提高制浆蒸煮过程纸浆Kappa值软测量精度的研究
|
摘要
蒸煮过程是制浆造纸工业中的一个重要环节,也是一个复杂的物理化学过程。纸浆的Kappa 值是蒸煮过程中最重要的一个质量指标,控制好纸浆的Kappa 值,不但可以稳定纸浆质量,而且有助于减少蒸汽和化学品的消耗,减少环境污染,提高生产效益。要控制好纸浆的卡伯值,需要对其进行在线测量或者估计,但是至今国内外尚未开发出准确、可靠、价廉、易维护的蒸煮过程纸浆Kappa 值在线、测量仪表,因此研究纸浆卡伯值的软测量技术具有很大的理论意义和实用价值。在前期的研究中,我们已经在Kappa 值的软测量方面已经进行了深入的研究,所获得的技术成果在实际应用中取得了一定的效果,但是还需要进一步提高其软测量精度。
本论文从现有蒸煮过程卡伯值软测量研究的不足和一些尚未进行研究的技术、方法的角度出发,通过增加过程信息量、采用简单有效的数据预处理方法、分析复杂工况下的升温曲线、采用外推性能好的新型建模方法及建立优势互补的混合模型等方法来提高蒸煮过程纸浆Kappa 值软测量的精度,并且在软测量建模过程中综合利用各种理论、方法,充分挖掘数据中的有用信息,以达到提高软测量精度的目的。
本论文通过深入、系统的研究,取得了以下有益的结果:
1. 提出了一种新的基于双取样点的Kappa 值软测量模型。新模型同时利用了大 量脱木素起始阶段和残余脱木素起始阶段两个取样点的有效碱浓度,增加了 过程的信息量,可以更好地跟踪蒸煮过程Kappa 值的变化,特别是在一些复 杂工况(如闷锅)下,新模型的预测精度要明显优于原有的Kappa 值软测量 模型。另外,双取样点的采用,也减小了有效碱浓度的人工测量误差对Kappa 值预测精度的影响,从而提高了模型的鲁棒性;
2. 针对工厂实际建模数据往往污染严重的问题,提出了一种基于模型的建模数 据可靠性评价方法。该方法可以利用蕴含在模型中的机理知识和经验知识来 对建模数据进行可靠性评价,并将评价结果应用于建模过程。与传统的基于 数理统计的数据预处理方法不同,该方法不是盲目地将识别出的异常数据加 以剔出,而是对不同质量的数据给予不同的可靠性评价权值,这在一定程度 上克服了由于盲目删除异常数据,而造成建模精度没有提高反而下降的问 题。论文还将基于模型的数据评价方法和最小二乘建模方法结合起来,提出 了基于数据评价的加权软测量建模方法,从而使得到的软测量模型在一定的 误差数据存在下,也能保持较好的预测精度。此外,虽然该方法是从数据预 处理的角度提出来的,但利用该方法,也可以进行过程工况的识别和划分。
Cooking process is an important stage in pulp and papermaking industrial. It isalso a very complicated physical and chemical process. Kappa number is the mostimportant quality index of cooking process. Good control of Kappa number is the keyto stabilize the quality of paper pulp. The steady Kappa number is also helpful todecrease the consumption of stream and chemical products, to decrease theenvironment pollution and enhance production efficiency. In order to control theKappa number of pulp, it must be measured or estimated online. But until now theKappa number online measurement instrument, which is precision, dependable, cheapand easy-to-maintain has not been developed throughout inland and overseas.Therefore, it is significant in theory and application to develop soft sensingtechnology of Kappa number in cooking process. In the former research, we havedone a deeply work on the soft sensing field of Kappa number. The results we gothave achieved certain efficiency in real applications, but farther research is needed toimprove the prediction precision.
This dissertation began the research work from the shortcomins of formerresearchs or the angle that is never concerned. By adding process information, usingsimple and effective data preprocessing method, analyzing temperature-rising curvesin complexy production condition, using new modeling method with goodgeneralization ability and building a hybrid model with better performance, some newmethods were put forward to improve prediction precision of Kappa number. In orderto reach the goal, different kinds of theorys and methods should be integrated to digout useful information from the original data.
This dissertation concentrated on the research work listed below and achievedsome creative results:
1) Based on the technical analysis and the condition of actual product process of thebatch pulp cooking, the dissertation points out the limits of single model for the wholecooking process, since the process of delignification is linearization for differentphase. A new subsection model is presented based on the simplified Hatton model.
