聚氯乙烯智能制造技术研究
|
摘要
数据挖掘技术是当今智能系统理论和技术的重要研究内容，它综合运用人工智能、计算智能、模式识别和数理统计等先进技术，从数据库中提取隐含在其中的有用信息和知识。本文充分利用数据挖掘技术的优点，对氯乙烯悬浮聚合过程进行了广泛研究，在PVC质量建模、聚合过程动态建模和引发体系优化等方面取得了许多研究成果，并在此基础上，提出了基于技术集成的PVC智能制造技术。
首先对数据挖掘技术在化工过程中的应用现状进行了综述，介绍了一些主要的数据挖掘研究方法，其中包括神经网络、遗传算法、遗传规划、主元分析、偏最小二乘法和粗集理论等，展望了数据挖掘技术在化工过程的应用前景，以及未来发展所需解决的问题。
针对颗粒特性这一PVC树脂的重要质量指标，采用多元回归分析方法建立了PVC平均粒径的回归模型，并运用趋势面分析方法研究不同搅拌转速下，纳米CaCO_3微乳液浓度和分散剂浓度等优化操作条件。
提出了基于组合神经网络—岭回归方法(SNNs-RR)的PVC颗粒特性预测方法，采用岭回归方法来选择合适的组合权重。通过与单一神经网络模型比较，结果表明采用SNNs-RR方法建立的组合模型具有更佳的预测精度和鲁棒性。
通过对反应器内反应混合物和冷却回路的热传递平衡进行分析，建立了PVC反应器的动态热量传递模型。由于考虑了反应过程中反应物质量及其比热的变化，所建的模型能准确地描述氯乙烯悬浮聚合过程的动态特性。运用此模型对氯乙烯悬浮聚合过程的反应速率、转化率和注水速率等过程状态和操作条件进行了必要的分析。
为了充分利用PVC反应器的冷却能力，氯乙烯悬浮聚合过程的反应速率最好能维持在一个与聚合反应系统最大冷却能力相符的水平上，解决该问题的常规方法是采用高低效引发剂相结合的复合引发体系。通过分析氯乙烯悬浮聚合过程的反应动力学，提出了引发体系的优化模型，并成功应用于二元复合引发体系的优化。
根据PVC智能制造技术的目标是将氯乙烯悬浮聚合过程的动态模型、新型仪表、多元统计方法及先进控制算法等反应控制手段实现于协调的系统集成中，提
浙江工业大学硕士学位论文
出了基于技术集成的PVC智能制造技术，其中涉及到氯乙烯悬浮聚合过程模拟技
术、先进控制与软测量技术、过程性能监测与故障诊断技术等。
本文充分运用信息技术为优化聚合配方和工艺条件，为提高PVC产品质量提
供了有效的研究手段，有助于进一步开展聚合过程先进控制、在线优化和故障诊
断等方面的研究，有利于促进智能制造技术在其它聚合物生产中得到进一步应用，
为数据挖掘技术在化工过程中应用提供一种示范。
Data mining, a rising technique nowadays, combines many advanced techniques, such as artificial intelligence, computational intelligence, pattern recognition, statistic etc., to mine and discover valuable and hidden knowledge from databases. Vinyl chloride suspension polymerization is widely studied by making full use of data mining in this paper. Many achievements about quality modeling of polyvinyl chloride (PVC), dynamic modeling of polymerization and optimization of initiation system are gained, and intelligent manufacturing technology (IMT) of PVC based on technology integration is presented.
Firstly, the status of research and major achievements in the research of data mining technique in the chemical process are reviewed. Some primary methods in data mining are introduced including methods of artificial neural network (ANN), genetic algorithm (GA), genetic programming (GP), principal component analysis (PCA), partial least square (PLS), rough set (RS), etc. The application prospect, existing problems which needed solving for further developing are analyzed.
Aimed at the importance of PVC particle feature, the regression model of the mean grain diameter is developed by using multiple nonlinear regression. The optimum operational conditions about the concentration of dispersant and nano-CaCO3 microemulsion is attained by using trend surface analysis.
Inferential estimation of PVC quality using stacked neural networks - ridge regression (SNNs-RR) approach is studied, and determination of appropriate weights for combining individual networks using ridge regression is proposed. Neural network generalization capacity can be improved by combining several neural networks. The results obtained demonstrate significant improvements in model accuracy and robustness, as a result of using SNNs model, compared to using single neural network model.
Based on heat transfer process form the reactants to the reactor wall and from the inner wall to the coolant in the jacket, the dynamic heat balances for the PVC reactor is developed. Since the changes in both the mass of the reactants in the reactor and its specific heat are considered, the model can be used to exactly describe the dynamic characteristic of vinyl chloride suspension polymerization. The analysis of the reaction
rate, conversion and the rate of water draining is provided.
In order to take full advantage of the PVC reactor cooling capacity, the polymerization rate must be kept approximately constant at a level which yields a reaction rate equal to the common maximum cooling capacity of the system. The common solution to this problem is to use a combination of rapid and slow initiators. The optimal formulation of initiation system is studied as an optimization problem based on reaction kinetics. The optimization model of initiation system is developed, and optimization of initiation system containing two initiators is successfully implemented.
IMT of PVC based on technology integration is presented. Its objective is the harmonious integration of the dynamic model of vinyl chloride suspension polymerization, advanced sensors, multivariable statistical approaches and advanced process control strategy. It relates to dynamic simulation technique of vinyl chloride suspension polymerization, advanced control and soft sensor technique, process performance monitoring and diagnosis, etc.
An effective research approach about improving quality of PVC by using information technology is provided. The results might be helpful to correlative study (advanced control, on-line optimization, diagnosis, etc.) in vinyl chloride suspension polymerization. The achievements also provide a basis for the further application of IMT in the production of others polymer, and provide an instantiation for the application of data mining in chemical process.
