软测量建模方法研究及其工业应用
|
摘要
现代工业过程对控制系统越来越高的要求促进了软测量技术的发展，作为解决现代复杂工业过程中较难甚至无法由硬件在线检测参量的实时估计问题的有效手段，软测量已经成为目前过程控制领域的研究热点之一，受到了国内外学者和生产企业的广泛关注。本文以实际工业过程为背景，结合化工过程的工艺知识，对软测量建模若干方法进行了深入的研究，并对软测量技术在实际工业过程中的应用进行了探讨和实践。本文的主要研究工作如下：
1)提出了一种基于改进的FasBack模糊神经网络的新型软测量建模方法。改进方法采用收敛性较好的Levenberg-Marquardt算法训练FasBack模糊神经网络模型中的部分参数，其余参数仍然采用原BP算法进行训练。由于FasBack模糊神经网络既有神经网络的非线性拟合能力，又具有较强的分类能力，因此，既适用于多输入／单输出(MISO)情况下的软测量建模又适用于多输入／多输出(MOMO)情况下的软测量建模。将所提出的建模方法分别用于MISO情况下精对苯二甲酸(PTA)生产过程中的4-CBA含量软测量建模和MIMO情况下的复合肥养分含量：氮、五氧化二磷、氧化钾含量软测量建模，经实际工业过程数据验证表明，提出的MISO和MIMO软测量模型学习速度快、预测精度高、鲁棒性强，不仅为实现PTA生产过程中4-CBA含量的实时、精确控制提供了一条有效的途径，而且为MIMO软测量建模方法进行了一次有益的尝试。
2)针对复合肥生产过程中产品的几种养分含量需要同时预报的一类多输入／多输出(MIMO)软测量建模问题，提出了一种基于混合建模技术的复合肥养分含量MIMO软测量建模方法。该方法充分利用了过程的工艺知识，将简化机理建模方法与数据驱动建模方法结合起来建立复合肥养分含量的MIMO软测量模型；同时，充分考虑了MIMO系统采集数据的严重相关性和大量冗余信息的存在，所以数据驱动建模方法选用了具有强大的处理相关和冗余信息能力的PLS算法；此外，在该算法中采用了一种新的方差递推算法，从而实现PLS模型的在线更新以克服模型在线应用时的老化现象。该算法充分利用了两种建模方法的优点，克服了其各自的局限性，基于实际工业过程数据的仿真结果表明，所建模型运算速度快、预测效果良好，模型预测结果与化验室分析结果趋势比较吻合，预测精度高，可以满足复合肥各养分含量在线预报要求。
3)将基于混合建模方法的复合肥养分含量MIMO软测量模型应用于实际工业过程中复合肥养分：氮、五氧化二磷、氧化钾含量的实时估计，通过对数据采集、预处理、时序匹配、软测量建模以及在线校正环节的精心实施，实现了过程的实时监控，在复合肥生产中起了重要的指导作用。实际运行结果显示所采用的软测量方法不仅实现简单，而且运算速度快、模型预测结果与化验室分析结果趋势较为吻合，满足了复合肥各养分含量在线实时预报的要求。
4)提出了一种基于混合建模技术的自适应软测量建模方法以解决软测量模型实际运行后的模型老化现象。该混合建模方法首先采用模糊C均值聚类(FCM)算法对训练样本进行聚类，并对每一类分别采用支持向量机进行训练建立子模型以提高模型的预测精度。当新增样本到来时，对支持向量机进行增量学习以便显著减少运算时间并提高模型适应工况变化的能力。由于支持向量机运算的复杂性取决于支持向量的个数，因此，当增加一个支持向量时，采用启发式策略去掉支持向量机工作集中的一个老的支持向量并进行减量学习，从而可以在软测量模型中不断增加能够代表新工况的信息样本的同时控制工作样本集的规模。将所提出的软测量建模方法用于对二甲苯(PX)吸附分离过程纯度的预测，仿真结果表明所提出的建模方法可以有效地增强软测量模型适应工况变化的能力，提高其预测精度。
The higher performance requirements of control systems for modern industrial process have been promoting the development of soft sensor technique. In modern complicated industrial process, some variables are very hard to be measured or even cannot be measured on-line by existing instruments and sensors. Soft sensor is an effective means of implementing the on-line evaluation of these variables. At present, soft sensor technique has become one of the most important research areas in process control field. Combining technics knowledge of chemical engineering process, some modeling methods of soft sensor technique are studied intensively in this dissertation. Furthermore, the problems of soft sensors implementing for industrial processes are also studied and solved. The main contributions are described as follows:
1) A new soft sensor modeling method based on improved FasBack neuro-fuzzy system is developed. Levenberg-Marquardt algorithm is used to train some parameters in the model, while the residual parameters are still trained by BP algorithm. Based on practical process data, the proposed improved FasBack neuro-fuzzy system is applied to build soft sensor model of 4-CBA concentration of purified terephthalic acid (PTA) product. Simulation results indicate that the proposed model is precise and efficient and it is possible to realize the quality control of PTA product in the commercial reactor. Because of the powerful clustering and nonlinear regression capability, FasBack neuro-fuzzy system is also very suitable to multi-input multi-output (MIMO) soft sensor modeling. So, the proposed model is also used to build a MIMO soft sensor model to evaluate the three quality variables simultaneously in compound fertilizer process. Simulation results indicate the proposed model possesses good convergence and prediction precision. It is a useful try in MIMO soft sensor modeling method.
2) In view of the problem that the three quality variables in compound fertilizer production need to be monitored and controlled simultaneously, a new modeling method of multi-inputs multi-outputs (MIMO) soft sensor, which is constructed
based on hybrid modeling technique, is proposed for these interactional variables. The technics information of the process is fully used in this modeling method, that is combing the simplified first principle of the process and data-driven modeling method toghther to build the MIMO soft sensor model of the contents of compound fertilizer process. The pertinence and redundancy of the data are considered at the same time, so limited memory PLS algorithm that is very powerful in solving pertinence and redundancy is chosen as the data-driven modeling method. Futhermore, a new variance recursive algorithm is adopted in the limited memory PLS algorithm, therefore the PLS model can be updated on-line. Simulation results based on practical process data indicate that the proposed model is fast, precise and efficient and it is possible to realize the on-line quality control for compound fertilizer.
3) The MIMO soft sensor model that is based on hybrid modeling method is applied for a practical compound fertilizer process to evaluate the content of nitrogen, P_2O_5 and K_2O on-line simultaneously, and therefore process monitoring is implemented. The detail procedures are described in detail, including the software and hardware platform of soft sensor implementing, data collection, data pretreatment, time alignment matching between the primary variables and the process variables, the modeling steps of the soft sensor, and the on-line soft sensor model rectification. In this dissertation, the on-line evaluating values are presented. The results indicate that the proposed model can satisfy the requirement of on-line evaluating of the three quality variables in compound fertilizer process.
4) In order to overcome the problem that soft sensor models cannot be updated with the process changes, an adaptive soft sensor modeling algorithm based on hybrid modeling method is proposed. In this hybrid modeling method, the training samples are firstly clustered by fuzzy c-means (FCM) algorithm, and then by training each clustering with SVM algorithm, sub-model is built to each clustering in order to improve the evaluation precision of the soft sensor model. When an incremental sample that represents new operation information is
introduced in the model, incremental learning is applied to the corresponding SVM sub-model in order to reducing computing time and increasing the model's adaptive abilities to various operation conditions. Because the computing complexity of SVM depends on the number of the support vectors, when a new support vector is added, an old support vector chosen by heuristic sample displacement method was then discarded from the sub-model to control the size of the working set. The proposed method is applied to predict the p-xylene (PX) purity in an adsorption separation process. Simulation results indicate that the proposed method actually increases the model's adaptive abilities to various operation conditions and improves its generalization capability.