2) After analyzing the composing of prediction error of soft sensing model, a methodof abnormal data discovery for data processing of Kappa number soft sensing ispresented. The new data processing method digs out incompatible data based on dataclustering and mechanism analysis, as well as finds out the outlier data by regressionanalyzing and statistical analysis. It also can explain the impact of abnormal data on
本论文从现有蒸煮过程卡伯值软测量研究的不足和一些尚未进行研究的技术、方法的角度出发,通过增加过程信息量、采用简单有效的数据预处理方法、分析复杂工况下的升温曲线、采用外推性能好的新型建模方法及建立优势互补的混合模型等方法来提高蒸煮过程纸浆Kappa 值软测量的精度,并且在软测量建模过程中综合利用各种理论、方法,充分挖掘数据中的有用信息,以达到提高软测量精度的目的。
本论文通过深入、系统的研究,取得了以下有益的结果:
1. 提出了一种新的基于双取样点的Kappa 值软测量模型。新模型同时利用了大 量脱木素起始阶段和残余脱木素起始阶段两个取样点的有效碱浓度,增加了 过程的信息量,可以更好地跟踪蒸煮过程Kappa 值的变化,特别是在一些复 杂工况(如闷锅)下,新模型的预测精度要明显优于原有的Kappa 值软测量 模型。另外,双取样点的采用,也减小了有效碱浓度的人工测量误差对Kappa 值预测精度的影响,从而提高了模型的鲁棒性;
2. 针对工厂实际建模数据往往污染严重的问题,提出了一种基于模型的建模数 据可靠性评价方法。该方法可以利用蕴含在模型中的机理知识和经验知识来 对建模数据进行可靠性评价,并将评价结果应用于建模过程。与传统的基于 数理统计的数据预处理方法不同,该方法不是盲目地将识别出的异常数据加 以剔出,而是对不同质量的数据给予不同的可靠性评价权值,这在一定程度 上克服了由于盲目删除异常数据,而造成建模精度没有提高反而下降的问 题。论文还将基于模型的数据评价方法和最小二乘建模方法结合起来,提出 了基于数据评价的加权软测量建模方法,从而使得到的软测量模型在一定的 误差数据存在下,也能保持较好的预测精度。此外,虽然该方法是从数据预 处理的角度提出来的,但利用该方法,也可以进行过程工况的识别和划分。
Cooking process is an important stage in pulp and papermaking industrial. It isalso a very complicated physical and chemical process. Kappa number is the mostimportant quality index of cooking process. Good control of Kappa number is the keyto stabilize the quality of paper pulp. The steady Kappa number is also helpful todecrease the consumption of stream and chemical products, to decrease theenvironment pollution and enhance production efficiency. In order to control theKappa number of pulp, it must be measured or estimated online. But until now theKappa number online measurement instrument, which is precision, dependable, cheapand easy-to-maintain has not been developed throughout inland and overseas.Therefore, it is significant in theory and application to develop soft sensingtechnology of Kappa number in cooking process. In the former research, we havedone a deeply work on the soft sensing field of Kappa number. The results we gothave achieved certain efficiency in real applications, but farther research is needed toimprove the prediction precision.
This dissertation began the research work from the shortcomins of formerresearchs or the angle that is never concerned. By adding process information, usingsimple and effective data preprocessing method, analyzing temperature-rising curvesin complexy production condition, using new modeling method with goodgeneralization ability and building a hybrid model with better performance, some newmethods were put forward to improve prediction precision of Kappa number. In orderto reach the goal, different kinds of theorys and methods should be integrated to digout useful information from the original data.
This dissertation concentrated on the research work listed below and achievedsome creative results:
1) Based on the technical analysis and the condition of actual product process of thebatch pulp cooking, the dissertation points out the limits of single model for the wholecooking process, since the process of delignification is linearization for differentphase. A new subsection model is presented based on the simplified Hatton model.
2) After analyzing the composing of prediction error of soft sensing model, a methodof abnormal data discovery for data processing of Kappa number soft sensing ispresented. The new data processing method digs out incompatible data based on dataclustering and mechanism analysis, as well as finds out the outlier data by regressionanalyzing and statistical analysis. It also can explain the impact of abnormal data on
引文
1. 中国造纸业的发展并未超速,http://www.papercn.com/news/daynews/ /03082602.htm.
2. 中国造纸工业的“十五规划”.
