇纪松,林丹等.遗传算法的基本理论与应用[M].北京：科学出版社,2002
[72]雷英杰,张善文,李续武,周创明MATLAB遗传算法工具箱及其应用.[M].西安：西安电子科技大学出版社,2005
[73]郑金华.多目标进化算法及其应用[M].北京：科学出版社,2006
[74]崔逊学.多目标进化算法及其应用[M].北京：国防工业出版社,2008
[75]Schaffer J D. Multiple Objective Optimization with Vector Evaluated Genetic Algorithms. Proceedings of an International Conference on Genetic Algorithms and Yheir Applications,1985
[76]FonsecaC M,Fleming P J. Genetic Algorithm for Multiobjective Optimization: Fomulation,discussion and Genetic Algorithms, San Mateo, California,1993
[77]Jeffrey Horn, Nicholas Nafpliotis, David E. Goldberg. A niched pareto genetic algorithm for multiobjetive optimization [J]. Proceeding of the first IEEE conference on Evolutionary Computation.82-87
[78]Srinivas N, Deb K. Multiobjective Optimization using Nondominated Sorting in Genetic Algorithms. Evo lutionary Computation,1994,3221-248
[79]Deb Kalyanmoy, Associate Member. A fast and elitist multi-objective genetic algorithm:NSGA-II [J]. IEEE Transaction on Evolutionary Computation,2002, 6(2):182-197
[80]Zitzler E,M Laumans, L Thiele. SPEA2:Improving the strength pareto evolutionary algorithm for multiobjetive optimization. EUROGEN 2001-Evolutionary Methods for Design Optimization and Control with Applications to Industrial Problems,2001
[81]Joshua D. Knowles, David W. Come. Approximating the nondominated front using the Pareto archived evolution strategy. Evolutionary Computation 2000,8(2): 149-172
[82]David W. Come, Joshua D. Knowles, Martin J. Oates. The Pareto envelope-based selection algorithm for multiobjective optimization Proceeding of the Parallel Problem Solving from Nature VT Conference.2000.839-848
[83]Coello Coello C A, Pulido GT. A Micro-Genetic Algorithm for Multiobjective Optimization First International Conference on Evolutionary Multi-Criterion Optimization,2001
[84]毕书东.多目标遗传算法的研究[D].安徽,安徽理工大学,2007
[85]阮宏博.基于遗传算法的工程多目标优化研究[D].大连,大连理工大学,2007
[86]李红梅.多目标优化演化算法[D].广州,中山大学,2007
[2]陆浩.硫酸盐制浆蒸煮过程的建模与控制.杭州,浙江大学,2003
[3]单鸿亮.间歇蒸煮过程的模型辨识与监控.杭州,浙江大学,2004
[4]张建.提高制浆蒸煮过程纸浆Kappa值软测量精度的研究.广东,华南理工大学,2004
[5]陈诗隆.微波预处理在制浆蒸煮工艺中的应用研究.武汉,湖北工业大学,2007
[6]福建林学院主编.木材制浆工艺学[M].北京：中国林业出版社,1986,39-41
[7]单鸿亮,王文海,孙优贤.间歇蒸煮过程软测量建模综述[J].中国造纸学报,2003,18(2),195—200
[8]Maciel Filho, R. Aguiar, H. C. Modeling and Analysis of a Continuous Indestrial Kraft Pulping Digester [Z].50th Canadian Engineering. Conference, Montreal, October 15-18,2000.http://www.csche 2000.ca/Abstracts/abstractss 123.pdf
[9]严文俊,孙优贤.间歇蒸煮过程的硬度控制策略.中国造纸学报,1993,8：25
[10]罗琪,刘焕彬,朱学峰.木片硫酸盐法蒸煮过程的建模.中国学术期刊文摘,1998(1)：1
[11]李向阳,朱学峰.硫酸盐法蒸煮过程卡伯值预测模型的研究与应用.广东造纸,2000(5)：23
[12]金福江,王慧,李平.间歇蒸煮过程的分层多目标优化[J].中国造纸学报,2002,17(1)：86-89