1)提出了一种基于改进的FasBack模糊神经网络的新型软测量建模方法。改进方法采用收敛性较好的Levenberg-Marquardt算法训练FasBack模糊神经网络模型中的部分参数，其余参数仍然采用原BP算法进行训练。由于FasBack模糊神经网络既有神经网络的非线性拟合能力，又具有较强的分类能力，因此，既适用于多输入／单输出(MISO)情况下的软测量建模又适用于多输入／多输出(MOMO)情况下的软测量建模。将所提出的建模方法分别用于MISO情况下精对苯二甲酸(PTA)生产过程中的4-CBA含量软测量建模和MIMO情况下的复合肥养分含量：氮、五氧化二磷、氧化钾含量软测量建模，经实际工业过程数据验证表明，提出的MISO和MIMO软测量模型学习速度快、预测精度高、鲁棒性强，不仅为实现PTA生产过程中4-CBA含量的实时、精确控制提供了一条有效的途径，而且为MIMO软测量建模方法进行了一次有益的尝试。
2)针对复合肥生产过程中产品的几种养分含量需要同时预报的一类多输入／多输出(MIMO)软测量建模问题，提出了一种基于混合建模技术的复合肥养分含量MIMO软测量建模方法。该方法充分利用了过程的工艺知识，将简化机理建模方法与数据驱动建模方法结合起来建立复合肥养分含量的MIMO软测量模型；同时，充分考虑了MIMO系统采集数据的严重相关性和大量冗余信息的存在，所以数据驱动建模方法选用了具有强大的处理相关和冗余信息能力的PLS算法；此外，在该算法中采用了一种新的方差递推算法，从而实现PLS模型的在线更新以克服模型在线应用时的老化现象。该算法充分利用了两种建模方法的优点，克服了其各自的局限性，基于实际工业过程数据的仿真结果表明，所建模型运算速度快、预测效果良好，模型预测结果与化验室分析结果趋势比较吻合，预测精度高，可以满足复合肥各养分含量在线预报要求。
3)将基于混合建模方法的复合肥养分含量MIMO软测量模型应用于实际工业过程中复合肥养分：氮、五氧化二磷、氧化钾含量的实时估计，通过对数据采集、预处理、时序匹配、软测量建模以及在线校正环节的精心实施，实现了过程的实时监控，在复合肥生产中起了重要的指导作用。实际运行结果显示所采用的软测量方法不仅实现简单，而且运算速度快、模型预测结果与化验室分析结果趋势较为吻合，满足了复合肥各养分含量在线实时预报的要求。
4)提出了一种基于混合建模技术的自适应软测量建模方法以解决软测量模型实际运行后的模型老化现象。该混合建模方法首先采用模糊C均值聚类(FCM)算法对训练样本进行聚类，并对每一类分别采用支持向量机进行训练建立子模型以提高模型的预测精度。当新增样本到来时，对支持向量机进行增量学习以便显著减少运算时间并提高模型适应工况变化的能力。由于支持向量机运算的复杂性取决于支持向量的个数，因此，当增加一个支持向量时，采用启发式策略去掉支持向量机工作集中的一个老的支持向量并进行减量学习，从而可以在软测量模型中不断增加能够代表新工况的信息样本的同时控制工作样本集的规模。将所提出的软测量建模方法用于对二甲苯(PX)吸附分离过程纯度的预测，仿真结果表明所提出的建模方法可以有效地增强软测量模型适应工况变化的能力，提高其预测精度。
The higher performance requirements of control systems for modern industrial process have been promoting the development of soft sensor technique. In modern complicated industrial process, some variables are very hard to be measured or even cannot be measured on-line by existing instruments and sensors. Soft sensor is an effective means of implementing the on-line evaluation of these variables. At present, soft sensor technique has become one of the most important research areas in process control field. Combining technics knowledge of chemical engineering process, some modeling methods of soft sensor technique are studied intensively in this dissertation. Furthermore, the problems of soft sensors implementing for industrial processes are also studied and solved. The main contributions are described as follows:
1) A new soft sensor modeling method based on improved FasBack neuro-fuzzy system is developed. Levenberg-Marquardt algorithm is used to train some parameters in the model, while the residual parameters are still trained by BP algorithm. Based on practical process data, the proposed improved FasBack neuro-fuzzy system is applied to build soft sensor model of 4-CBA concentration of purified terephthalic acid (PTA) product. Simulation results indicate that the proposed model is precise and efficient and it is possible to realize the quality control of PTA product in the commercial reactor. Because of the powerful clustering and nonlinear regression capability, FasBack neuro-fuzzy system is also very suitable to multi-input multi-output (MIMO) soft sensor modeling. So, the proposed model is also used to build a MIMO soft sensor model to evaluate the three quality variables simultaneously in compound fertilizer process. Simulation results indicate the proposed model possesses good convergence and prediction precision. It is a useful try in MIMO soft sensor modeling method.
2) In view of the problem that the three quality variables in compound fertilizer production need to be monitored and controlled simultaneously, a new modeling method of multi-inputs multi-outputs (MIMO) soft sensor, which is constructed
based on hybrid modeling technique, is proposed for these interactional variables. The technics information of the process is fully used in this modeling method, that is combing the simplified first principle of the process and data-driven modeling method toghther to build the MIMO soft sensor model of the contents of compound fertilizer process. The pertinence and redundancy of the data are considered at the same time, so limited memory PLS algorithm that is very powerful in solving pertinence and redundancy is chosen as the data-driven modeling method. Futhermore, a new variance recursive algorithm is adopted in the limited memory PLS algorithm, therefore the PLS model can be updated on-line. Simulation results based on practical process data indicate that the proposed model is fast, precise and efficient and it is possible to realize the on-line quality control for compound fertilizer.
3) The MIMO soft sensor model that is based on hybrid modeling method is applied for a practical compound fertilizer process to evaluate the content of nitrogen, P_2O_5 and K_2O on-line simultaneously, and therefore process monitoring is implemented. The detail procedures are described in detail, including the software and hardware platform of soft sensor implementing, data collection, data pretreatment, time alignment matching between the primary variables and the process variables, the modeling steps of the soft sensor, and the on-line soft sensor model rectification. In this dissertation, the on-line evaluating values are presented. The results indicate that the proposed model can satisfy the requirement of on-line evaluating of the three quality variables in compound fertilizer process.
4) In order to overcome the problem that soft sensor models cannot be updated with the process changes, an adaptive soft sensor modeling algorithm based on hybrid modeling method is proposed. In this hybrid modeling method, the training samples are firstly clustered by fuzzy c-means (FCM) algorithm, and then by training each clustering with SVM algorithm, sub-model is built to each clustering in order to improve the evaluation precision of the soft sensor model. When an incremental sample that represents new operation information is
introduced in the model, incremental learning is applied to the corresponding SVM sub-model in order to reducing computing time and increasing the model's adaptive abilities to various operation conditions. Because the computing complexity of SVM depends on the number of the support vectors, when a new support vector is added, an old support vector chosen by heuristic sample displacement method was then discarded from the sub-model to control the size of the working set. The proposed method is applied to predict the p-xylene (PX) purity in an adsorption separation process. Simulation results indicate that the proposed method actually increases the model's adaptive abilities to various operation conditions and improves its generalization capability.