3. Marjatta Ollila.卡伯值与亮度的测量及其重要性.刘新兵译.中国造纸.1998, (5):57-64
4. Eglis Kubulnieks et al.The STFI OPTI-Kappa analyzer —applications and accuracy.Tappi Journal.1987,38:11
5. L.Agneus et al . Optimal process control with on-line Kappa number analysis.Pulp and Paper Canada.1992,93:2
6. Richard J. et al.Advanced sensors and control for the pulping and bleaching process.Appita Journal.1998,51(6):412
7. 闫东波. 纸浆卡伯值光学在线传感器的研究[D]. 华南理工大学博士学位论文,2000:1-19
8. 俞金寿, 刘爱伦等编. 软测量技术及其在石油化工中的应用[M]. 北京: 化学工业出版社, 2000
9. C.B.Brosilow. Inferential Control of process control, AIChE J 1978,24(3):475-484
10. MacVoy. T J. Comtemplative stance for chemical process. Automatica, 1992, 28(2): 441-442
11. Kerr A J. The kinetics of kraft pulping-batch digester control[J]. Tappi,1976, 59: 89
12. E.W.马科隆.T.M.格雷斯编.最新碱法制浆技术[M].曹邦威译.北京:中国轻工业出版社,1999:48-49
13. Hatton J V. The Potential of Process Control in Kraft Pulping of Hardwoods Relative to Softwoods [J]. Tappi. 1976,59(8):48
14. Lin, C.P., Mao, M.Y. and Jane, C.Y., Tappi, 1978,61(2):72
15. Chari, N.C.S. Integrated Control System for Batch Digester Control [J]. Tappi. 1973,56(7):65
16. S.Noreus, G. Wallin, T.Olsson, etl. Computer control of batch digesters. Pulp Paper Mag. Can. 1974, 75(5):T204
17. Tasman, J.E., Tappi, 1981, 64(3):175-176
18. H.C.Kim, X.Shen, M.Rao, Quality prediction by neural network for pulp and paper processes. CCECE/CCGEI, 1993:104-107
19. Ming Rao, Jean Corbin, Qun Wang.Soft sensors for quality prediction in batch chemical pulping processes[J] . Proceedings of the 1993 International Symposium on Intelligent Control, Chicago, Illinois, USA, 1993:150-155
20. M.T.Musavi, C.Domnisoru, G.Smith, etl. A neuro-fuzzy system for prediction of pulp digester k-number [J]. IEEE, 1999: 4253-4258
21. Belarbi K, Bettou K etc. Fuzzy Neural Networks for Estimation and Fuzzy Controller Design Simulation Study for a Pulp Batch Digester [J]. Journal of Process Control 10, 2000:35
22. Helena, Cristina, Aguiar, Rubens, Maciel, Filho. Neural Network and Hybrid Model: A Discussion about Different Modeling Techniques to Predict Pulping Degree with Industrial Date [J]. Chemical Engineering Science, 2001, 56:565
23. Lee, Jay H. and A. K. Datta, “Nonlinear inferential control of pulp digesters”[J], AIChE J., 1994,40(1):50-64
24. Anjan Kumar Datta. Model-Based Monitoring and Control of Batch Pulp Digester[J]. Proceedings of the American Control Conference, Baltlmere, Maryland, June,1994
25. A.W. Dorsey, J.H. Lee. Subspace identification for batch process[J]. Proceedings of the American Control Conference, San Diego, California, June 1999
26. 吴诗钦.硫酸盐法蒸煮脱木素的动力学数学模型及其应用[J].中国造纸.1984(4):13-16
27. 巫淑萍.邱公伟.硫酸盐法间歇蒸煮化学浆的动力学数学模型及其计算机控制方案研讨[J].中国造纸.1988(2):35~40
28. 管永刚.关于硫酸盐法蒸煮数学模型的若干问题[J].中国造纸.1997,16(2): 55-58
29. 管永刚.落叶松KP 法蒸煮数学模型参数的确定[J].中国造纸.1999(2):22-24
30. 王海燕,宋光燕,杨静.蒸煮液有效碱浓度与纸浆硬度控制[J]. 纸和造纸.1999(2):37
31. 胡慕伊.间歇蒸煮过程控制的研究[J].林产化学与工业.1998,18(4):18-22
32. 许向阳等.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
33. 罗琪.刘焕彬,硫酸盐间歇蒸煮过程中有效碱浓度数学模型的研究[J].广东造纸.1997(3):1-4
34. 罗琪.刘焕彬等,由硫酸盐法蒸煮脱木素反应动力学推导出的纸浆Kappa 值 数学模型[J].广东造纸.1997(4):1-4
35. 罗琪.刘焕彬等.Lo-SolidsTM蒸煮过程纸浆Kappa 值数学模型的建立[J].广东造纸.1998(3):11-13
36. 罗琪.刘焕彬.硫酸盐法间歇蒸煮过程的建模[J].华南理工大学学报:自科版.2000,19(4):53-55
37. 李向阳,朱学峰.硫酸盐蒸煮过程Kappa 值预测模型的研究与应用[J].广东造纸,2000(5):23
38. 于玲,祝和云.神经元网络用于纸浆的高锰酸钾值的软测量[J].中国造纸学报, 1997,13(sup):63-67
39. 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):9-14
