基于模糊在线支持向量回归的建模与预测控制研究
|
摘要
支持向量机是基于统计学习理论的学习机器，能够有效地处理小样本学习问题；并且支持向量机以结构风险最小化为原则，有效地克服了神经网络收敛慢、局部最优、泛化能力差等缺点。近年来支持向量机在模式识别、信号处理、系统建模和控制等方面都得到了广泛应用，逐渐成为了机器学习领域理论研究的新热点。常用的支持向量机训练算法都只能离线训练，而离线训练建立的模型很难适应非线性系统的实时变化，系统鲁棒性较差。因此本文在现有的研究基础之上，重点地研究了在线支持向量回归训练算法的理论与应用，在线支持向量回归是一种逐步迭代的支持向量机学习算法，并已成功应用于非线性时变系统建模与控制。本文的主要研究内容为：
(1)针对在线支持向量回归算法抗干扰能力差、训练速度慢等问题，提出了模糊在线支持向量回归(FOSVR)算法。FOSVR算法通过对样本设定不同的模糊隶属度、优化学习步骤，有效地提高了建模精度和训练速度，仿真实验验证了算法的有效性。
(2)生物发酵过程中重要的生物浓度变量难以在线测量，因此本文提出基于FOSVR算法的谷氨酸发酵过程软测量建模。利用FOSVR算法良好的泛化能力和在线学习能力，分别建立了菌体浓度和产物浓度的软测量模型；并且将机理模型和FOSVR软测量模型相结合，从而实现了对生物发酵过程的混合建模。
(3)针对常规非线性模型预测控制的预测模型容易失配的问题，提出采用FOSVR建立模型预测控制的预测模型。通过其在线学习能力有效的解决了预测模型失配问题，并主要研究了基于FOSVR的单步和多步模型预测控制的算法与实现；同时针对多步模型预测控制算法容易局部优化的缺点，采用粒子群优化算法求解目标函数，有效地提高了算法的全局优化能力。
(4)针对预测函数控制对非线性强和时变的实际对象控制效果不佳问题，提出基于FOSVR逆模型的非线性预测函数控制算法。通过引入FOSVR逆模型，将非线性预测函数控制转化为线性预测函数控制，既实现了非线性预测函数控制，同时又避免了复杂的非线性优化。为进一步提高算法的性能，针对传统基函数对参考轨迹的整体逼近性能并不理想的缺点，选取小波基函数为基函数，利用小波的紧支性和多尺度分析的特性，实现了优化变量的集结。
(5)针对发酵过程自动化水平低、生物浓度难以在线控制，采用基于FOSVR的预测控制调节谷氨酸发酵过程流加。在发酵过程集散控制系统的基础上，利用Delphi和Matlab的混合编程，从而实现了基于FOSVR的底物流加预测控制。通过对谷氨酸发酵的三次流加控制结果显示，流加预测控制有效的提高了最终产物浓度。
通过本文研究表明，FOSVR是一种有效的在线学习算法，不仅可以为补料分批生物发酵过程等复杂生化过程的建立准确模型，还可以实现基于此模型的先进控制算法，对于生化过程建模与控制具有重要意义。
Support vector machine (SVM) is a learning machine based on statistical learning theory,which can solve small sample learning problem effectively. According to minimum structurerisk principle, SVM overcomes shortcomings of neural network, such as slow convergence,local optimum, and bad generalization. Therefore, SVM has been widely applied to manyareas: pattern recognition, signal treatment, system modeling and control et al., it hasgradually become a research hotpot in machine learning area. Up to now, severial SVMtraining algorithms have been widely used, whereas these algorithms are almost offlinetraining, which can’t adapt to nonlinear system real-time change. Based on previous results,online support vector regression (OSVR) theory and application were mainly studied in thisthesis. An advantage of OSVR is online learning ability, which can adjust model parametersonline. The main contents of this thesis are:
(1) Fuzzy online support vector regression algorithm (FOSVR) is proposed to solveweak anti-jamming capability and slow training speed problems of OSVR. Through settingdifferent weighted factor to each sample and optimizing learning steps, FOSVR algorithmimproves model accuracy and training speed. Simulation results verified the improvements ofFOSVR algorithm.