引文
[1] 刘伯高．化工过程推断估计的若干问题研究，华东理工大学博士学位论文，1999
[2] Joseph B., Brosilow C.B.. Inferential control of process: part Ⅰ. Steady state analysis and design, AIChE Journal, 1978, 24(3): 485-492
[3] Brosilow C.B., Tong M.. Inferential control of process: part Ⅱ. The structure and dynamics of inferential control system, AIChE Journal, 1978, 24(3): 492-500
[4] Joseph B., Brosilow C.B.. Inferential control of process: part Ⅲ. Construction of optimal and suboptimal dynamic estimators, AIChE Journal, 1978, 24(3): 500-509
[5] 俞金寿，刘爱伦，张克进．软测量技术及其在石油化工中的应用，化学工业出版社，2000
[6] McAvoy T.J.. Contemplative stance for chemical process control-an IFAC report, Automatica, 1992, 28(2): 441-442
[7] 仲蔚．软测量与先进控制策略研究及其在石油化工过程中的应用，华东理工大学博士学位论文，1999
[8] Araúzo-Bravo M J, et al.. Automatization of a penicillin production process with soft sensors and an adaptive controller based on neuro fuzzy systems. Control Engineering Practice, 2004, 12: 1073—1090
[9] 刘瑞兰，苏宏业，褚健．PLS回归软测量方法在催化重整稳定油组分估计中的应用，化工自动化及仪表，2002，29(5)：44-47
[10] Er M.J., Liao J., Lin J.. Fuzzy neural networks-based quality prediction system for sintering process, IEEE Transactions on Fuzzy Systems, 2000, 8(3): 314-324
[11] Teppola P., Mujunen S., Minkkinen P.. A combined approach of partial least squares and fuzzy c-means clustering for the monitoring of an activated-sludge waste-water treatment plant, Chemometfics and Intelligent Laboratory Systems, 1998, 41 (1): 95-103
[12] Fortuna L., Graziani S., Xibilia M.G.. Soft sensors for product quality monitoring in debutanizer distillation columns, Control Engineering Pratice, 2005, 13(4): 499-508
[13] Antony S.J., Zhou C.H., Wang X.. An integrated mechanistic-neural network modeling for granular systems, Applied Mathematical Modelling, 2006, 30(1): 116-128
[14] Desai K., Badhe Y., Tambe S.S., Kulkarni B.D.. Soft-sensor development for fed-batch bioreactors using support vector regression, Biochemical Engineering Journal, 2006, 27(3): 225-239
[15] 刘涵，刘丁，郑岗，梁炎明，宋念龙．基于最小二乘支持向量机的天然气负荷预测，化工学报，2004，55(5)：828-832
[16] 罗荣富，邵惠鹤．推断控制中二次变量选择方法的研究，1992年控制与决策学术年会 论文集，控制与决策编委会出版，1992
[17] 刘良宏，周兴贵，袁渭康．非线性分布参数系统状态估计的最佳测量位置，化工学报，1996，47(3)：267-272
[18] Zamprogna E., Barolo M., Seborg D.E.. Optimal selection of soft sensors inputs for batch distillation columns using principal component analysis, Journal of Process Control, 2005, 15(1): 39-52
[19] 马朝阳，苏宏业，傅永峰，褚健．基于KPCA-SVR方法的复合肥养分含量建模，中国科学技术大学学报，2005，35(增刊)：314—321
[20] Luo J.X., Shao H.H.. Selecting secondary measurements for soft sensor modeling using rough sets theory, Proceedings of the 4th World Congress on Intelligent Control and Automation, June 10-14 2002, Shanghai, China, 415-419
[21] 刘瑞兰，陈渭泉，苏宏业．基于改进GA-PLS算法的最优辅助变量选择及其在软测量建模中的应用，南京邮电大学学报(自然科学科学版)，2006，26(1)：76-80
[22] 李华生，董文葆，袁一．化工过程测量数据中过失误差的侦破，炼油化工自动化，1992，(2)：16-20
[23] Narasimhan S., Mah R.S.H.. Generalized likelihood ratio method for gross error identification, AIChE Journal, 1987, 33(9): 1514-1521
[24] Michael L., Mark A.. Modeling chemical processes using prior knowledge and neural networks, AIChE Journal, 1994, 40(8): 1328-1340
[25] 陈剑．数据校正理论及其应用研究，浙江大学硕士学位论文，2000
[26] Yang S.H., Chen B.H., Wang X.Z.. Neural network based fault diagnosis using unmeasurable inputs, Engineering Applications of Artificial Intelligence, 2000, (13): 345-356
[27] 于静江，周春晖．过程控制中的软测量技术，控制理论与应用，1996，13(2)137-144
[28] 涂植英，朱麟章．过程控制系统，机械工业出版社，1998
[29] 刘瑞兰．软测量技术若干问题的研究及工业应用，浙江大学博士学位论文，2004
[30] 宋凯，王海青，李平．折息递推PLS算法及其在橡胶混炼质量控制中的应用，化工学报，2004，55(6)：942-946
[31] 张英，苏宏业，褚健．基于ISVM的软测量建模及其在PX生产中的应用研究，控制与决策，2005，20(10)：1102-1106
[32] Feng R., Zhang Y.J., Zhang Y.Z., Shao H.H.. Drifting modeling method using weighted support vector machines with application to soft sensor, Acta Automatica Sinica, 2004, 30(3): 436-441
[33] 李春富，Zhang J．，王桂增．基于PLS模型的自适应间歇过程质量预测，清华大学学报(自然科学版)，2004，44(10)：1360-1363
[34] 鄂加强，王耀南，梅炽．铜精炼过程铜液温度软测量模型及应用，化工学报，2006， 57(1)：203-209
[35] Mu S., Zeng Y., Liu R., Wu P., Su H., Chu J.. Online dual updating with recursive PLS model and its application in predicting crystal size of purified terephthalic acid (PTA) process, Journal of Process Control, 2006, 16(6): 557-566
[36] Zhou L., Lu Y.Z.. Modeling and control for nonlinear time-delay system via pattern recognition approach, Preprints of 2nd IFAC workshop on artificial intelligence in real time control, 1989, 7-12
[37] 黄克瑾．精馏过程的模型化及仿真，浙江大学博士学位论文，1992
[38] 丁云，于静江，周春晖．原油蒸馏塔的质量估计和优化管理，石油炼制与化工，1994，25(5)：23-28
[39] Weber R., Brosilow C.B.. The use of secondary measurement to improve control. AIChE Journal, 1972, 18(3): 614-623
[40] Joseph B., Brosilow C.B.. Inferential control of process, AIChE Journal, 1978, 24(3): 485-509
[41] Tham M.T., Montague G.A., Morris A.J., Lant P.A.. Soft-sensors for process estimation and inferential control, Journal of Process Control, 1991, 1(1): 3-14
[42] Tham M.T., Morris A.J., Montague G.A.. Soft-sensing: a solution to the problem of measurement delays. Chemical Engineering Res. Des., 1989, 67(6): 547-554
[43] Guilandoust M.T., Morris A.J., Tham M.T.. An adaptive estimation algorithm for inferential control, Ind. Eng. Chem. Res., 1988, 27(9): 1658-1664
[44] 王旭东，邵惠鹤．基于事件的建模问题的分析和解决，化工自动化及仪表，1997，24(1)：10-13
[45] Wise B.M., Gallagher N.B.. The process chemometrics approach to process monitoring and fault detection, Journal of Process Control, 1996, 6(6): 329-348
[46] Chem G., McAvoy T.J., Piovoso M.J.. A multivariate statistical controller for on-line quality improvement, Journal of Process Control, 1998, 8(2): 139-149
[47] Frank B.E., Friedman J.H.. A statistical view of some chemometrics regression tools, Technometrics, 1993, 35(2): 109-135