40. 李艳.李向阳.朱学峰.刘焕彬.基于粗集理论和RBF 神经网络的软测量技术研究[J].自动化学报.2000,6(Supplement B):168-172
41. 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)
42. 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
43. 青州造纸厂关于引进Measurex2002 蒸煮控制系统的有关资料
44. 管永刚. 碱法蒸煮实用技术[M]. 天津:天津大学出版社,1992:1
45. 陈嘉翔. 制浆原理与工程[M].北京:中国轻工业出版社,1990:49-50
46. Vroom K.E.The H factor: a means of expressing cooking times and temperatures as a single variable.Pulp Paper Mag.Can.1957,58(C):228
47. 隆言泉. 制浆造纸工艺学[M]. 北京:轻工业出版社,1987:70
48. TAPPI T236cm-85
49. ISO302 TC6
50. GB 1546-89, 纸浆卡伯值的测量法
51. 王慧,陆浩.硫酸盐法制浆蒸煮过程的建模与控制的进展[J].中国造纸学报,17(2):124
52. 罗琪.硫酸盐法蒸煮过程纸浆Kappa 值软测量技术的研究[D].华南理工大学博士学位论文,1998
53. 李艳,张健,朱学峰等,蒸煮过程纸浆Kappa 值分段模型研究[J]. 纸和造纸. 2003(4)
54. 杨惠连,张涛. 误差理论与数据处理. 天津:天津大学出版社,1992
55. 李艳.制浆蒸煮过程纸浆卡伯值软测量技术研究与应用[D].华南理工大学博士学位论文,2003
56. 陈剑,古勇,苏宏业,褚健.化工过程数据校正中的数据分类问题.仪器仪 表学报.2000,21(6):625-628
57. 陆利忠.测控系统中采样数据的预处理.测控技术.2000,19(8):15-16
58. 陈文明,谢英秀,苏冬平,冯建生.KDD 在产品质量分析与控制中的应用.宝钢技术,2000,(3):55-58
59. 杨阳,刘峰,张天戈.分类器的数据预处理.计算机工程.1998,24(4):33-34
60. 王辉,曾献兵.工业过程监测的数据处理方法研究.计算技术与自动化.1994, 13(2):28-31
61. Zhong Bo, Xiao Zhi.Application of compositive clustering analysis methods in data preprocessing.Journal of Southwest China Normal University (Natural Science).2002,27(5):658-663
62. Hou W. Extraction and application of statistical relationships in relational databases. IEEE Transactions on Knowledge and Data Engineering. 1996, 8(6): 936-945
63. 肖智,李勇,李昌隆.一种基于相关分析的数据预处理方法.重庆大学学报(自然科学版).2002,25(6):132-134
64. 刘采勤. 加权回归分析. 河北省科学院学报. 1996: 5-10
65. 杨波. 加权最小二乘估计中加权系数的确定. 现代电子技术. 2002(12):45-47
66. 张永吉. 曲线拟合中的加权处理. 计算机与应用化学. 1994,11(3):238-240
67. 张贤达. 现代信号处理. 北京: 清华大学出版社, 1995
68. 张健, 李艳,朱学峰等. 基于升温曲线模式识别的蒸煮卡伯值预测[A]. 朱学峰,陈伟基,黄道平.过程控制科学技术与应用[C]. 广州:华南理工大学出版社,2002.464-467.
69. 于静江, 周春晖. 过程控制中的软测量技术[J]. 控制理论与应用. 1996, 13 (2): 137-144
70. 崔锦泰.小波分析导论.西安:西安交通大学出版社,1995
71. 李建平.小波分析与信号处理——理论、应用及软件实现.重庆:重庆出版社,1997
72. 杨福生.小波变换的工程分析与应用.北京:科学出版社,2000
73. I. Daubechies. Orthnomal bases of compactly supported wavelet. Comm. Pure and Appl. Math. 1988, 41: 909-996
74. M. Kobayashi . Wavelets and their applications in industry . Nonlinear Analysis.2001, 47:1749-1760
75. M. Antonopoulos-domis, T. Tambaouratzis. System identification during a transient via wavelet multi-resolution analysis followed by spectral techniques.Annals of Nuclear Energy.1998, 25(6):465-480
76. Jean Marc Lina, Michel. Mayrand.Complex Daubechies wavelets.Applied and Computational Harmonic Analysis.1995, (2):219-229
77. Chun-Hui Hsiao . State analysis of linear time delayed systems via Haar wavelets.Mathematics and Computers in Simulation.1997, 44: 457-470
78. Meyer Yves, Xu Hong . Wavelet Analysis and Chirps . Applied and Computational Harmonic Analysis.1997, 4(4):366-379
79. 于开平,邹经湘,杨炳渊.小波函数的性质及其应用研究[J].哈尔滨工业大学学报.2000,32(2):36-39
80. B.E.Boser, I.M.Guyon and V.Vapnik. A Training Algorithm for Optimal Margin Classifiers. Proceedings of the Fifth Annual Workshop on Computational Learning Theory, Pittsburgh, PA, USA. 1992: 144-152
81. C.Cortes and V.Vapnik. Support Vector Networks. Machine Learning. Vol. 20, 1995:273-297
82. Vapnik. V. The Nature of Statistical Learning Theory [M]. New York: Springer, 1995
83. Vapnik.V. Statistical Learning Theory. New York: Wiley, 1998
84. 边肇祺, 张学工. 模式识别(第二版)[M]. 北京: 清华大学出版社, 2000
85. Muller. K R, Smola A. J, et al. Predicting time series with support vector machines[A]. ProcICANN 97[C]. New York: Springer,1997. 999-1004.