首先对数据挖掘技术在化工过程中的应用现状进行了综述，介绍了一些主要的数据挖掘研究方法，其中包括神经网络、遗传算法、遗传规划、主元分析、偏最小二乘法和粗集理论等，展望了数据挖掘技术在化工过程的应用前景，以及未来发展所需解决的问题。
针对颗粒特性这一PVC树脂的重要质量指标，采用多元回归分析方法建立了PVC平均粒径的回归模型，并运用趋势面分析方法研究不同搅拌转速下，纳米CaCO_3微乳液浓度和分散剂浓度等优化操作条件。
提出了基于组合神经网络—岭回归方法(SNNs-RR)的PVC颗粒特性预测方法，采用岭回归方法来选择合适的组合权重。通过与单一神经网络模型比较，结果表明采用SNNs-RR方法建立的组合模型具有更佳的预测精度和鲁棒性。
通过对反应器内反应混合物和冷却回路的热传递平衡进行分析，建立了PVC反应器的动态热量传递模型。由于考虑了反应过程中反应物质量及其比热的变化，所建的模型能准确地描述氯乙烯悬浮聚合过程的动态特性。运用此模型对氯乙烯悬浮聚合过程的反应速率、转化率和注水速率等过程状态和操作条件进行了必要的分析。
为了充分利用PVC反应器的冷却能力，氯乙烯悬浮聚合过程的反应速率最好能维持在一个与聚合反应系统最大冷却能力相符的水平上，解决该问题的常规方法是采用高低效引发剂相结合的复合引发体系。通过分析氯乙烯悬浮聚合过程的反应动力学，提出了引发体系的优化模型，并成功应用于二元复合引发体系的优化。
根据PVC智能制造技术的目标是将氯乙烯悬浮聚合过程的动态模型、新型仪表、多元统计方法及先进控制算法等反应控制手段实现于协调的系统集成中，提
浙江工业大学硕士学位论文
出了基于技术集成的PVC智能制造技术，其中涉及到氯乙烯悬浮聚合过程模拟技
术、先进控制与软测量技术、过程性能监测与故障诊断技术等。
本文充分运用信息技术为优化聚合配方和工艺条件，为提高PVC产品质量提
供了有效的研究手段，有助于进一步开展聚合过程先进控制、在线优化和故障诊
断等方面的研究，有利于促进智能制造技术在其它聚合物生产中得到进一步应用，
为数据挖掘技术在化工过程中应用提供一种示范。
Data mining, a rising technique nowadays, combines many advanced techniques, such as artificial intelligence, computational intelligence, pattern recognition, statistic etc., to mine and discover valuable and hidden knowledge from databases. Vinyl chloride suspension polymerization is widely studied by making full use of data mining in this paper. Many achievements about quality modeling of polyvinyl chloride (PVC), dynamic modeling of polymerization and optimization of initiation system are gained, and intelligent manufacturing technology (IMT) of PVC based on technology integration is presented.
Firstly, the status of research and major achievements in the research of data mining technique in the chemical process are reviewed. Some primary methods in data mining are introduced including methods of artificial neural network (ANN), genetic algorithm (GA), genetic programming (GP), principal component analysis (PCA), partial least square (PLS), rough set (RS), etc. The application prospect, existing problems which needed solving for further developing are analyzed.
Aimed at the importance of PVC particle feature, the regression model of the mean grain diameter is developed by using multiple nonlinear regression. The optimum operational conditions about the concentration of dispersant and nano-CaCO3 microemulsion is attained by using trend surface analysis.
Inferential estimation of PVC quality using stacked neural networks - ridge regression (SNNs-RR) approach is studied, and determination of appropriate weights for combining individual networks using ridge regression is proposed. Neural network generalization capacity can be improved by combining several neural networks. The results obtained demonstrate significant improvements in model accuracy and robustness, as a result of using SNNs model, compared to using single neural network model.
Based on heat transfer process form the reactants to the reactor wall and from the inner wall to the coolant in the jacket, the dynamic heat balances for the PVC reactor is developed. Since the changes in both the mass of the reactants in the reactor and its specific heat are considered, the model can be used to exactly describe the dynamic characteristic of vinyl chloride suspension polymerization. The analysis of the reaction
rate, conversion and the rate of water draining is provided.
In order to take full advantage of the PVC reactor cooling capacity, the polymerization rate must be kept approximately constant at a level which yields a reaction rate equal to the common maximum cooling capacity of the system. The common solution to this problem is to use a combination of rapid and slow initiators. The optimal formulation of initiation system is studied as an optimization problem based on reaction kinetics. The optimization model of initiation system is developed, and optimization of initiation system containing two initiators is successfully implemented.
IMT of PVC based on technology integration is presented. Its objective is the harmonious integration of the dynamic model of vinyl chloride suspension polymerization, advanced sensors, multivariable statistical approaches and advanced process control strategy. It relates to dynamic simulation technique of vinyl chloride suspension polymerization, advanced control and soft sensor technique, process performance monitoring and diagnosis, etc.
An effective research approach about improving quality of PVC by using information technology is provided. The results might be helpful to correlative study (advanced control, on-line optimization, diagnosis, etc.) in vinyl chloride suspension polymerization. The achievements also provide a basis for the further application of IMT in the production of others polymer, and provide an instantiation for the application of data mining in chemical process.
引文
[1] 杨友麒．聚合物制造业的智能工厂[J]．石油化工自动化，2001，2：13～17．
[2] Chen, M.S., Han, J., Yu, P.S. Data mining: an overview from a database perspective[J].IEEE Trans. Knowl. Data Eng., 1996, 8(6): 866～883.
[3] Agrawal, R., Imielinski, T., Swami, A. Database mining: a performance perspective[J]. IEEE Trans. Knowl. Data Eng., 1993, 5(6): 914～925.
[4] Clifton, C., Thuraisingham, B. Emerging standards for data mining[J]. Comput. Stand. Interfaces, 2001, 23(3): 187～193.
[5] Kuisiak, A., Tseng, T.L. Data mining in engineering design: a case study[C]. Proc. IEEE Int. Conf Rob. Autom., USA, San Francisco, 2000, 1: 206～211.
[6] Mastrangelo, C.M., Porter, J.M. Data mining in a chemical process application[C].Proc. IEEE Int. Conf Syst. Man Cybern., USA, San Diego, 1998, 3: 2917～2921.
[7] Carbone, P.L. Expanding the meaning of and applications for data mining[C]. Proc. IEEE Int. Conf. Syst. Man Cybern., USA, Nashville, 2000, 3: 1872～1873.
[8] Han, J. Data mining techniques[C]. SIGMOD Rec., Can, Montreal, 1996, 25(2): 545.
[9] Mitra, S., Pal, S.K., Mitra, P. Data mining in soft computing framework: A survey[J]. IEEE Trans. Neural Networks, 2002, 13(1): 3～14.