[48] Geladi P.. Notes on the history and nature of PLS modeling, Journal of Chemometrics, 1988, 2:231-246
[49] Hoskuldsson A.. PLS regression methods, Journal of Chemometrics, 1988, 2:211-228
[50] Geladi P., Kowalski B.R.. Partial least-squares regression: a tutorial, Analytical Chimica Acta, 1986, 185:1-17
[51] Lindgren F., Geladi P., Wold S.. The kernel algorithm for PLS, Journal of Chemometrics, 1993, 7:45-59
[52] Rannar S., Lindgren F., Wold S.. A PLS kernel algorithm for data sets with many variables and fewer objects, part Ⅰ: Theory and algorithm, Journal of Chemometrics, 1995, 8: 111-125
[53] Dayal B.S., Macgregor J.E. Improved PLS algorithm, Journal of Chemometrics, 1997, 11: 73-85
[54] Zhu E., Barnes R.M.. A simple iteration algorithm for PLS regression, Journal of Chemometrics, 1995, 9:363-372
[55] Helland K., Bemtsen H.E., Borgen O.S., Martens H.. Recursive algorithm for partial least squares regression, Chemometrics and Intelligent Laboratory Systems, 1992, 14:129-137
[56] Qin S.J.. Recursive PLS algorithms for adaptive data modeling, Computers & Chemical Engineering, 1998, 22(4-5): 503-514
[57] Dayal B.S., MacGregor J.F.. Recursive exponentially weighted PLS and its applications to adaptive control and prediction, Journal of Process Control, 1997, 7 (3): 169-179
[58] 汪小勇，梁军，刘育明，王文庆．基于递推PLS的自适应软测量模型及其应用，浙江大学学报，2005，39(5)：676-680
[59] Wold S., Kettaneh-wold N., Skagerberg B.. Nonlinear PLS modeling, Chemometrics and Intelligent Laboratory Systems, 1989, 7:53-65
[60] Berglund A., Wold S.. INLR implicit non-linear latent variable regression, Journal of Chemometrics, 1997, 11:141-156
[61] Hoskuldsson A.. Quadratic PLS regression, Journal of Chemometrics, 1992, 6:307-334
[62] Wold S.. Nonlinear partial least squares modeling Ⅱ: Spline inner relation, Chemometrics and Intelligent Laboratory Systems, 1992, 14:71-84
[63] Qin S.J., McAvoy T.J.. Nonlinear PLS modeling using neural networks, Computers & Chemical Engineering, 1992, 16(4): 379-391
[64] Holcumb T.R., Morari M.. PLS/neural networks, Computers & Chemical Engineering, 1992, 16(4): 391-411
[65] 张英．基于支持向量机的过程工业数据挖掘技术研究，浙江大学博士学位论文，2005
[66] Vapnik V．N．(张学工译)．统计学习理论的本质，清华大学出版社，2000
[67] 张学工．关于统计学习理论与支持向量机，自动化学报，2000，26(1)：32-42
[68] Vapnik V．N．(许建华，张学工译)．统计学习理论，电子工业出版社，2004
[69] Smola A.J., Scholkopf B.. A tutorial on support vector regression, NeuroCOLT2 Technical Report Series NC2-TR-1998-030, Royal Holloway College, University of London, UK, 1998
[70] Platt J.C.. Using analytic QP and sparseness to speed training of support vector machines, Advances in neural information processing systems 11, M.S. Kearns, S.A. Solla, D.A. Cohn, eds., MIT Press, 1999, 557-563
[71] 邵信光，杨慧中，石晨曦．ε不敏感支持向量回归在化工数据建模中的应用，东南大学学报(自然科学版)，2004，34(增刊)：215-218
[72] 冯瑞，张浩然，邵惠鹤．基于SVM的软测量建模，信息与控制，2002，31(6)：567-571
[73] 朱国强，刘士荣，俞金寿．支持向量机及其在函数逼近中的应用，华东理工大学学报， 2002，28(5)：555-559
[74] 陆文聪，陈念贻，叶晨洲，李国正．支持向量机算法和软件ChemSVM介绍，计算机与应用化学，2002，19(6)：697-702
[75] 陆文聪，陈念贻，叶晨洲等．支持向量机用于民航安检炸药判别研究，计算机与应用化学，2002，19(6)：709-711
[76] 陈念贻，陆文聪．支持向量机算法在化学化工中的应用，计算机与应用化学，2002，19(6)：674-676
[77] 陈念贻，陆文聪，叶晨洲，李国正．支持向量机及其他核函数算法在化学计量学中的应用，计算机与应用化学，2002，19(6)：691-696
[78] 王华忠，俞金寿．核函数方法及其在软测量建模中的应用研究，自动化仪表，2004，25(10)：22-25
[79] Cauwenberghs G., Poggio T.. Incremental and decremental support vector machine learning, Advances in Neural Information Processing Systems (NIPS'2000) 13, MIT Press, Cambridge, MA, 2001
[80] 张英，苏宏业，褚健．基于ISVM的软测量建模及其在PX生产中的应用研究，控制与决策，2005，20(10)：1102-1106
[81] 阎威武，常俊林，邵惠鹤．基于滚动时间窗的最小二乘支持向量机回归估计方法及仿真，上海交通大学学报，2004，38(4)：524-526
[82] 叶楠，吕勇哉．模式识别在状态估计中的应用——类软测量技术，仪器仪表学报，1988，9(4)：368-374
[83] 穆罕默德·阿塔，祝如松，蒋慰孙．间歇精馏塔塔板效率的在线模式识别，信息与控制，1993，22(1)：47-49
[84] Hunt K.J., Sbarbaro D., Zbikowski R., Gawthrop P.J.. Neural networks for control systems - A survey, Automatica, 1992, 28(6): 1083-1112
[85] Willis M.J., Montague G.A., Massimo C.D., Tham M.T., Morris A.J.. Artificial neural networks in process estimation and control, Automatica, 1992, 28(6): 1181-1187
[86] Greg M.. Consider soft sensors. Chemical Engineering Progress, 1997, 93(7): 66-70
[87] Chen X., Gao F., Chen G. A soft-sensor development for melt-flow-length measurement during injection mold filling, Materials Science and Engineering A, 2004, 384(1-2): 245-254
[88] Karakuzu C., Türker M., Oztürk S.. Modeling, on-line state estimation and fuzzy control of production scale fed-batch baker's yeast fermentation, Control Engineering Practice, 2006, 14:959-974
[89] Devogelaere D., Rijckaert M., Leon O.G., Lemus G.C.. Application of feedforward neural networks for soft sensors in the sugar industry, IEEE Proceedings of the Ⅶ Brazilian Symposium on Neural Networks (SBRN'02), 11-14 Nov. 2002:2-6
[90] 王旭东，邵惠鹤．神经元网络建模技术与软测量技术，化工自动化及仪表，1996，23(2)：28-31
[91] Shi J., Liu X., Sun Y.. Melt index prediction by neural networks based on independent component analysis and multi-scale analysis, Neurocomputing, 2006, 70:280-287
[92] Fortuna L., Rizzo A., Sinatra M., Xibilia M.G.. Soft analyzers for a sulfur recovery unit, Control Engineering Practice, 2003, 11(12): 1491-1500
[93] 薄翠梅，张浞，林锦国，翟军勇，戴庆成．基于径向基函数神经网络的精馏塔优化控制，石油化工高等学校学报，2002，15(3)：58-61
[94] 邱书波，王化祥，刘雪真．RBF神经网络在卡伯值软测量中的应用，电子测量与仪器学报，2005，19(1)：30-34
[95] Izquierdo J.M.C., Dimitriadis Y.A., Sánchez E.G., Goronado J.P.. Learning from noisy information in FasArt and FasBack neuro-fuzzy systems, Neural Networks, 2001, 14: 407-425
[96] 仲蔚，俞金寿．基于Fuzzy ARTMAP的加氢裂化分馏塔MIMO软测量，化工学报，2000，51(5)：671-675
[97] Linkens D.A., Chen M.Y.. Input selection and partition validation for fuzzy modeling using neural network, Fuzzy Sets and Systems, 1999, 107(3): 299-308
[98] Takagi T., Sugeno M.. Fuzzy identification of systems and its applications to modeling and control, IEEE Transactions on Systems, Man and Cybernetics, 1985, 15(1): 116-132