86. Drucker H, Burges C.J, Kaufman L, et al. Support vector regression machines[A]. Adv Neural Infor Proc Syst[C], Cambridge: MIT Press, 1997,155-161
87. Suykens J.A.K., Vandewalle J.. Chaos control using least-squares support vector machines. Interantional Journal of Circuit Theory and Applications, 1999,27:605-615
88. Haixin Ke, Xuegong Zhang. Editing Support Vector Machines. IEEE 2001:1464-1467
89. Lin Chun-Fu, Sheng-De Wang. Fuzzy support vector machines. IEEE Transaction on Neural Networks. 2002, 13(2)
90. 朱国强,刘士荣,俞金寿. 基于支持向量机的数据建模在软测量建模中的应用[J]. 华东理工大学学报. 2002,28(增刊):6-10
91. 冯瑞,张浩然,邵惠鹤. 基于SVM 的软测量建模[J]. 信息与控制. 2002,31(6): 567-571
92. 李丽娜,侯朝桢. 基于支持向量机(SVM)的工业过程辨识[J]. 北京理工大学学报. 2003, 23(5):569-571
93. 王定成,方廷健,高理富等. 支持向量机回归在线建模与应用[J]. 控制与决策. 2003, 18(1): 89-93
94. 孙宗海. 支持向量机及其在控制中的应用研究[D]. 浙江大学博士学位论文. 2003: 77-87
95. 邵惠鹤. 支持向量机理论及其应用[J]. 自动化博览. 2003,二十周年纪念文集:90-95
96. Duan K., Keerthi S.S and Poo A.N, Evalutaion of simple performance measures for tuning SVM hyperparameters, Nat. Univ. Singapore, Tech. Rep. CD-01-11,2001
97. Smits G.F, Jordaan E.M, Improved SVM Regression Using Mixtures of Kernels. IEEE, 2002, 2785-2790
98. Xuegong Zhang. Using Class-center Vectors to Bulild Support Vector Machines. IEEE, 1999, 3-11
99. Olvi L. Mangasarian, David R. Musicant. Robust linear and support vector regression. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(9)
100. Suykens J.A.K., De Brabanter J., Lukas L.,et al, Weighted least squares support vector machines: robustness and sparse approximation. Neurocomputing, 2002, 48(1-4):85-105
101. Sun ZongHai, Youxian Sun. Fuzzy support vector machine for regression estimation. 2003 IEEE conference on system, man. ,Cybernetics.
102. Dug Hun Hong, Changha Hwang. Support vector fuzzy regression machines. Fuzzy Sets and Systems, 138(2003): 271-281
103. Chen-Chia Chuang, Shun-Feng Su and Chih-Ching Hsiao, Robust Support Vector Regression Networks for Function Approximation with Outliers. IEEE Transactions on Neural Networks. 2002, 13(6)
104. 杨慧中,张素贞,陶振麟. 聚合反应过程质量指标的推理估计混合模型[J]. 高校化学工程学报. 2003, 17(5): 552-558
105. 王雅琳. 智能集成建模理论及其在有色冶炼过程优化控制中的应用研究[D]. 中南大学博士学位论文,2001
106. 王树青,金晓明,荣冈. 先进控制技术及应用:第一讲工业生产过程的先进控制[J]. 化工自动化及仪表, 1999, 26(2): 61-65
107. 罗荣富,邵惠鹤.丙烯精馏塔的非线性推断控制系统[J].化工自动化及仪表, 1992.18(5):5-9
108. 刘齐忠,马金魁,康庆山.FCCU 轻柴油365℃含量的软测量[J].石油化工自
2. 中国造纸工业的“十五规划”.