[13]Chimmiri V, Kota Gangiah. Dynamic modeling and optimal state estimation using extended kalman filter for a kraft pulping digester. American Chemical Society, 1992,31:848
[14]Lee J H, Data A K. No linear inferential control of pulp digesters.Process System Engineering,1994,40(1):50
[15]Datta AK, Lee J H. Model-based monitoring and control ofbatchpulp digester.Proceeding of A. C. C.,1994,6:500
[16]Kesavan P, Lee J H. Partial least(PLS) based monitoring and control ofbatch digesters. Journal of Process Contro1,2000,10(2) 229
[17]吴新生,刘焕彬,谢益民等.基于人工神经网络方法的间歇硫酸盐法蒸煮纸浆硬度的H-因子控制[J].广东造纸,1998,2：5
[18]朱学峰,黄道平,刘焕彬.间歇纸浆蒸煮终点预测方法.计算机与应用化学.2001,18(2)：17
[19]Helena Cristina,I.L.Aguiar,Rubens MacielFilho. Modeling and Optimization of Pulp and Paper using Neutrual Networks [J]. Computer chem.Engng.1998,22: 981-984
[20]于玲,祝和云.神经元网络用于纸浆的高锰酸钾值(P值)的软测量.自动化理论、技术与应用(第四卷)[A].1997：379
[21]罗琪,刘焕彬.人工神经网络在硫酸盐间歇蒸煮过程纸浆硬度建模中的应用[J].广东造纸,1997(5-6)：94,114
[22]Belarbi K, Bettou K, Mezaache A. Fuzzy neural networks for estimation and fuzzy controller design:simulation study for a pulp batch digeater. Journal of Process Control,2000,10(1)35
[23]Musavi M T, Domnisoru C, Smith G, et al. A neuron fuzzy system for prediction of pulp digester K-number.International Joint Conference on Neural Networks.1999.4253
[24]Nomikos P, MacGregor J F. Monitoring of bacth processes using Multi-way Principal Component Analysis J. AICHE,1994,40:1361
[25]MacGregor J F, Jaeckle C, et aLMornitoring and Diagnosis of process operating performance by Multi-block Partial Least Sauares methods with application to low density polyethylene production. J. AICHE,1994,40:826
[26]李友明,H-m.Chang,H. Jameel硫化度对RDH蒸煮脱木素选择性的影响[J].中国造纸学报,1999,4：1-5
[27]刘秉钺,李淋,杨大成.稻草亚铵法优化蒸煮工艺条件[J].黑龙江造纸,2003,4：12-14
[28]何忠良,何广钊.低浓亚硫酸氢盐法蒸煮竹浆[J].Paper Science & Technology, 2001,20(2):49-51
[29]肖兰,王慧,李平.基于过程建模与优化技术的清洁生产策略[J].浙江大学学报(自然科学版),1998,5：777-780
[30]肖兰,王慧,李平.基于过程建模与优化技术的清洁生产策略[J].浙江大学学报 (自然科学版),1998,5：777—780
[31]Helena Cristina,I.L.Aguiar,Rubens MacielFilho. Neural network and hybrid mod el-a discussion about different modeling techniques to predict pulping degree with industrial data [J]. Chemical Engineering Science.2001,56:565-570
[32]鄢烈祥,聂青.神经网络降维分析法用于制浆蒸煮工艺条件的优化[J].中国造纸学报,2000,15：10-13
[33]许向阳,于玲,祝和云,孙优贤等.间歇蒸煮过程计算机优化控制系统[J].中国造纸学报,2000,15：98-102
[34]金福江,王慧,李平.间歇蒸煮过程的分层多目标优化[J].中国造纸学报,2002,17(1)：86-89
[35]SIDRAK, YL. Model-based optimization of kamyr digester operation.. TECH ASS NPULP PAPER IND INC,TAPPI JOURNAL 1998,78:93-98
[36]杨春节,何川,宋执环.基于近红外光谱与支持向量机的纸浆卡伯值在线测量[J].光谱学与光谱分析,2008,28(8)：1795
[37]杜树新,吴铁军.用于回归估计的支持向量机方法[J].系统仿真学报,2003,15(11)：1580-1586
[38]白鹏,张喜斌,张斌等.支持向量机理论及工程应用实例[M].西安：西安电子科技大学出版社,2008
[39]唐发明.基于统计学习理论的支持向量机算法研究.武汉,华中科技大学,2005