[99] Sugeno M., Kang G.T.. Structure identification of fuzzy model, Fuzzy Sets and Systems, 1988, 28(1): 15-33
[100] Liu R., Su H., Mu S., Jia T., Chen W., Chu J.. Fuzzy neural network model of 4-CBA concentration for industrial purified terephthalic acid oxidation process, Chinese Journal of Chemical Engineering, 2004, 12(2): 234-239
[101] Runlder T.A., Gerstorfer E., Schlang M., Jünnemann E., Hollatz J.. Modelling and optimisation of a refining process for fibre board production, Control Engineering Practice, 2003, 11(11): 1229-1241
[102] 刘漫丹，杜文莉，钱锋．裂解炉燃料气热值的模糊神经网络软测量，计算机集成制造系统，2003，9(5)：412-416
[103] Qi H.Y., Zhou X.G., Liu L.H., Yuan W.K., A hybrid neural network-first principles model for fixed-bed reactor, Chemical Engineering Science, 1999, 54(13-14): 2521-2526
[104] 李向阳，朱学峰，刘焕彬，间歇制浆蒸煮过程的混合建模方法研究，中国造纸学报，2001，16(2)：24-28
[105] 仲蔚，俞金寿．软测量技术及其在加氢裂化分馏塔中的应用，华东理工大学学报，1999，25(4)：420-423
[106] Dai X., Wang W., Ding Y., Sun Z.. "Assumed inherent sensor" inversion based ANN dynamic soft-sensing method and its application in erythromycin fermentation process, Computers and Chemical Engineering, 2006, 30(8): 1203-1225
[107] 杨辉，柴天佑．稀土萃取分离过程的优化设定控制，控制与决策，2005，20(4)：398-402
[108] 许光，俞欢军，陶少辉，陈德钊．与机理杂交的支持向量机为发酵过程建模，化工学报，2005，56(4)：653-658
[109] Zhao Y.. A soft sensor based on nonlinear principal component analysis, IEEE Proceedings of the Second International Conference on Machine Learning and Cybernetics, Xi'an, 2-5 November 2003, 707-710
[110] Dam M., Saraf D.N.. Design of neural networks using genetic algorithm for on-line property estimation of crude fractionator products, Computers and Chemical Engineering, 2006, 30(4): 722-729
[111] 吕立华，宋执环，李平．用于过程软测量的多小波网络，仪器仪表学报，2002，23(5)：508-511
[112] Luo J., Shao H.. Soft sensing modeling using neurofuzzy system based on rough set theory, Proceedings of the American Control Conference, Anchorage, AK 8-10 May 2002, 543-548
[113] Liang H., Sun Z., Gu X.. Chaos-RBF network and its application in soft sensor of continuous catalytic reforming process, Proceedings of the 5th World Congress on Intelligent Control and Automation, Hangzhou, China, 15-19 June 2004, 2634-2638
[114] 常玉清，王小刚，王福利．基于多神经网络模型的软测量方法及应用，东北大学学报(自然科学版)，2005，26(6)：519-522
[115] 桂卫华，李勇刚，阳春华，陈志盛．基于改进聚类算法的分布式SVM及其应用，控制与决策，2004，19(8)：852-856
[116] 常玉清．软测量技术的研究与应用，东北大学博士学位论文，2002
[117] Dayal B. S., MacGregor J. F.. Multi-output process identification, Journal of process control, 1997, 7(4): 269-282
[118] Carpenter G. A, Grossberg S, Markuzon N, Reynolds J H.. Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps. IEEE Transactions on Neural Networks, 1992, 3: 698—713
[119] 杨行峻，郑君里．人工神经网络与盲信号处理，北京：清华大学出版社，2003，234-263
[120] Cano-Izquierdo J M, Dimitriadis Y, Lrpez-Coronado J. FasBack: Matching error based learning for automatic generation of fuzzy logic systems. Proceedings of the sixth IEEE International Conference on Fuzzy System, Barcelona, Spain, 1997, 3:1561—1566
[121] 邓正龙，化工中的优化方法，北京：化学工业出版社，1992，60-62
[122] Hagan M T, Menhaj M B.. Training feedforward networks with the Marquardt algorithm. IEEE Transanctions on Neural Networks, 1994, 5(6): 989-993
[123] Cao G, Alberto S, Massimo P.. Kinetics of p-xylene liqui-phase catalytic oxidation. AIChE J., 1994, 40:1156-1166
[124] 王丽军．PX氧化动力学研究及氧化反应器模拟，杭州：浙江大学，2001，26-31
[125] Takano, et al. Process for producing purified terephthalic acid. U. S. Patent: 5973196, Oct. 1999
[126] 陈渭泉，刘瑞兰，牟盛静，苏宏业．基于贝叶斯方法的4-CBA含量软测量研究，化工自动化及仪表，2003，30(5)：49-51
[127] Lindahl H A, et al. Method and apparatus for controlling the manufacture of terephthalic acid to control the level and vaniablity of the contaminant content and the optical density. U. S. Patent: 4835307, May
[128] Georgieva P., Meireles M.J., Feyo de Azevedo S., Knowledge-based hybrid modeling of a batch crystallization when accounting for nucleation, growth and agglomeration phenomena, Chemical Engineering Science, 2003, 58:3699-3713
[129] Wold S., Multi-way principal components and PLS-analysis, Journal of Chemometrics, 1987, 1:41-56
[130] 王慧文，偏最小二乘回归方法及其应用，北京，国防工业出版社，1995
[131] 林洪桦，动态测试数据处理，北京理工大学出版社，1995
[132] 苏宏业，刘瑞兰，荣冈，褚健，基于限定记忆部分最小二乘算法的4-CBA含量在线软测量建模方法，中国发明专利，CN1570629A
[133] 苏宏业，牟盛静，王长明，古勇，褚健，基于工业软测量模型的离线化验值双重校正算法，中国发明专利，CN1570627A
[134] 仲蔚，刘爱伦，俞金寿．多变量系统的软测量建模研究，控制与决策，2000，15(2)：209-212
[135] 肖嵘，王继成，孙正兴，张福炎．一种SVM增量学习算法α-ISVM，软件学报，2001，12(12)：1818-1824
[136] 阎威武，邵惠鹤．支持向量机和最小二乘支持向量机的比较及应用研究，控制与决策，2003，18(3)：358-360
[137] Dunn J. C.. A fuzzy relative of the ISODATA process and its use in detecting compact well separated cluster, Journal of Cybernet, 1974, 3:32-57
[138] Bezdek J. C.. A convergence theorem for the fuzzy ISODATA clustering algorithm, IEEE Trans Pattern Anal March Intel, 1980, 2(1): 1-8
[139] Burges C. J. C.. A tutorial on Support Vector Machines for Pattern Recognition, Data Mining and Knowledge Discovery, 1998, 2(2): 1-47
[140] Chang C. C., Lin C. J.. Training Nu-support Vector Regression: Theory and Algorithms, Neural Computation, 2002, 14(2): 1959-1977
[141] Naqa I. E., Yang Y.. Relevance Feedback Based on Incremental Learning for Mammogram Retrieval, Image Processing, 2003, 4(2): 7-11
[142] Tax D. M. J., Duin R. P. W.. Data Domian Description using Support Vectors, Proc. of 8th European, Symposium on Artificial Neural Networks, Bruges, Belgium, 1999, 251-256
[143] Pavone D., Hotler G. System Approach Modeling Applied to the Eluxyl Process, Oil & Gas Science and Technology-rev, 2000, 55(4): 437-446
[144] Minceva M., Rodrigues A. E.. Modeling and Simulation of a Simulated Moving Bed for the Separation ofp-Xylene, Ind. Eng. Chem. Res., 2002, 41:3454-3461