3. Marjatta Ollila.卡伯值与亮度的测量及其重要性.刘新兵译.中国造纸.1998, (5):57-64
4. Eglis Kubulnieks et al.The STFI OPTI-Kappa analyzer —applications and accuracy.Tappi Journal.1987,38:11
5. L.Agneus et al . Optimal process control with on-line Kappa number analysis.Pulp and Paper Canada.1992,93:2
6. Richard J. et al.Advanced sensors and control for the pulping and bleaching process.Appita Journal.1998,51(6):412
7. 闫东波. 纸浆卡伯值光学在线传感器的研究[D]. 华南理工大学博士学位论文,2000:1-19
8. 俞金寿, 刘爱伦等编. 软测量技术及其在石油化工中的应用[M]. 北京: 化学工业出版社, 2000
9. C.B.Brosilow. Inferential Control of process control, AIChE J 1978,24(3):475-484
10. MacVoy. T J. Comtemplative stance for chemical process. Automatica, 1992, 28(2): 441-442
11. Kerr A J. The kinetics of kraft pulping-batch digester control[J]. Tappi,1976, 59: 89
12. E.W.马科隆.T.M.格雷斯编.最新碱法制浆技术[M].曹邦威译.北京:中国轻工业出版社,1999:48-49
13. Hatton J V. The Potential of Process Control in Kraft Pulping of Hardwoods Relative to Softwoods [J]. Tappi. 1976,59(8):48
14. Lin, C.P., Mao, M.Y. and Jane, C.Y., Tappi, 1978,61(2):72
15. Chari, N.C.S. Integrated Control System for Batch Digester Control [J]. Tappi. 1973,56(7):65
16. S.Noreus, G. Wallin, T.Olsson, etl. Computer control of batch digesters. Pulp Paper Mag. Can. 1974, 75(5):T204
17. Tasman, J.E., Tappi, 1981, 64(3):175-176
18. H.C.Kim, X.Shen, M.Rao, Quality prediction by neural network for pulp and paper processes. CCECE/CCGEI, 1993:104-107
19. Ming Rao, Jean Corbin, Qun Wang.Soft sensors for quality prediction in batch chemical pulping processes[J] . Proceedings of the 1993 International Symposium on Intelligent Control, Chicago, Illinois, USA, 1993:150-155
20. M.T.Musavi, C.Domnisoru, G.Smith, etl. A neuro-fuzzy system for prediction of pulp digester k-number [J]. IEEE, 1999: 4253-4258
21. Belarbi K, Bettou K etc. Fuzzy Neural Networks for Estimation and Fuzzy Controller Design Simulation Study for a Pulp Batch Digester [J]. Journal of Process Control 10, 2000:35
22. Helena, Cristina, Aguiar, Rubens, Maciel, Filho. Neural Network and Hybrid Model: A Discussion about Different Modeling Techniques to Predict Pulping Degree with Industrial Date [J]. Chemical Engineering Science, 2001, 56:565
23. Lee, Jay H. and A. K. Datta, “Nonlinear inferential control of pulp digesters”[J], AIChE J., 1994,40(1):50-64
24. Anjan Kumar Datta. Model-Based Monitoring and Control of Batch Pulp Digester[J]. Proceedings of the American Control Conference, Baltlmere, Maryland, June,1994
25. A.W. Dorsey, J.H. Lee. Subspace identification for batch process[J]. Proceedings of the American Control Conference, San Diego, California, June 1999
26. 吴诗钦.硫酸盐法蒸煮脱木素的动力学数学模型及其应用[J].中国造纸.1984(4):13-16
27. 巫淑萍.邱公伟.硫酸盐法间歇蒸煮化学浆的动力学数学模型及其计算机控制方案研讨[J].中国造纸.1988(2):35~40
28. 管永刚.关于硫酸盐法蒸煮数学模型的若干问题[J].中国造纸.1997,16(2): 55-58
29. 管永刚.落叶松KP 法蒸煮数学模型参数的确定[J].中国造纸.1999(2):22-24
30. 王海燕,宋光燕,杨静.蒸煮液有效碱浓度与纸浆硬度控制[J]. 纸和造纸.1999(2):37
31. 胡慕伊.间歇蒸煮过程控制的研究[J].林产化学与工业.1998,18(4):18-22
32. 许向阳等.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
33. 罗琪.刘焕彬,硫酸盐间歇蒸煮过程中有效碱浓度数学模型的研究[J].广东造纸.1997(3):1-4
34. 罗琪.刘焕彬等,由硫酸盐法蒸煮脱木素反应动力学推导出的纸浆Kappa 值 数学模型[J].广东造纸.1997(4):1-4
35. 罗琪.刘焕彬等.Lo-SolidsTM蒸煮过程纸浆Kappa 值数学模型的建立[J].广东造纸.1998(3):11-13
36. 罗琪.刘焕彬.硫酸盐法间歇蒸煮过程的建模[J].华南理工大学学报:自科版.2000,19(4):53-55
37. 李向阳,朱学峰.硫酸盐蒸煮过程Kappa 值预测模型的研究与应用[J].广东造纸,2000(5):23
38. 于玲,祝和云.神经元网络用于纸浆的高锰酸钾值的软测量[J].中国造纸学报, 1997,13(sup):63-67
39. 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):9-14