[10] Dillon, T.S., Wang, D.H., Chang, E. Data mining using neural networks[J].Int. J. Eng. Intell. Syst. Electic Eng. Commun., 2001, 9(4): 187～194.
[11] Lu, H., Setiono, R., Liu, H. Effective data mining using neural networks[J]. IEEE Trans. Knowl. Data Eng., 1996, 8(6): 957～961.
[12] Bakshi, B.R., Stephanopoulos, G. Compression of chemical process data by functional approximation and feature extraction[J]. AIChE J., 1996, 42(2): 477～492.
[13] Nounou, M.N., Bakshi, B.R., Goel, K., Shen, X. Improving principal component analysis using Bayesian estimation[C].Proc. Am. Control Conf., VA, Arlington, 2001, 5: 3666～3671.
[14] Kamrani, A., Rong, W., Gonzalez, R. A genetic algorithm methodology for data mining and intelligent knowledge acquisition[J]. Comput. Ind. Eng., 2001, 40(4): 361～377.
[15] Podlena, J.R., Hendtlass, T. Accelerated genetic algorithm[J].Appl. Intell., 1998, 8(2):
103～111.
[16] Pawlak, Z. Rough set theory and its applications to data analysis[J].Cybern. Syst., 1998, 29(7): 661～688.
[17] Pawlak, Z., Grazymala-Busse, J., Slowinski, R.,Ziarko, W. Rough sets[J].Commun. ACM, 1995, 38(11): 88～95.
[18] Kryszkiewicz, M. Rough set approach to incomplete information systems[J].Inf. Sci., 1998, 112(1～4): 39～49.
[19] Brambilla, A., Trivella, F. Estimate product quality with ANNs[J].Hydrocarbon Process., 1996. 75(9): 61～66.
[20] Zhang, J., Morris, A.J., Martin, E.B. Long-term prediction models based on mixed order locally recurrent neural networks[J]. Comput. Chem. Eng., 1998, 22(7/8): 1051～1063.
[21] Hashem, S., Mathur, A., Famouri, P. Neural networks based chemical process models[C]. Proc. Int. Jt. Conf. Neural Networks, USA, Washington, DC, 1999: 6: 3948～3951.
[22] McKay, B., Willis, M., Barton, G. Steady-state modeling of chemical process systems using genetic programming[J]. Comput. Chem. Eng., 1997, 21(9): 981～996.
[23] Grosman, B., Lewin, D.R. Automated nonlinear model predictive control using genetic programming[J]. Comput. Chem. Eng., 2002, 26(4/5): 631～640.
[24] Szladow, A.J., Ziarko, W. Adaptive process control using rough sets[C]. Adv. Instrum. Control Int. Conf. Exhib., USA, Chicago, 1993, 48(2): 1421～1430.
[25] Xie, K., Chen, Z. Application of rough sets in intelligent control[C].Proc. Int. Symp. Test Meas., Shanghai, 2001, 1: 291～294.
[26] Hussain, M.A. Review of the applications of neural networks in chemical process controlsimulation and online implementation[J]. Artif. Intell. Eng.,1999, 13(1): 55～68.
[27] Willis, M.J., Montague, G.A., Di Massimo, C., Tham, M.T., Morris, A.J. Artificial neural networks in process estimation and control[J]. Automatica, 1992, 28(6): 1181～1187.
[28] Kavchak, M., Budman, H. Adaptive neural network structures for non-linear process estimation and control[J].Comput. Chem. Eng., 1999, 23(9): 1209～1228.
[29] Ramirez-Beltran, N.D., Jackson, H. Application of neural networks to chemical process control[J]. Comput. Ind. Eng., 1999, 37(1/2): 387～390.
[30] Al-Duwaish, H., Wasif, N. Nonlinear model predictive control of Hammerstein and Wiener models using genetic algorithms[C]. IEEE Conf. Control Appl. Proc., Mexico. 2001, 465～469.
[31] Ruiz, D., Nougues, J.M., Puigjaner, L. Artificial neural networks applied to on-line fault diagnosis in chemical plants[C].IEEE Symp. Emerging Technol. Fact. Autom. ETFA, Spain, Barcelona, 1999, 2: 977～986.
[32] Luan, D.N., Chang, D.S., Chang, M.P., Yu, C.C. Diagnosis of abrupt faults using variable-structure neural network[J]. J. Chin. Inst. Eng. Trans. Chin. Inst. Eng. Ser. A, 2000, 23(5): 567～574.
[33] Martin, E.B., Morris, A.J., Zhang, J. Process performance monitoring using multivariate statistical process control[J]. IEE Proc. Control Theory Appl., 1996, 143(2): 132～144.
[34] Zhang, J., Martin, E.B., Morris, A.J. Process monitoring using non-linear statistical techniques[J]. Chem. Eng. J., 1997.67(3): 181～189.
[35] Wachs, A., Lewin, D.R. Improved PCA methods for process disturbance and failure identification[J]. AIChE J., 1999, 45(8): 1688～1700.
[36] Fourie, S.H., de Vail, P. Advanced process monitoring using an on-line non-linear multi-scale principal component analysis methodology[J]. Comput. Chem. Eng., 2000. 24(2): 755～760.
[37] Chen, J., Liu, J. Derivation of function space analysis based PCA control charts for batch process monitoring[J]. Chem. Eng. Sci., 2001, 56(10): 3289～3304.
[38] Chen, J., Liu, K.C. On-line batch process monitoring using dynamic PCA and dynamic PLS models[J]. Chem. Eng. Sci., 2002.57(1): 63～75.
[39] Lakshminarayanan, S., Shah, S.L., Nandakumar, K. Modeling and control of multivariable processes: Dynamic PLS approach[J]. AIChE J., 1997, 43(9): 2307～2322.
[40] Oller, N., Claudio, A., Giudici, R., Cuardani, R. Neural network based approach for optimization of industrial chemical processes[J]. Comput. Chem. Eng., 2000, 24(9): 2303～2314.
[41] Herjee, S., Dahule, R.K., Tambe, S.S., Ravetkar, D.D., Kulkarni, B.D. Consider genetic algorithms to optimize batch distillation[J]. Hydrocarbon Process., 2001, 80(9): 59～66.