[2] Joseph B., Brosilow C.B.. Inferential control of process: part Ⅰ. Steady state analysis and design, AIChE Journal, 1978, 24(3): 485-492
[3] Brosilow C.B., Tong M.. Inferential control of process: part Ⅱ. The structure and dynamics of inferential control system, AIChE Journal, 1978, 24(3): 492-500
[4] Joseph B., Brosilow C.B.. Inferential control of process: part Ⅲ. Construction of optimal and suboptimal dynamic estimators, AIChE Journal, 1978, 24(3): 500-509
[5] 俞金寿，刘爱伦，张克进．软测量技术及其在石油化工中的应用，化学工业出版社，2000
[6] McAvoy T.J.. Contemplative stance for chemical process control-an IFAC report, Automatica, 1992, 28(2): 441-442
[7] 仲蔚．软测量与先进控制策略研究及其在石油化工过程中的应用，华东理工大学博士学位论文，1999
[8] Araúzo-Bravo M J, et al.. Automatization of a penicillin production process with soft sensors and an adaptive controller based on neuro fuzzy systems. Control Engineering Practice, 2004, 12: 1073—1090
[9] 刘瑞兰，苏宏业，褚健．PLS回归软测量方法在催化重整稳定油组分估计中的应用，化工自动化及仪表，2002，29(5)：44-47
[10] Er M.J., Liao J., Lin J.. Fuzzy neural networks-based quality prediction system for sintering process, IEEE Transactions on Fuzzy Systems, 2000, 8(3): 314-324
[11] Teppola P., Mujunen S., Minkkinen P.. A combined approach of partial least squares and fuzzy c-means clustering for the monitoring of an activated-sludge waste-water treatment plant, Chemometfics and Intelligent Laboratory Systems, 1998, 41 (1): 95-103
[12] Fortuna L., Graziani S., Xibilia M.G.. Soft sensors for product quality monitoring in debutanizer distillation columns, Control Engineering Pratice, 2005, 13(4): 499-508
[13] Antony S.J., Zhou C.H., Wang X.. An integrated mechanistic-neural network modeling for granular systems, Applied Mathematical Modelling, 2006, 30(1): 116-128
[14] Desai K., Badhe Y., Tambe S.S., Kulkarni B.D.. Soft-sensor development for fed-batch bioreactors using support vector regression, Biochemical Engineering Journal, 2006, 27(3): 225-239
[15] 刘涵，刘丁，郑岗，梁炎明，宋念龙．基于最小二乘支持向量机的天然气负荷预测，化工学报，2004，55(5)：828-832
[16] 罗荣富，邵惠鹤．推断控制中二次变量选择方法的研究，1992年控制与决策学术年会 论文集，控制与决策编委会出版，1992
[17] 刘良宏，周兴贵，袁渭康．非线性分布参数系统状态估计的最佳测量位置，化工学报，1996，47(3)：267-272
[18] Zamprogna E., Barolo M., Seborg D.E.. Optimal selection of soft sensors inputs for batch distillation columns using principal component analysis, Journal of Process Control, 2005, 15(1): 39-52
[19] 马朝阳，苏宏业，傅永峰，褚健．基于KPCA-SVR方法的复合肥养分含量建模，中国科学技术大学学报，2005，35(增刊)：314—321
[20] Luo J.X., Shao H.H.. Selecting secondary measurements for soft sensor modeling using rough sets theory, Proceedings of the 4th World Congress on Intelligent Control and Automation, June 10-14 2002, Shanghai, China, 415-419
[21] 刘瑞兰，陈渭泉，苏宏业．基于改进GA-PLS算法的最优辅助变量选择及其在软测量建模中的应用，南京邮电大学学报(自然科学科学版)，2006，26(1)：76-80
[22] 李华生，董文葆，袁一．化工过程测量数据中过失误差的侦破，炼油化工自动化，1992，(2)：16-20
[23] Narasimhan S., Mah R.S.H.. Generalized likelihood ratio method for gross error identification, AIChE Journal, 1987, 33(9): 1514-1521
[24] Michael L., Mark A.. Modeling chemical processes using prior knowledge and neural networks, AIChE Journal, 1994, 40(8): 1328-1340
[25] 陈剑．数据校正理论及其应用研究，浙江大学硕士学位论文，2000
[26] Yang S.H., Chen B.H., Wang X.Z.. Neural network based fault diagnosis using unmeasurable inputs, Engineering Applications of Artificial Intelligence, 2000, (13): 345-356
[27] 于静江，周春晖．过程控制中的软测量技术，控制理论与应用，1996，13(2)137-144
[28] 涂植英，朱麟章．过程控制系统，机械工业出版社，1998
[29] 刘瑞兰．软测量技术若干问题的研究及工业应用，浙江大学博士学位论文，2004
[30] 宋凯，王海青，李平．折息递推PLS算法及其在橡胶混炼质量控制中的应用，化工学报，2004，55(6)：942-946
[31] 张英，苏宏业，褚健．基于ISVM的软测量建模及其在PX生产中的应用研究，控制与决策，2005，20(10)：1102-1106
[32] Feng R., Zhang Y.J., Zhang Y.Z., Shao H.H.. Drifting modeling method using weighted support vector machines with application to soft sensor, Acta Automatica Sinica, 2004, 30(3): 436-441
[33] 李春富，Zhang J．，王桂增．基于PLS模型的自适应间歇过程质量预测，清华大学学报(自然科学版)，2004，44(10)：1360-1363
[34] 鄂加强，王耀南，梅炽．铜精炼过程铜液温度软测量模型及应用，化工学报，2006， 57(1)：203-209
[35] Mu S., Zeng Y., Liu R., Wu P., Su H., Chu J.. Online dual updating with recursive PLS model and its application in predicting crystal size of purified terephthalic acid (PTA) process, Journal of Process Control, 2006, 16(6): 557-566
[36] Zhou L., Lu Y.Z.. Modeling and control for nonlinear time-delay system via pattern recognition approach, Preprints of 2nd IFAC workshop on artificial intelligence in real time control, 1989, 7-12
[37] 黄克瑾．精馏过程的模型化及仿真，浙江大学博士学位论文，1992
[38] 丁云，于静江，周春晖．原油蒸馏塔的质量估计和优化管理，石油炼制与化工，1994，25(5)：23-28
[39] Weber R., Brosilow C.B.. The use of secondary measurement to improve control. AIChE Journal, 1972, 18(3): 614-623
[40] Joseph B., Brosilow C.B.. Inferential control of process, AIChE Journal, 1978, 24(3): 485-509
[41] Tham M.T., Montague G.A., Morris A.J., Lant P.A.. Soft-sensors for process estimation and inferential control, Journal of Process Control, 1991, 1(1): 3-14
[42] Tham M.T., Morris A.J., Montague G.A.. Soft-sensing: a solution to the problem of measurement delays. Chemical Engineering Res. Des., 1989, 67(6): 547-554
[43] Guilandoust M.T., Morris A.J., Tham M.T.. An adaptive estimation algorithm for inferential control, Ind. Eng. Chem. Res., 1988, 27(9): 1658-1664
[44] 王旭东，邵惠鹤．基于事件的建模问题的分析和解决，化工自动化及仪表，1997，24(1)：10-13
[45] Wise B.M., Gallagher N.B.. The process chemometrics approach to process monitoring and fault detection, Journal of Process Control, 1996, 6(6): 329-348
[46] Chem G., McAvoy T.J., Piovoso M.J.. A multivariate statistical controller for on-line quality improvement, Journal of Process Control, 1998, 8(2): 139-149
[47] Frank B.E., Friedman J.H.. A statistical view of some chemometrics regression tools, Technometrics, 1993, 35(2): 109-135
[48] Geladi P.. Notes on the history and nature of PLS modeling, Journal of Chemometrics, 1988, 2:231-246