[40]Yorston, F.H.,& Liebergott, N.(1965). Correlation of the rate of sulphite pulping with temperature and pressure. Pulp and Paper Magazine of Cananda,66(5),272
[41]Hagberg, B.,&Schoon,.N.H.(1973). Kinetical aspects of the acid sulfite cooking process. Part 1:Rates of dissolution of lignin and hemicelluloses. Svensk Papperstidning,76(15),127-130
[42]Philip de Vaal, Carl Sandrock. Control of a Batch pulp digester using a Simplified Mechanistic Model to predict Degree of Polymerisation[J]. Computer and Science Engineering.2007(31):1222-1230
[43]Francis, J. Doyle III, Ferhan, Kayihan. Reaction Profile Control of the Continious Pulp Digester[J]. Chemical Engineering Science 1994.54:2679-2688
[44]K. Belarbi, K. Bettou, A. Mezaache. Fuzzy Neural Networks for Estimation and Fuzzy Controller Design-simulation Study For a Pulp Batch Digester[J]. Journal of Process Control,2000,10:35-41
[45]李向阳,朱学峰,刘焕彬.工业过程混合建模方法研究及应用[J].计算机工程与应用.2001(3)：31-35
[46]郑启富.制浆蒸煮过程卡伯值测定的研究[J].中国造纸学报,2002,17(2)：92-93
[47]鄢烈祥,聂青.神经网络降维分析法用于制浆蒸煮工艺条件的优化[J].中国造纸学报,2000,15：10-13
[48]吴新生,谢益民,詹怀宇.人工神经网络方法在蒸煮工艺条件优化中的应用[J]. Paper Science & Technology,2005,24(2):25-27
[49]肖兰,王慧,李平.基于过程建模与优化技术的清洁生产策略[J].浙江大学学报(自然科学版),1998,5：777-780
[50]王慧,肖兰,李平.面向清洁生产的制浆过程建模与优化方法.中国造纸学报.2000,15：88-92
[51]金福江.制浆生产蒸煮过程多目标优化控制[J].华侨大学学报(自然科学版),2001,22(4)：422-427
[52]Bagley, J. D. The Behavior of Adaptive Systems Which Employ Genetic and Correlation Algorithm. Dissertation Abtracts International,1967,28(12)
[53]Holland J H. Adaption in Natural and Artificial Systems. MI:University of Michigan Press.1975
[54]De Jong K A. The Analysis of the Behavior of a Class of Genetic Adaptive Systems [D]. Depart of Computer and Communication Sciences, University of Michigan, Ann Arbor,1975
[55]Cavicchio D J. Adaptive search using simulated evolution[D]. Ann Arbor: University of Michigan,1970
[56]Cavicchio D J. Reproductive adaptive plans[C]//Proc of the ACM 1972 Annual Conf Boston:Association of Commuting Machinery,1972:1-11
[57]D E Goldberg. Genetic Algorithm with Sharing for multimodal Function Optimization [M]//Grefenstette J J. Proceeding of the Second International Conference on Genetic Algorithm. Hillscale:Lawrence Erlbaum Associates,1987: 41-49
[58]Bethke, A.D. Genetic Algorithm as Function Optimizers (Ph. D. dissertation). University of Michigan, No.8106101,1980
[59]Smith, S. E. A Learning System based on Genetic Adaptive Algorithms(Ph. D. dissertation). University of Pittsburgh,1980
[60]Goldberg D E. Genetic Algorithms in Search Optimization and Machine Learning. Addison Wesley Publishing Company,1989
[61]Davis, L.,(ed) Handbook of Genetic Algorithms. Van Nostrand Reingold, New York,1991