[42] Grau, M.D., Nougues, J.M., Puigjaner, L. Obtention of the optimal feeding profile in a
fed-batch reactor using genetic algorithms[J]. Ind. Eng. Chem. Res., 2001, 40(6): 1488～1494.
[43] Edwards, K., Edgar, T.F., Manousiouthakis, V.I. Kinetic model reduction using genetic algorithms[J]. Comput. Chem. Eng., 1998, 22(1/2): 239～246.
[44] Han, S.S., May, G.S. Optimization of neural network structure and learning parameters using genetic algorithms[C]. Proc. Int. Conf. Tools Artif. Intell., Fr, Toulouse, 1996, 200～206.
[45] Mukherjee, P., Tambe, S.S., Kulkami, B.D., Nandi, S., Kumar, R. Reaction modeling and optimization using neural networks and genetic algorithms: Case study involving TS-1-catalyzed hydroxylation of benzene[J]. Ind. Eng. Chem. Res., 2002, 41(9): 2159～2169.
[46] Tan, S., Marvrovouniotis, M.L. Reducing data dimensionality through optimizing neural network inputs[J]. AIChE J., 1995, 41(6): 1471～1480.
[47] Chen, J., Liao, C.M. Dynamic process fault monitoring based on neural network and PCA[J]. J. Process Control, 2002, 12(2): 277～289.
[48] Min, K.G., Han, I.S., Han, C. Iterative error-based nonlinear PLS method for nonlinear chemical process modeling[J]. J. Chem. Eng. Jpn., 2002. 35(7): 613～625.
[49] Hiden, H.G., Willis, M.J., Tham, M.T.,Montague, G.A. Non-linear principal components analysis using genetic programming[J]. Comput. Chem. Eng., 1999, 23(3): 413～425.
[50] 严福英，潘祖仁．聚氯乙烯工艺学[M]．北京：化学工业出版社，1990，92～101．
[51] 韩和良，钱锦文，徐雨尧，李文学．纳米CaCO3微乳液存在下的万吨级氯乙烯原位聚合技术[J]．聚氯乙烯，2001，4：11～15，27．
[52] 潘祖仁，翁志学，黄志明．悬浮聚合[M]．北京：化学工业出版社，1997，180～191．
[53] 邓正龙．化工中的优化方法[M]．北京：化学工业出版社，1995，57～69．
[54] Sjoberg, J., Zhang, Q., Ljung, L. Benveniste, A., Delyon, B., Glorennec, P.Y., Hjalmarsson, H., Judisky, A. Nonlinear black-box modeling in system identification: a unified overview[J]. Automatica, 1995, 31(12): 1691～1724.
[55] Sridhar, D.V., Seagrave, R.C., Bartlett, E.B. Process Modeling Using Stacked Neural Networks[J]. AIChE J., 1996, 42(9): 2529～2539.
[56] Wolpert D H. Stacked generalization[J], Neural Networks, 1992, 5(2): 241～259.
[57] Ahmad, Z., Zhang, J. A comparison of different methods for combining multiple neural
networks models[C]. Proc. Int. Jt. Conf. Neural Networks, HI, Honolulu, 2002, 1: 828～833.
[58] Sridhar, D.V., Bartlett, E.B., Seagrave, R.C. Information theoretic approach for combining neural network process models[J]. Neural Networks, 1999, 12(6): 915～926.
[59] Zhang, J. Developing robust non-linear models through bootstrap aggregated neural networks[J]. Neurocomput., 1999, 25(1): 93～113.
[60] Zhang, J., Morris, A.J., Martin, E.B., Kiparissides, C. Prediction of polymer quality in batch polymerization reactors using robust neural networks[J]. Chem. Eng. J., 1998, 69(2): 135～143.
[61] 马永开，唐小我．线性组合预测模型优化问题研究[J]．系统工程理论与实践，1998，9：110～114，123．
[62] 丁岳维．交通量预测中组合预测参数估计方法的研究[J]．西安公路交通大学学报，1997，17(2B)：29～33．
[63] 胡上序，陈德钊．观测数据的分析与处理[M]．浙江：浙江大学出版社，2002，193～214．
[64] Dimitrators, J., Georgakis, C., El-Aasser, M.S., Klein, A. Dynamic modelling and state estimation for an emulsion copolymerization reactor[J]. Comput. Chem. Eng., 1989, 13(3): 21～33.
[65] 冯连芳，顾雪萍，王凯．搅拌反应器中反应热的实时监测Ⅰ．确定性动态模型的量热法[J]．化学反应工程与工艺，1999，15(1)：65～70．
[66] 顾雪萍，冯连芳，王凯．搅拌反应器中反应热的实时监测Ⅱ．搅拌放热反应过程的状态及参数估计[J]．化学反应工程与工艺，1999，15(2)：158～165．
[67] Bonvin, D., Valliere, P.D., Rippin, D.W. Application of estimation techniques to batch reactors-Ⅰ. modelling thermal effects[J]. Comput. Chem. Eng., 1989, 13(1/2): 1～9.
[68] Bonvin, D., Valliere, P.D. Application of estimation techniques to batch reactors-Ⅱ. experimental studies in state and parameter estimation[J]. Comput. Chem. Eng., 1989, 13(1/2): 11～20.
[69] Maschio, G, Ferrara, I., Bassani, C., Nieman, H. An integrated calorimetric approach for the scale-up of polymerization reactors[J]. Chem. Eng. Sci., 1999, 54(17/18): 3273～3282.
[70] Zeaiter, J., Gomes, V.G., Romagnoli, J.A., Barton, G.W. Inferential conversion monitoring and control in emulsion polymerization through calorimetric measurements[J].Chem. Eng. J.,
2002, 89(1～3): 37～45.
[71] Mejdell, T., Pettersen, T., Naustdal, C., Svendsen, H.F. Modelling of industrial S-PVC reactor[J]. Chem. Eng. Sci., 1999, 54(13/14): 2459～2466.
[72] Nagy, Z., Agachi, S. Model predictive control of a PVC batch reactor[J].Comput. Chem. Eng., 1997, 21(6): 571～591.
[73] Lewin, D.R. Modelling and control of an industrial PVC suspension polymerization reactor[J]. Comput. Chem. Eng., 1996, 20(Suppl): S865～S870.
[74] Crowe, C.M. Data reconciliation-progress and challenges[J]. J. Proc. Cont. 1996, 6(2/3): 89～94.