[49] Hoskuldsson A.. PLS regression methods, Journal of Chemometrics, 1988, 2:211-228
[50] Geladi P., Kowalski B.R.. Partial least-squares regression: a tutorial, Analytical Chimica Acta, 1986, 185:1-17
[51] Lindgren F., Geladi P., Wold S.. The kernel algorithm for PLS, Journal of Chemometrics, 1993, 7:45-59
[52] Rannar S., Lindgren F., Wold S.. A PLS kernel algorithm for data sets with many variables and fewer objects, part Ⅰ: Theory and algorithm, Journal of Chemometrics, 1995, 8: 111-125
[53] Dayal B.S., Macgregor J.E. Improved PLS algorithm, Journal of Chemometrics, 1997, 11: 73-85
[54] Zhu E., Barnes R.M.. A simple iteration algorithm for PLS regression, Journal of Chemometrics, 1995, 9:363-372
[55] Helland K., Bemtsen H.E., Borgen O.S., Martens H.. Recursive algorithm for partial least squares regression, Chemometrics and Intelligent Laboratory Systems, 1992, 14:129-137
[56] Qin S.J.. Recursive PLS algorithms for adaptive data modeling, Computers & Chemical Engineering, 1998, 22(4-5): 503-514
[57] Dayal B.S., MacGregor J.F.. Recursive exponentially weighted PLS and its applications to adaptive control and prediction, Journal of Process Control, 1997, 7 (3): 169-179
[58] 汪小勇，梁军，刘育明，王文庆．基于递推PLS的自适应软测量模型及其应用，浙江大学学报，2005，39(5)：676-680
[59] Wold S., Kettaneh-wold N., Skagerberg B.. Nonlinear PLS modeling, Chemometrics and Intelligent Laboratory Systems, 1989, 7:53-65
[60] Berglund A., Wold S.. INLR implicit non-linear latent variable regression, Journal of Chemometrics, 1997, 11:141-156
[61] Hoskuldsson A.. Quadratic PLS regression, Journal of Chemometrics, 1992, 6:307-334
[62] Wold S.. Nonlinear partial least squares modeling Ⅱ: Spline inner relation, Chemometrics and Intelligent Laboratory Systems, 1992, 14:71-84
[63] Qin S.J., McAvoy T.J.. Nonlinear PLS modeling using neural networks, Computers & Chemical Engineering, 1992, 16(4): 379-391
[64] Holcumb T.R., Morari M.. PLS/neural networks, Computers & Chemical Engineering, 1992, 16(4): 391-411
[65] 张英．基于支持向量机的过程工业数据挖掘技术研究，浙江大学博士学位论文，2005
[66] Vapnik V．N．(张学工译)．统计学习理论的本质，清华大学出版社，2000
[67] 张学工．关于统计学习理论与支持向量机，自动化学报，2000，26(1)：32-42
[68] Vapnik V．N．(许建华，张学工译)．统计学习理论，电子工业出版社，2004
[69] Smola A.J., Scholkopf B.. A tutorial on support vector regression, NeuroCOLT2 Technical Report Series NC2-TR-1998-030, Royal Holloway College, University of London, UK, 1998
[70] Platt J.C.. Using analytic QP and sparseness to speed training of support vector machines, Advances in neural information processing systems 11, M.S. Kearns, S.A. Solla, D.A. Cohn, eds., MIT Press, 1999, 557-563
[71] 邵信光，杨慧中，石晨曦．ε不敏感支持向量回归在化工数据建模中的应用，东南大学学报(自然科学版)，2004，34(增刊)：215-218
[72] 冯瑞，张浩然，邵惠鹤．基于SVM的软测量建模，信息与控制，2002，31(6)：567-571
[73] 朱国强，刘士荣，俞金寿．支持向量机及其在函数逼近中的应用，华东理工大学学报， 2002，28(5)：555-559
[74] 陆文聪，陈念贻，叶晨洲，李国正．支持向量机算法和软件ChemSVM介绍，计算机与应用化学，2002，19(6)：697-702
[75] 陆文聪，陈念贻，叶晨洲等．支持向量机用于民航安检炸药判别研究，计算机与应用化学，2002，19(6)：709-711
[76] 陈念贻，陆文聪．支持向量机算法在化学化工中的应用，计算机与应用化学，2002，19(6)：674-676
[77] 陈念贻，陆文聪，叶晨洲，李国正．支持向量机及其他核函数算法在化学计量学中的应用，计算机与应用化学，2002，19(6)：691-696
[78] 王华忠，俞金寿．核函数方法及其在软测量建模中的应用研究，自动化仪表，2004，25(10)：22-25
[79] Cauwenberghs G., Poggio T.. Incremental and decremental support vector machine learning, Advances in Neural Information Processing Systems (NIPS'2000) 13, MIT Press, Cambridge, MA, 2001
[80] 张英，苏宏业，褚健．基于ISVM的软测量建模及其在PX生产中的应用研究，控制与决策，2005，20(10)：1102-1106
[81] 阎威武，常俊林，邵惠鹤．基于滚动时间窗的最小二乘支持向量机回归估计方法及仿真，上海交通大学学报，2004，38(4)：524-526
[82] 叶楠，吕勇哉．模式识别在状态估计中的应用——类软测量技术，仪器仪表学报，1988，9(4)：368-374
[83] 穆罕默德·阿塔，祝如松，蒋慰孙．间歇精馏塔塔板效率的在线模式识别，信息与控制，1993，22(1)：47-49
[84] Hunt K.J., Sbarbaro D., Zbikowski R., Gawthrop P.J.. Neural networks for control systems - A survey, Automatica, 1992, 28(6): 1083-1112
[85] Willis M.J., Montague G.A., Massimo C.D., Tham M.T., Morris A.J.. Artificial neural networks in process estimation and control, Automatica, 1992, 28(6): 1181-1187
[86] Greg M.. Consider soft sensors. Chemical Engineering Progress, 1997, 93(7): 66-70
[87] Chen X., Gao F., Chen G. A soft-sensor development for melt-flow-length measurement during injection mold filling, Materials Science and Engineering A, 2004, 384(1-2): 245-254
[88] Karakuzu C., Türker M., Oztürk S.. Modeling, on-line state estimation and fuzzy control of production scale fed-batch baker's yeast fermentation, Control Engineering Practice, 2006, 14:959-974
[89] Devogelaere D., Rijckaert M., Leon O.G., Lemus G.C.. Application of feedforward neural networks for soft sensors in the sugar industry, IEEE Proceedings of the Ⅶ Brazilian Symposium on Neural Networks (SBRN'02), 11-14 Nov. 2002:2-6
[90] 王旭东，邵惠鹤．神经元网络建模技术与软测量技术，化工自动化及仪表，1996，23(2)：28-31
[91] Shi J., Liu X., Sun Y.. Melt index prediction by neural networks based on independent component analysis and multi-scale analysis, Neurocomputing, 2006, 70:280-287
[92] Fortuna L., Rizzo A., Sinatra M., Xibilia M.G.. Soft analyzers for a sulfur recovery unit, Control Engineering Practice, 2003, 11(12): 1491-1500
[93] 薄翠梅，张浞，林锦国，翟军勇，戴庆成．基于径向基函数神经网络的精馏塔优化控制，石油化工高等学校学报，2002，15(3)：58-61
[94] 邱书波，王化祥，刘雪真．RBF神经网络在卡伯值软测量中的应用，电子测量与仪器学报，2005，19(1)：30-34
[95] Izquierdo J.M.C., Dimitriadis Y.A., Sánchez E.G., Goronado J.P.. Learning from noisy information in FasArt and FasBack neuro-fuzzy systems, Neural Networks, 2001, 14: 407-425
[96] 仲蔚，俞金寿．基于Fuzzy ARTMAP的加氢裂化分馏塔MIMO软测量，化工学报，2000，51(5)：671-675
[97] Linkens D.A., Chen M.Y.. Input selection and partition validation for fuzzy modeling using neural network, Fuzzy Sets and Systems, 1999, 107(3): 299-308
[98] Takagi T., Sugeno M.. Fuzzy identification of systems and its applications to modeling and control, IEEE Transactions on Systems, Man and Cybernetics, 1985, 15(1): 116-132