[62]Grefenstette, J. J. Optimization of Control Parameters for Genetic Algorithms. IEEE Transaction on Systems, Man, and Cybernetics,1986,16(1):122-128
[63]Bauer, R J. Genetic Algorithm and Investment Strategies. New York:John Wiley & Sons, Inc.,1994
[64]M. Srinivas, L, M. Patnaik. Adaptive Probabilities of Crossover and Mutation in Genetic Algorithms [J].IEEE Trans on System, Man, and Cybemetics,1994,24 (4): 656-667
[65]Koza, J.R. Genetic Programming 1.Cambridge, MA:The MIT Press,1992
[66]Koza, J.R. Genetic Programming 2. Cambridge, MA:The MIT Press,1994
[67]陆青,梁昌勇,杨善林,张俊岭.面向多模态函数优化的自适应小生境遗传算法.[J].模式识别与人工智能,2005,22(1)91-100
[68]陈娟,徐立鸿.动态小生境遗传算法在多模函数优化中的应用.[J].同济大学学报(自然科学版),2006,34(5)：684-688
[69]朱筱蓉,张兴华.基于小生境遗传算法的多峰函数全局优化研究.[J].南京工业大学学报,2006,28(5)：39-43
[70]黄聪明,陈湘秀.小生境遗传算法的改进.[J].北京理工大学学报,2004,24(8)：675-678
[71]李敏强,寇纪松,林丹等.遗传算法的基本理论与应用[M].北京：科学出版社,2002
[72]雷英杰,张善文,李续武,周创明MATLAB遗传算法工具箱及其应用.[M].西安：西安电子科技大学出版社,2005
[73]郑金华.多目标进化算法及其应用[M].北京：科学出版社,2006
[74]崔逊学.多目标进化算法及其应用[M].北京：国防工业出版社,2008
[75]Schaffer J D. Multiple Objective Optimization with Vector Evaluated Genetic Algorithms. Proceedings of an International Conference on Genetic Algorithms and Yheir Applications,1985
[76]FonsecaC M,Fleming P J. Genetic Algorithm for Multiobjective Optimization: Fomulation,discussion and Genetic Algorithms, San Mateo, California,1993
[77]Jeffrey Horn, Nicholas Nafpliotis, David E. Goldberg. A niched pareto genetic algorithm for multiobjetive optimization [J]. Proceeding of the first IEEE conference on Evolutionary Computation.82-87
[78]Srinivas N, Deb K. Multiobjective Optimization using Nondominated Sorting in Genetic Algorithms. Evo lutionary Computation,1994,3221-248
[79]Deb Kalyanmoy, Associate Member. A fast and elitist multi-objective genetic algorithm:NSGA-II [J]. IEEE Transaction on Evolutionary Computation,2002, 6(2):182-197
[80]Zitzler E,M Laumans, L Thiele. SPEA2:Improving the strength pareto evolutionary algorithm for multiobjetive optimization. EUROGEN 2001-Evolutionary Methods for Design Optimization and Control with Applications to Industrial Problems,2001
[81]Joshua D. Knowles, David W. Come. Approximating the nondominated front using the Pareto archived evolution strategy. Evolutionary Computation 2000,8(2): 149-172
[82]David W. Come, Joshua D. Knowles, Martin J. Oates. The Pareto envelope-based selection algorithm for multiobjective optimization Proceeding of the Parallel Problem Solving from Nature VT Conference.2000.839-848
[83]Coello Coello C A, Pulido GT. A Micro-Genetic Algorithm for Multiobjective Optimization First International Conference on Evolutionary Multi-Criterion Optimization,2001
[84]毕书东.多目标遗传算法的研究[D].安徽,安徽理工大学,2007
[85]阮宏博.基于遗传算法的工程多目标优化研究[D].大连,大连理工大学,2007
[86]李红梅.多目标优化演化算法[D].广州,中山大学,2007