[75] Derrick, K.R. Unbiassed estimation in data reconciliation[J]. AIChE J. 1993, 40(8): 1330～1334.
[76] Tong, H.W., Crorve C.M. Detecting of gross errors in data reconciliation by principal component analysis[J]. AIChE J. 1995, 41(7): 1712～1722.
[77] Xie, T.Y., Hamielec, A.E., Wood, P.E., Woods, D.R. Experimental investigation of vinyl chloride polymerization at high conversion: mechanism, kinetics and modeling[J]. Polymer, 1991b, 32(3): 537～554.
[78] Burgess, R.H. Manufacturing and processing of PVC. Applied science publishers: London, 1982.
[79] Daupert, T.E., Danner, R.P. Data compilation tables of properties of pure compounds. Design institute for physical properties data: AIChE: New York, 1985.
[80] 黄志明，郭开诚，包永忠，尚国荣，余春荣，翁志学，宋晓玲，张新力．氯乙烯悬浮聚合计算机实时检测及智能化[J]．聚氯乙烯，2001，5：5～8，21．
[81] 郑继楚．聚合反应过程注水控制[J]．化工自动化及仪表，1999，26(2)：68～69．
[82] 陈树泉，肖卫国，曾力江，吴海虎．聚合釜的优化控制[J]．化工自动化及仪表，2000，27(4)：10～12．
[83] 蒋蔚孙，俞金寿．过程控制工程[M]．北京：中国石化出版社，1999，384～388．
[84] Pinto, J.C. Vinyl chloride suspension polymerization with constant rate: a number study of batch reactors, [J]. J. Vinyl Tech., 1990, 12(1): 7～12.
[85] Jose, M.P., Reinaldo, G. Optimization of a cocktail of initiators for suspension polymerization
of vinyl chloride in batch reactors[J]. Chem. Eng. Sci., 2001, 56(3): 1021～1028.
[86] Kiparissides, C., Daskalakis, G., Achilias. D.S., Sidiropoulou, E. Dynamic simulation of industrial poly(vinyl chloride) batch suspension polymerization reactors[J].Ind. Eng. Chem. Res., 1997, 36(4): 1253～1267.
[87] Xie, T.Y., Hamielec, A.E., Wood, P.E., Woods, D.R. Experimental investigation of vinyl chloride polymerization at high conversion: mechanism, kinetic and modelling[J]. J. Appl. Polym. Sci., 1991, 43(7): 1259-1269.
[88] Talamini, G., Visentini, A., Kerr, J. Bulk and suspension polymerization of vinyl chloride: the two-phase model[J]. Polymer, 1998, 39(10): 1879～1891.
[89] Xie, T.Y., Hamielec, A.E., Wood, P.E., Woods, D.R. Experimental investigation of vinyl chloride polymerization at high conversion—conversion and tracer response relationships[J]. J. Appl. Polym. Sci., 1990, 41(9/10): 2327～2347.
[90] 王桂增，王诗宓．高等过程控制[M]．北京：清华大学出版社，2002：159～187．
[91] 何小荣．化工过程优化[M]．北京：清华大学出版社，12～15．
[92] 单国荣，翁志学，黄志明，潘祖仁．复合引发剂体系下氯乙烯悬浮聚合动力学模型及应用[J]．高等学校化学学报，2000，21(12)：1928～1931．
[93] Penlidis, A. Polymer reaction engineering: from reaction kinetics to polymer reactor control[J]. Can. J. Chem. Eng., 1994, 72(3): 385～390.
[94] 赵东标，朱剑英．智能制造技术与系统的发展与研究[J]．中国机械工程，1999，10(8)：927～931．
[95] 魏源迁，徐金相，章宗城．智能制造技术及系统[J]．中国机械工程，1995，6(6)：14～16．
[96] 赵亚波．智能制造[J]．工业控制计算机，2002，15(3)：1～4．
[97] Kiparissides, C., Morris, J. Intelligent manufacturing of polymers[J]. Comput. Chem. Eng., 1996, 20(Suppl): S1113-S1118.
[98] Bretelle, D., Chua, E.S., Macchietto, S. Simulation and on-line scheduling of a PVC process for operator training[J]. Comput. Chem. Eng., 1994, 18(Suppl): S547～S551.
[99] Kiparissides, C. Polymerization reactor modeling: a review of recent developments and future directions[J]. Chem. Eng. Sci., 1996, 51(10A): 1637～1659.
[100] 陆恩锡，张慧娟．化工过程模拟及相关高新技术(Ⅱ)化工过程动态模拟[J]．化工进展，
2000, 19(1): 76～78.
[101] Embirucu, M., Lima, E.L., Pinto, J.G. Survey of advanced control of polymerization reactors[J]. Polym. Eng. Sci., 1996, 36(4): 433～447.
[102] Ohshima, M., Tanigaki, M. Quality control of polymer production processes[J]. J. Process Control, 2000, 10(2): 135～148.
[103] 陆恩锡，张慧娟，甄惠清．化工过程模拟及相关高新技术(Ⅲ)化工过程先进控制[J]．化工进展，2000，19(2)：71～74．
[104] 李海青，黄志尧．软测量技术原理及应用[M]．北京：化学工业出版社，2000，1～9．
[105] 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[M]．北京：化学工业出版社，2000，1～7．
[106] 李元，谢植，周东华，王纲．MPCA在间歇反应过程故障诊断中的引用[J]．化工自动化及仪表，2003，30(4)：10～12．
[107] 钱宇，李秀喜，程华农，江燕斌．化工过程运行系统的集成[J]．化工学报，2003，54(4)：557～563．
[2] Chen, M.S., Han, J., Yu, P.S. Data mining: an overview from a database perspective[J].IEEE Trans. Knowl. Data Eng., 1996, 8(6): 866～883.
[3] Agrawal, R., Imielinski, T., Swami, A. Database mining: a performance perspective[J]. IEEE Trans. Knowl. Data Eng., 1993, 5(6): 914～925.
[4] Clifton, C., Thuraisingham, B. Emerging standards for data mining[J]. Comput. Stand. Interfaces, 2001, 23(3): 187～193.
[5] Kuisiak, A., Tseng, T.L. Data mining in engineering design: a case study[C]. Proc. IEEE Int. Conf Rob. Autom., USA, San Francisco, 2000, 1: 206～211.