[99] Sugeno M., Kang G.T.. Structure identification of fuzzy model, Fuzzy Sets and Systems, 1988, 28(1): 15-33
[100] Liu R., Su H., Mu S., Jia T., Chen W., Chu J.. Fuzzy neural network model of 4-CBA concentration for industrial purified terephthalic acid oxidation process, Chinese Journal of Chemical Engineering, 2004, 12(2): 234-239
[101] Runlder T.A., Gerstorfer E., Schlang M., Jünnemann E., Hollatz J.. Modelling and optimisation of a refining process for fibre board production, Control Engineering Practice, 2003, 11(11): 1229-1241
[102] 刘漫丹，杜文莉，钱锋．裂解炉燃料气热值的模糊神经网络软测量，计算机集成制造系统，2003，9(5)：412-416
[103] Qi H.Y., Zhou X.G., Liu L.H., Yuan W.K., A hybrid neural network-first principles model for fixed-bed reactor, Chemical Engineering Science, 1999, 54(13-14): 2521-2526
[104] 李向阳，朱学峰，刘焕彬，间歇制浆蒸煮过程的混合建模方法研究，中国造纸学报，2001，16(2)：24-28
[105] 仲蔚，俞金寿．软测量技术及其在加氢裂化分馏塔中的应用，华东理工大学学报，1999，25(4)：420-423
[106] Dai X., Wang W., Ding Y., Sun Z.. "Assumed inherent sensor" inversion based ANN dynamic soft-sensing method and its application in erythromycin fermentation process, Computers and Chemical Engineering, 2006, 30(8): 1203-1225
[107] 杨辉，柴天佑．稀土萃取分离过程的优化设定控制，控制与决策，2005，20(4)：398-402
[108] 许光，俞欢军，陶少辉，陈德钊．与机理杂交的支持向量机为发酵过程建模，化工学报，2005，56(4)：653-658
[109] Zhao Y.. A soft sensor based on nonlinear principal component analysis, IEEE Proceedings of the Second International Conference on Machine Learning and Cybernetics, Xi'an, 2-5 November 2003, 707-710
[110] Dam M., Saraf D.N.. Design of neural networks using genetic algorithm for on-line property estimation of crude fractionator products, Computers and Chemical Engineering, 2006, 30(4): 722-729
[111] 吕立华，宋执环，李平．用于过程软测量的多小波网络，仪器仪表学报，2002，23(5)：508-511
[112] Luo J., Shao H.. Soft sensing modeling using neurofuzzy system based on rough set theory, Proceedings of the American Control Conference, Anchorage, AK 8-10 May 2002, 543-548
[113] Liang H., Sun Z., Gu X.. Chaos-RBF network and its application in soft sensor of continuous catalytic reforming process, Proceedings of the 5th World Congress on Intelligent Control and Automation, Hangzhou, China, 15-19 June 2004, 2634-2638
[114] 常玉清，王小刚，王福利．基于多神经网络模型的软测量方法及应用，东北大学学报(自然科学版)，2005，26(6)：519-522
[115] 桂卫华，李勇刚，阳春华，陈志盛．基于改进聚类算法的分布式SVM及其应用，控制与决策，2004，19(8)：852-856
[116] 常玉清．软测量技术的研究与应用，东北大学博士学位论文，2002
[117] Dayal B. S., MacGregor J. F.. Multi-output process identification, Journal of process control, 1997, 7(4): 269-282
[118] Carpenter G. A, Grossberg S, Markuzon N, Reynolds J H.. Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps. IEEE Transactions on Neural Networks, 1992, 3: 698—713
[119] 杨行峻，郑君里．人工神经网络与盲信号处理，北京：清华大学出版社，2003，234-263
[120] Cano-Izquierdo J M, Dimitriadis Y, Lrpez-Coronado J. FasBack: Matching error based learning for automatic generation of fuzzy logic systems. Proceedings of the sixth IEEE International Conference on Fuzzy System, Barcelona, Spain, 1997, 3:1561—1566
[121] 邓正龙，化工中的优化方法，北京：化学工业出版社，1992，60-62
[122] Hagan M T, Menhaj M B.. Training feedforward networks with the Marquardt algorithm. IEEE Transanctions on Neural Networks, 1994, 5(6): 989-993
[123] Cao G, Alberto S, Massimo P.. Kinetics of p-xylene liqui-phase catalytic oxidation. AIChE J., 1994, 40:1156-1166
[124] 王丽军．PX氧化动力学研究及氧化反应器模拟，杭州：浙江大学，2001，26-31
[125] Takano, et al. Process for producing purified terephthalic acid. U. S. Patent: 5973196, Oct. 1999
[126] 陈渭泉，刘瑞兰，牟盛静，苏宏业．基于贝叶斯方法的4-CBA含量软测量研究，化工自动化及仪表，2003，30(5)：49-51
[127] Lindahl H A, et al. Method and apparatus for controlling the manufacture of terephthalic acid to control the level and vaniablity of the contaminant content and the optical density. U. S. Patent: 4835307, May
[128] Georgieva P., Meireles M.J., Feyo de Azevedo S., Knowledge-based hybrid modeling of a batch crystallization when accounting for nucleation, growth and agglomeration phenomena, Chemical Engineering Science, 2003, 58:3699-3713
[129] Wold S., Multi-way principal components and PLS-analysis, Journal of Chemometrics, 1987, 1:41-56
[130] 王慧文，偏最小二乘回归方法及其应用，北京，国防工业出版社，1995
[131] 林洪桦，动态测试数据处理，北京理工大学出版社，1995
[132] 苏宏业，刘瑞兰，荣冈，褚健，基于限定记忆部分最小二乘算法的4-CBA含量在线软测量建模方法，中国发明专利，CN1570629A
[133] 苏宏业，牟盛静，王长明，古勇，褚健，基于工业软测量模型的离线化验值双重校正算法，中国发明专利，CN1570627A
[134] 仲蔚，刘爱伦，俞金寿．多变量系统的软测量建模研究，控制与决策，2000，15(2)：209-212
[135] 肖嵘，王继成，孙正兴，张福炎．一种SVM增量学习算法α-ISVM，软件学报，2001，12(12)：1818-1824
[136] 阎威武，邵惠鹤．支持向量机和最小二乘支持向量机的比较及应用研究，控制与决策，2003，18(3)：358-360
[137] Dunn J. C.. A fuzzy relative of the ISODATA process and its use in detecting compact well separated cluster, Journal of Cybernet, 1974, 3:32-57
[138] Bezdek J. C.. A convergence theorem for the fuzzy ISODATA clustering algorithm, IEEE Trans Pattern Anal March Intel, 1980, 2(1): 1-8
[139] Burges C. J. C.. A tutorial on Support Vector Machines for Pattern Recognition, Data Mining and Knowledge Discovery, 1998, 2(2): 1-47
[140] Chang C. C., Lin C. J.. Training Nu-support Vector Regression: Theory and Algorithms, Neural Computation, 2002, 14(2): 1959-1977
[141] Naqa I. E., Yang Y.. Relevance Feedback Based on Incremental Learning for Mammogram Retrieval, Image Processing, 2003, 4(2): 7-11
[142] Tax D. M. J., Duin R. P. W.. Data Domian Description using Support Vectors, Proc. of 8th European, Symposium on Artificial Neural Networks, Bruges, Belgium, 1999, 251-256
[143] Pavone D., Hotler G. System Approach Modeling Applied to the Eluxyl Process, Oil & Gas Science and Technology-rev, 2000, 55(4): 437-446
[144] Minceva M., Rodrigues A. E.. Modeling and Simulation of a Simulated Moving Bed for the Separation ofp-Xylene, Ind. Eng. Chem. Res., 2002, 41:3454-3461