40. 李艳.李向阳.朱学峰.刘焕彬.基于粗集理论和RBF 神经网络的软测量技术研究[J].自动化学报.2000,6(Supplement B):168-172
41. 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)
42. 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
43. 青州造纸厂关于引进Measurex2002 蒸煮控制系统的有关资料
44. 管永刚. 碱法蒸煮实用技术[M]. 天津:天津大学出版社,1992:1
45. 陈嘉翔. 制浆原理与工程[M].北京:中国轻工业出版社,1990:49-50
46. Vroom K.E.The H factor: a means of expressing cooking times and temperatures as a single variable.Pulp Paper Mag.Can.1957,58(C):228
47. 隆言泉. 制浆造纸工艺学[M]. 北京:轻工业出版社,1987:70
48. TAPPI T236cm-85
49. ISO302 TC6
50. GB 1546-89, 纸浆卡伯值的测量法
51. 王慧,陆浩.硫酸盐法制浆蒸煮过程的建模与控制的进展[J].中国造纸学报,17(2):124
52. 罗琪.硫酸盐法蒸煮过程纸浆Kappa 值软测量技术的研究[D].华南理工大学博士学位论文,1998
53. 李艳,张健,朱学峰等,蒸煮过程纸浆Kappa 值分段模型研究[J]. 纸和造纸. 2003(4)
54. 杨惠连,张涛. 误差理论与数据处理. 天津:天津大学出版社,1992
55. 李艳.制浆蒸煮过程纸浆卡伯值软测量技术研究与应用[D].华南理工大学博士学位论文,2003
56. 陈剑,古勇,苏宏业,褚健.化工过程数据校正中的数据分类问题.仪器仪 表学报.2000,21(6):625-628
57. 陆利忠.测控系统中采样数据的预处理.测控技术.2000,19(8):15-16
58. 陈文明,谢英秀,苏冬平,冯建生.KDD 在产品质量分析与控制中的应用.宝钢技术,2000,(3):55-58
59. 杨阳,刘峰,张天戈.分类器的数据预处理.计算机工程.1998,24(4):33-34
60. 王辉,曾献兵.工业过程监测的数据处理方法研究.计算技术与自动化.1994, 13(2):28-31
61. Zhong Bo, Xiao Zhi.Application of compositive clustering analysis methods in data preprocessing.Journal of Southwest China Normal University (Natural Science).2002,27(5):658-663
62. Hou W. Extraction and application of statistical relationships in relational databases. IEEE Transactions on Knowledge and Data Engineering. 1996, 8(6): 936-945
63. 肖智,李勇,李昌隆.一种基于相关分析的数据预处理方法.重庆大学学报(自然科学版).2002,25(6):132-134
64. 刘采勤. 加权回归分析. 河北省科学院学报. 1996: 5-10
65. 杨波. 加权最小二乘估计中加权系数的确定. 现代电子技术. 2002(12):45-47
66. 张永吉. 曲线拟合中的加权处理. 计算机与应用化学. 1994,11(3):238-240
67. 张贤达. 现代信号处理. 北京: 清华大学出版社, 1995
68. 张健, 李艳,朱学峰等. 基于升温曲线模式识别的蒸煮卡伯值预测[A]. 朱学峰,陈伟基,黄道平.过程控制科学技术与应用[C]. 广州:华南理工大学出版社,2002.464-467.
69. 于静江, 周春晖. 过程控制中的软测量技术[J]. 控制理论与应用. 1996, 13 (2): 137-144
70. 崔锦泰.小波分析导论.西安:西安交通大学出版社,1995
71. 李建平.小波分析与信号处理——理论、应用及软件实现.重庆:重庆出版社,1997
72. 杨福生.小波变换的工程分析与应用.北京:科学出版社,2000
73. I. Daubechies. Orthnomal bases of compactly supported wavelet. Comm. Pure and Appl. Math. 1988, 41: 909-996
74. M. Kobayashi . Wavelets and their applications in industry . Nonlinear Analysis.2001, 47:1749-1760
75. M. Antonopoulos-domis, T. Tambaouratzis. System identification during a transient via wavelet multi-resolution analysis followed by spectral techniques.Annals of Nuclear Energy.1998, 25(6):465-480
76. Jean Marc Lina, Michel. Mayrand.Complex Daubechies wavelets.Applied and Computational Harmonic Analysis.1995, (2):219-229
77. Chun-Hui Hsiao . State analysis of linear time delayed systems via Haar wavelets.Mathematics and Computers in Simulation.1997, 44: 457-470
78. Meyer Yves, Xu Hong . Wavelet Analysis and Chirps . Applied and Computational Harmonic Analysis.1997, 4(4):366-379
79. 于开平,邹经湘,杨炳渊.小波函数的性质及其应用研究[J].哈尔滨工业大学学报.2000,32(2):36-39
80. B.E.Boser, I.M.Guyon and V.Vapnik. A Training Algorithm for Optimal Margin Classifiers. Proceedings of the Fifth Annual Workshop on Computational Learning Theory, Pittsburgh, PA, USA. 1992: 144-152
81. C.Cortes and V.Vapnik. Support Vector Networks. Machine Learning. Vol. 20, 1995:273-297
82. Vapnik. V. The Nature of Statistical Learning Theory [M]. New York: Springer, 1995
83. Vapnik.V. Statistical Learning Theory. New York: Wiley, 1998
84. 边肇祺, 张学工. 模式识别(第二版)[M]. 北京: 清华大学出版社, 2000
85. Muller. K R, Smola A. J, et al. Predicting time series with support vector machines[A]. ProcICANN 97[C]. New York: Springer,1997. 999-1004.