[6] Mastrangelo, C.M., Porter, J.M. Data mining in a chemical process application[C].Proc. IEEE Int. Conf Syst. Man Cybern., USA, San Diego, 1998, 3: 2917～2921.
[7] Carbone, P.L. Expanding the meaning of and applications for data mining[C]. Proc. IEEE Int. Conf. Syst. Man Cybern., USA, Nashville, 2000, 3: 1872～1873.
[8] Han, J. Data mining techniques[C]. SIGMOD Rec., Can, Montreal, 1996, 25(2): 545.
[9] Mitra, S., Pal, S.K., Mitra, P. Data mining in soft computing framework: A survey[J]. IEEE Trans. Neural Networks, 2002, 13(1): 3～14.
[10] Dillon, T.S., Wang, D.H., Chang, E. Data mining using neural networks[J].Int. J. Eng. Intell. Syst. Electic Eng. Commun., 2001, 9(4): 187～194.
[11] Lu, H., Setiono, R., Liu, H. Effective data mining using neural networks[J]. IEEE Trans. Knowl. Data Eng., 1996, 8(6): 957～961.
[12] Bakshi, B.R., Stephanopoulos, G. Compression of chemical process data by functional approximation and feature extraction[J]. AIChE J., 1996, 42(2): 477～492.
[13] Nounou, M.N., Bakshi, B.R., Goel, K., Shen, X. Improving principal component analysis using Bayesian estimation[C].Proc. Am. Control Conf., VA, Arlington, 2001, 5: 3666～3671.
[14] Kamrani, A., Rong, W., Gonzalez, R. A genetic algorithm methodology for data mining and intelligent knowledge acquisition[J]. Comput. Ind. Eng., 2001, 40(4): 361～377.
[15] Podlena, J.R., Hendtlass, T. Accelerated genetic algorithm[J].Appl. Intell., 1998, 8(2):
103～111.
[16] Pawlak, Z. Rough set theory and its applications to data analysis[J].Cybern. Syst., 1998, 29(7): 661～688.
[17] Pawlak, Z., Grazymala-Busse, J., Slowinski, R.,Ziarko, W. Rough sets[J].Commun. ACM, 1995, 38(11): 88～95.
[18] Kryszkiewicz, M. Rough set approach to incomplete information systems[J].Inf. Sci., 1998, 112(1～4): 39～49.
[19] Brambilla, A., Trivella, F. Estimate product quality with ANNs[J].Hydrocarbon Process., 1996. 75(9): 61～66.
[20] Zhang, J., Morris, A.J., Martin, E.B. Long-term prediction models based on mixed order locally recurrent neural networks[J]. Comput. Chem. Eng., 1998, 22(7/8): 1051～1063.
[21] Hashem, S., Mathur, A., Famouri, P. Neural networks based chemical process models[C]. Proc. Int. Jt. Conf. Neural Networks, USA, Washington, DC, 1999: 6: 3948～3951.
[22] McKay, B., Willis, M., Barton, G. Steady-state modeling of chemical process systems using genetic programming[J]. Comput. Chem. Eng., 1997, 21(9): 981～996.
[23] Grosman, B., Lewin, D.R. Automated nonlinear model predictive control using genetic programming[J]. Comput. Chem. Eng., 2002, 26(4/5): 631～640.
[24] Szladow, A.J., Ziarko, W. Adaptive process control using rough sets[C]. Adv. Instrum. Control Int. Conf. Exhib., USA, Chicago, 1993, 48(2): 1421～1430.
[25] Xie, K., Chen, Z. Application of rough sets in intelligent control[C].Proc. Int. Symp. Test Meas., Shanghai, 2001, 1: 291～294.
[26] Hussain, M.A. Review of the applications of neural networks in chemical process controlsimulation and online implementation[J]. Artif. Intell. Eng.,1999, 13(1): 55～68.
[27] Willis, M.J., Montague, G.A., Di Massimo, C., Tham, M.T., Morris, A.J. Artificial neural networks in process estimation and control[J]. Automatica, 1992, 28(6): 1181～1187.
[28] Kavchak, M., Budman, H. Adaptive neural network structures for non-linear process estimation and control[J].Comput. Chem. Eng., 1999, 23(9): 1209～1228.
[29] Ramirez-Beltran, N.D., Jackson, H. Application of neural networks to chemical process control[J]. Comput. Ind. Eng., 1999, 37(1/2): 387～390.
[30] Al-Duwaish, H., Wasif, N. Nonlinear model predictive control of Hammerstein and Wiener models using genetic algorithms[C]. IEEE Conf. Control Appl. Proc., Mexico. 2001, 465～469.
[31] Ruiz, D., Nougues, J.M., Puigjaner, L. Artificial neural networks applied to on-line fault diagnosis in chemical plants[C].IEEE Symp. Emerging Technol. Fact. Autom. ETFA, Spain, Barcelona, 1999, 2: 977～986.
[32] Luan, D.N., Chang, D.S., Chang, M.P., Yu, C.C. Diagnosis of abrupt faults using variable-structure neural network[J]. J. Chin. Inst. Eng. Trans. Chin. Inst. Eng. Ser. A, 2000, 23(5): 567～574.
[33] Martin, E.B., Morris, A.J., Zhang, J. Process performance monitoring using multivariate statistical process control[J]. IEE Proc. Control Theory Appl., 1996, 143(2): 132～144.
[34] Zhang, J., Martin, E.B., Morris, A.J. Process monitoring using non-linear statistical techniques[J]. Chem. Eng. J., 1997.67(3): 181～189.
[35] Wachs, A., Lewin, D.R. Improved PCA methods for process disturbance and failure identification[J]. AIChE J., 1999, 45(8): 1688～1700.
[36] Fourie, S.H., de Vail, P. Advanced process monitoring using an on-line non-linear multi-scale principal component analysis methodology[J]. Comput. Chem. Eng., 2000. 24(2): 755～760.
[37] Chen, J., Liu, J. Derivation of function space analysis based PCA control charts for batch process monitoring[J]. Chem. Eng. Sci., 2001, 56(10): 3289～3304.
[38] Chen, J., Liu, K.C. On-line batch process monitoring using dynamic PCA and dynamic PLS models[J]. Chem. Eng. Sci., 2002.57(1): 63～75.
[39] Lakshminarayanan, S., Shah, S.L., Nandakumar, K. Modeling and control of multivariable processes: Dynamic PLS approach[J]. AIChE J., 1997, 43(9): 2307～2322.
[40] Oller, N., Claudio, A., Giudici, R., Cuardani, R. Neural network based approach for optimization of industrial chemical processes[J]. Comput. Chem. Eng., 2000, 24(9): 2303～2314.
[41] Herjee, S., Dahule, R.K., Tambe, S.S., Ravetkar, D.D., Kulkarni, B.D. Consider genetic algorithms to optimize batch distillation[J]. Hydrocarbon Process., 2001, 80(9): 59～66.
[42] Grau, M.D., Nougues, J.M., Puigjaner, L. Obtention of the optimal feeding profile in a
fed-batch reactor using genetic algorithms[J]. Ind. Eng. Chem. Res., 2001, 40(6): 1488～1494.
[43] Edwards, K., Edgar, T.F., Manousiouthakis, V.I. Kinetic model reduction using genetic algorithms[J]. Comput. Chem. Eng., 1998, 22(1/2): 239～246.
[44] Han, S.S., May, G.S. Optimization of neural network structure and learning parameters using genetic algorithms[C]. Proc. Int. Conf. Tools Artif. Intell., Fr, Toulouse, 1996, 200～206.
[45] Mukherjee, P., Tambe, S.S., Kulkami, B.D., Nandi, S., Kumar, R. Reaction modeling and optimization using neural networks and genetic algorithms: Case study involving TS-1-catalyzed hydroxylation of benzene[J]. Ind. Eng. Chem. Res., 2002, 41(9): 2159～2169.
[46] Tan, S., Marvrovouniotis, M.L. Reducing data dimensionality through optimizing neural network inputs[J]. AIChE J., 1995, 41(6): 1471～1480.
[47] Chen, J., Liao, C.M. Dynamic process fault monitoring based on neural network and PCA[J]. J. Process Control, 2002, 12(2): 277～289.
[48] Min, K.G., Han, I.S., Han, C. Iterative error-based nonlinear PLS method for nonlinear chemical process modeling[J]. J. Chem. Eng. Jpn., 2002. 35(7): 613～625.
[49] Hiden, H.G., Willis, M.J., Tham, M.T.,Montague, G.A. Non-linear principal components analysis using genetic programming[J]. Comput. Chem. Eng., 1999, 23(3): 413～425.
[50] 严福英，潘祖仁．聚氯乙烯工艺学[M]．北京：化学工业出版社，1990，92～101．
[51] 韩和良，钱锦文，徐雨尧，李文学．纳米CaCO3微乳液存在下的万吨级氯乙烯原位聚合技术[J]．聚氯乙烯，2001，4：11～15，27．
[52] 潘祖仁，翁志学，黄志明．悬浮聚合[M]．北京：化学工业出版社，1997，180～191．
[53] 邓正龙．化工中的优化方法[M]．北京：化学工业出版社，1995，57～69．
[54] Sjoberg, J., Zhang, Q., Ljung, L. Benveniste, A., Delyon, B., Glorennec, P.Y., Hjalmarsson, H., Judisky, A. Nonlinear black-box modeling in system identification: a unified overview[J]. Automatica, 1995, 31(12): 1691～1724.
[55] Sridhar, D.V., Seagrave, R.C., Bartlett, E.B. Process Modeling Using Stacked Neural Networks[J]. AIChE J., 1996, 42(9): 2529～2539.
[56] Wolpert D H. Stacked generalization[J], Neural Networks, 1992, 5(2): 241～259.
[57] Ahmad, Z., Zhang, J. A comparison of different methods for combining multiple neural
networks models[C]. Proc. Int. Jt. Conf. Neural Networks, HI, Honolulu, 2002, 1: 828～833.
[58] Sridhar, D.V., Bartlett, E.B., Seagrave, R.C. Information theoretic approach for combining neural network process models[J]. Neural Networks, 1999, 12(6): 915～926.
[59] Zhang, J. Developing robust non-linear models through bootstrap aggregated neural networks[J]. Neurocomput., 1999, 25(1): 93～113.
[60] Zhang, J., Morris, A.J., Martin, E.B., Kiparissides, C. Prediction of polymer quality in batch polymerization reactors using robust neural networks[J]. Chem. Eng. J., 1998, 69(2): 135～143.
[61] 马永开，唐小我．线性组合预测模型优化问题研究[J]．系统工程理论与实践，1998，9：110～114，123．
[62] 丁岳维．交通量预测中组合预测参数估计方法的研究[J]．西安公路交通大学学报，1997，17(2B)：29～33．
[63] 胡上序，陈德钊．观测数据的分析与处理[M]．浙江：浙江大学出版社，2002，193～214．
[64] Dimitrators, J., Georgakis, C., El-Aasser, M.S., Klein, A. Dynamic modelling and state estimation for an emulsion copolymerization reactor[J]. Comput. Chem. Eng., 1989, 13(3): 21～33.
[65] 冯连芳，顾雪萍，王凯．搅拌反应器中反应热的实时监测Ⅰ．确定性动态模型的量热法[J]．化学反应工程与工艺，1999，15(1)：65～70．
[66] 顾雪萍，冯连芳，王凯．搅拌反应器中反应热的实时监测Ⅱ．搅拌放热反应过程的状态及参数估计[J]．化学反应工程与工艺，1999，15(2)：158～165．
[67] Bonvin, D., Valliere, P.D., Rippin, D.W. Application of estimation techniques to batch reactors-Ⅰ. modelling thermal effects[J]. Comput. Chem. Eng., 1989, 13(1/2): 1～9.
[68] Bonvin, D., Valliere, P.D. Application of estimation techniques to batch reactors-Ⅱ. experimental studies in state and parameter estimation[J]. Comput. Chem. Eng., 1989, 13(1/2): 11～20.
[69] Maschio, G, Ferrara, I., Bassani, C., Nieman, H. An integrated calorimetric approach for the scale-up of polymerization reactors[J]. Chem. Eng. Sci., 1999, 54(17/18): 3273～3282.
[70] Zeaiter, J., Gomes, V.G., Romagnoli, J.A., Barton, G.W. Inferential conversion monitoring and control in emulsion polymerization through calorimetric measurements[J].Chem. Eng. J.,
2002, 89(1～3): 37～45.