86. Drucker H, Burges C.J, Kaufman L, et al. Support vector regression machines[A]. Adv Neural Infor Proc Syst[C], Cambridge: MIT Press, 1997,155-161
87. Suykens J.A.K., Vandewalle J.. Chaos control using least-squares support vector machines. Interantional Journal of Circuit Theory and Applications, 1999,27:605-615
88. Haixin Ke, Xuegong Zhang. Editing Support Vector Machines. IEEE 2001:1464-1467
89. Lin Chun-Fu, Sheng-De Wang. Fuzzy support vector machines. IEEE Transaction on Neural Networks. 2002, 13(2)
90. 朱国强,刘士荣,俞金寿. 基于支持向量机的数据建模在软测量建模中的应用[J]. 华东理工大学学报. 2002,28(增刊):6-10
91. 冯瑞,张浩然,邵惠鹤. 基于SVM 的软测量建模[J]. 信息与控制. 2002,31(6): 567-571
92. 李丽娜,侯朝桢. 基于支持向量机(SVM)的工业过程辨识[J]. 北京理工大学学报. 2003, 23(5):569-571
93. 王定成,方廷健,高理富等. 支持向量机回归在线建模与应用[J]. 控制与决策. 2003, 18(1): 89-93
94. 孙宗海. 支持向量机及其在控制中的应用研究[D]. 浙江大学博士学位论文. 2003: 77-87
95. 邵惠鹤. 支持向量机理论及其应用[J]. 自动化博览. 2003,二十周年纪念文集:90-95
96. Duan K., Keerthi S.S and Poo A.N, Evalutaion of simple performance measures for tuning SVM hyperparameters, Nat. Univ. Singapore, Tech. Rep. CD-01-11,2001
97. Smits G.F, Jordaan E.M, Improved SVM Regression Using Mixtures of Kernels. IEEE, 2002, 2785-2790
98. Xuegong Zhang. Using Class-center Vectors to Bulild Support Vector Machines. IEEE, 1999, 3-11
99. Olvi L. Mangasarian, David R. Musicant. Robust linear and support vector regression. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(9)
100. Suykens J.A.K., De Brabanter J., Lukas L.,et al, Weighted least squares support vector machines: robustness and sparse approximation. Neurocomputing, 2002, 48(1-4):85-105
101. Sun ZongHai, Youxian Sun. Fuzzy support vector machine for regression estimation. 2003 IEEE conference on system, man. ,Cybernetics.
102. Dug Hun Hong, Changha Hwang. Support vector fuzzy regression machines. Fuzzy Sets and Systems, 138(2003): 271-281
103. Chen-Chia Chuang, Shun-Feng Su and Chih-Ching Hsiao, Robust Support Vector Regression Networks for Function Approximation with Outliers. IEEE Transactions on Neural Networks. 2002, 13(6)
104. 杨慧中,张素贞,陶振麟. 聚合反应过程质量指标的推理估计混合模型[J]. 高校化学工程学报. 2003, 17(5): 552-558
105. 王雅琳. 智能集成建模理论及其在有色冶炼过程优化控制中的应用研究[D]. 中南大学博士学位论文,2001
106. 王树青,金晓明,荣冈. 先进控制技术及应用:第一讲工业生产过程的先进控制[J]. 化工自动化及仪表, 1999, 26(2): 61-65
107. 罗荣富,邵惠鹤.丙烯精馏塔的非线性推断控制系统[J].化工自动化及仪表, 1992.18(5):5-9
108. 刘齐忠,马金魁,康庆山.FCCU 轻柴油365℃含量的软测量[J].石油化工自