[71] Mejdell, T., Pettersen, T., Naustdal, C., Svendsen, H.F. Modelling of industrial S-PVC reactor[J]. Chem. Eng. Sci., 1999, 54(13/14): 2459～2466.
[72] Nagy, Z., Agachi, S. Model predictive control of a PVC batch reactor[J].Comput. Chem. Eng., 1997, 21(6): 571～591.
[73] Lewin, D.R. Modelling and control of an industrial PVC suspension polymerization reactor[J]. Comput. Chem. Eng., 1996, 20(Suppl): S865～S870.
[74] Crowe, C.M. Data reconciliation-progress and challenges[J]. J. Proc. Cont. 1996, 6(2/3): 89～94.
[75] Derrick, K.R. Unbiassed estimation in data reconciliation[J]. AIChE J. 1993, 40(8): 1330～1334.
[76] Tong, H.W., Crorve C.M. Detecting of gross errors in data reconciliation by principal component analysis[J]. AIChE J. 1995, 41(7): 1712～1722.
[77] Xie, T.Y., Hamielec, A.E., Wood, P.E., Woods, D.R. Experimental investigation of vinyl chloride polymerization at high conversion: mechanism, kinetics and modeling[J]. Polymer, 1991b, 32(3): 537～554.
[78] Burgess, R.H. Manufacturing and processing of PVC. Applied science publishers: London, 1982.
[79] Daupert, T.E., Danner, R.P. Data compilation tables of properties of pure compounds. Design institute for physical properties data: AIChE: New York, 1985.
[80] 黄志明，郭开诚，包永忠，尚国荣，余春荣，翁志学，宋晓玲，张新力．氯乙烯悬浮聚合计算机实时检测及智能化[J]．聚氯乙烯，2001，5：5～8，21．
[81] 郑继楚．聚合反应过程注水控制[J]．化工自动化及仪表，1999，26(2)：68～69．
[82] 陈树泉，肖卫国，曾力江，吴海虎．聚合釜的优化控制[J]．化工自动化及仪表，2000，27(4)：10～12．
[83] 蒋蔚孙，俞金寿．过程控制工程[M]．北京：中国石化出版社，1999，384～388．
[84] Pinto, J.C. Vinyl chloride suspension polymerization with constant rate: a number study of batch reactors, [J]. J. Vinyl Tech., 1990, 12(1): 7～12.
[85] Jose, M.P., Reinaldo, G. Optimization of a cocktail of initiators for suspension polymerization
of vinyl chloride in batch reactors[J]. Chem. Eng. Sci., 2001, 56(3): 1021～1028.
[86] Kiparissides, C., Daskalakis, G., Achilias. D.S., Sidiropoulou, E. Dynamic simulation of industrial poly(vinyl chloride) batch suspension polymerization reactors[J].Ind. Eng. Chem. Res., 1997, 36(4): 1253～1267.
[87] Xie, T.Y., Hamielec, A.E., Wood, P.E., Woods, D.R. Experimental investigation of vinyl chloride polymerization at high conversion: mechanism, kinetic and modelling[J]. J. Appl. Polym. Sci., 1991, 43(7): 1259-1269.
[88] Talamini, G., Visentini, A., Kerr, J. Bulk and suspension polymerization of vinyl chloride: the two-phase model[J]. Polymer, 1998, 39(10): 1879～1891.
[89] Xie, T.Y., Hamielec, A.E., Wood, P.E., Woods, D.R. Experimental investigation of vinyl chloride polymerization at high conversion—conversion and tracer response relationships[J]. J. Appl. Polym. Sci., 1990, 41(9/10): 2327～2347.
[90] 王桂增，王诗宓．高等过程控制[M]．北京：清华大学出版社，2002：159～187．
[91] 何小荣．化工过程优化[M]．北京：清华大学出版社，12～15．
[92] 单国荣，翁志学，黄志明，潘祖仁．复合引发剂体系下氯乙烯悬浮聚合动力学模型及应用[J]．高等学校化学学报，2000，21(12)：1928～1931．
[93] Penlidis, A. Polymer reaction engineering: from reaction kinetics to polymer reactor control[J]. Can. J. Chem. Eng., 1994, 72(3): 385～390.
[94] 赵东标，朱剑英．智能制造技术与系统的发展与研究[J]．中国机械工程，1999，10(8)：927～931．
[95] 魏源迁，徐金相，章宗城．智能制造技术及系统[J]．中国机械工程，1995，6(6)：14～16．
[96] 赵亚波．智能制造[J]．工业控制计算机，2002，15(3)：1～4．
[97] Kiparissides, C., Morris, J. Intelligent manufacturing of polymers[J]. Comput. Chem. Eng., 1996, 20(Suppl): S1113-S1118.
[98] Bretelle, D., Chua, E.S., Macchietto, S. Simulation and on-line scheduling of a PVC process for operator training[J]. Comput. Chem. Eng., 1994, 18(Suppl): S547～S551.
[99] Kiparissides, C. Polymerization reactor modeling: a review of recent developments and future directions[J]. Chem. Eng. Sci., 1996, 51(10A): 1637～1659.
[100] 陆恩锡，张慧娟．化工过程模拟及相关高新技术(Ⅱ)化工过程动态模拟[J]．化工进展，
2000, 19(1): 76～78.
[101] Embirucu, M., Lima, E.L., Pinto, J.G. Survey of advanced control of polymerization reactors[J]. Polym. Eng. Sci., 1996, 36(4): 433～447.
[102] Ohshima, M., Tanigaki, M. Quality control of polymer production processes[J]. J. Process Control, 2000, 10(2): 135～148.
[103] 陆恩锡，张慧娟，甄惠清．化工过程模拟及相关高新技术(Ⅲ)化工过程先进控制[J]．化工进展，2000，19(2)：71～74．
[104] 李海青，黄志尧．软测量技术原理及应用[M]．北京：化学工业出版社，2000，1～9．
[105] 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[M]．北京：化学工业出版社，2000，1～7．
[106] 李元，谢植，周东华，王纲．MPCA在间歇反应过程故障诊断中的引用[J]．化工自动化及仪表，2003，30(4)：10～12．
[107] 钱宇，李秀喜，程华农，江燕斌．化工过程运行系统的集成[J]．化工学报，2003，54(4)：557～563．