(2) Biological concentrations of fermentation process are hardly measured online,FOSVR is proposed to model glutamate fermentation process. Through online learning abilityof FOSVR, biomass concentration and production concentration soft sensor model were built.Futhermore, combining first principle model and FOSVR soft sensor model, a hybrid modelstrategy is proposed for fermentration process.
(3) To solve predictive model mismatch problem, a nonlinear modle predictive control(MPC) based on FOSVR was proposed. FOSVR can modify predictive model parametersonline, single-step MPC and multi-step MPC were studied. Due to local optimum problem ofgradient decent method, particle swarm algorithm (PSO) was applied to rolling optimizemulti-step model predictive control.
(4) For predictive functional control (PFC) bad performance in strong nonlinear andtime-varying system control, a PFC based on FOSVR inverse model was proposed. FOSVRwas used to obtain the inverse model of the Wiener model nonlinear part, the nonlinear PFChas been transferred to linear control. In this way, nonlinear objective function can be solvedby linear optimum algorithm. Aiming to improve performance of PFC, wavelet basis functionwas selected as basis function of PFC. Due to compact support and multi-scale analysis ofwavelet, the optimal parameters are aggregated.
(5) Low automatic level of fermentation process and difficulty in biologicalconcentration control, therefore, the predictive control was employed to glutamatefermentation process feeding optimized control. Based on fermentation distribute controlsystem, Delphi and Matlab hybrid programing was used, so based on key biologicalconcentrations FOSVR model, substrate feeding predictive control was carried out. Throughthree feeding control experiments, the higher cumulative production concentrations were obtained.
Through the stuy of this thesis, it is shown that FOSVR is an effective online modelingalgorithm. The algorithm not only can be used in solving modeling problem of fed-batchfermentation process, but also provide a powerful tool in complexity biochemical processcontrol. The study of this thesis has important significance for biochemical process.
(1)针对在线支持向量回归算法抗干扰能力差、训练速度慢等问题，提出了模糊在线支持向量回归(FOSVR)算法。FOSVR算法通过对样本设定不同的模糊隶属度、优化学习步骤，有效地提高了建模精度和训练速度，仿真实验验证了算法的有效性。
(2)生物发酵过程中重要的生物浓度变量难以在线测量，因此本文提出基于FOSVR算法的谷氨酸发酵过程软测量建模。利用FOSVR算法良好的泛化能力和在线学习能力，分别建立了菌体浓度和产物浓度的软测量模型；并且将机理模型和FOSVR软测量模型相结合，从而实现了对生物发酵过程的混合建模。
(3)针对常规非线性模型预测控制的预测模型容易失配的问题，提出采用FOSVR建立模型预测控制的预测模型。通过其在线学习能力有效的解决了预测模型失配问题，并主要研究了基于FOSVR的单步和多步模型预测控制的算法与实现；同时针对多步模型预测控制算法容易局部优化的缺点，采用粒子群优化算法求解目标函数，有效地提高了算法的全局优化能力。
(4)针对预测函数控制对非线性强和时变的实际对象控制效果不佳问题，提出基于FOSVR逆模型的非线性预测函数控制算法。通过引入FOSVR逆模型，将非线性预测函数控制转化为线性预测函数控制，既实现了非线性预测函数控制，同时又避免了复杂的非线性优化。为进一步提高算法的性能，针对传统基函数对参考轨迹的整体逼近性能并不理想的缺点，选取小波基函数为基函数，利用小波的紧支性和多尺度分析的特性，实现了优化变量的集结。
(5)针对发酵过程自动化水平低、生物浓度难以在线控制，采用基于FOSVR的预测控制调节谷氨酸发酵过程流加。在发酵过程集散控制系统的基础上，利用Delphi和Matlab的混合编程，从而实现了基于FOSVR的底物流加预测控制。通过对谷氨酸发酵的三次流加控制结果显示，流加预测控制有效的提高了最终产物浓度。
通过本文研究表明，FOSVR是一种有效的在线学习算法，不仅可以为补料分批生物发酵过程等复杂生化过程的建立准确模型，还可以实现基于此模型的先进控制算法，对于生化过程建模与控制具有重要意义。
Support vector machine (SVM) is a learning machine based on statistical learning theory,which can solve small sample learning problem effectively. According to minimum structurerisk principle, SVM overcomes shortcomings of neural network, such as slow convergence,local optimum, and bad generalization. Therefore, SVM has been widely applied to manyareas: pattern recognition, signal treatment, system modeling and control et al., it hasgradually become a research hotpot in machine learning area. Up to now, severial SVMtraining algorithms have been widely used, whereas these algorithms are almost offlinetraining, which can’t adapt to nonlinear system real-time change. Based on previous results,online support vector regression (OSVR) theory and application were mainly studied in thisthesis. An advantage of OSVR is online learning ability, which can adjust model parametersonline. The main contents of this thesis are:
(1) Fuzzy online support vector regression algorithm (FOSVR) is proposed to solveweak anti-jamming capability and slow training speed problems of OSVR. Through settingdifferent weighted factor to each sample and optimizing learning steps, FOSVR algorithmimproves model accuracy and training speed. Simulation results verified the improvements ofFOSVR algorithm.
(2) Biological concentrations of fermentation process are hardly measured online,FOSVR is proposed to model glutamate fermentation process. Through online learning abilityof FOSVR, biomass concentration and production concentration soft sensor model were built.Futhermore, combining first principle model and FOSVR soft sensor model, a hybrid modelstrategy is proposed for fermentration process.
(3) To solve predictive model mismatch problem, a nonlinear modle predictive control(MPC) based on FOSVR was proposed. FOSVR can modify predictive model parametersonline, single-step MPC and multi-step MPC were studied. Due to local optimum problem ofgradient decent method, particle swarm algorithm (PSO) was applied to rolling optimizemulti-step model predictive control.
(4) For predictive functional control (PFC) bad performance in strong nonlinear andtime-varying system control, a PFC based on FOSVR inverse model was proposed. FOSVRwas used to obtain the inverse model of the Wiener model nonlinear part, the nonlinear PFChas been transferred to linear control. In this way, nonlinear objective function can be solvedby linear optimum algorithm. Aiming to improve performance of PFC, wavelet basis functionwas selected as basis function of PFC. Due to compact support and multi-scale analysis ofwavelet, the optimal parameters are aggregated.
(5) Low automatic level of fermentation process and difficulty in biologicalconcentration control, therefore, the predictive control was employed to glutamatefermentation process feeding optimized control. Based on fermentation distribute controlsystem, Delphi and Matlab hybrid programing was used, so based on key biologicalconcentrations FOSVR model, substrate feeding predictive control was carried out. Throughthree feeding control experiments, the higher cumulative production concentrations were obtained.
Through the stuy of this thesis, it is shown that FOSVR is an effective online modelingalgorithm. The algorithm not only can be used in solving modeling problem of fed-batchfermentation process, but also provide a powerful tool in complexity biochemical processcontrol. The study of this thesis has important significance for biochemical process.
引文
1. Vapnik V N. The Nature of Statistical learning theory[M], New York: Springer,1995,267-270.
2. Gunn SR, Brown M, Bossley KM. Network performance assessment for neuro fuzzy datamodeling[C]. In Proc. Intelligent Data Analysis, Lecture Notes in Computer Science,1997,313-323.
3. Vapnik VN. Statistical Learning Theory[M]. New York: Springer,1998,153-157.
4. Osuna E, Freund R, Griosi F. Training support vector machines: an application to facedetection[C]. Proceeding of the1997IEEE Computer Society Conference in ComputerVision and Pattern Recognition CVPR-97, Puerto Rico,1997,130-136.
5. Joachims T. Text categorization with support vector machines: learning with manyrelevant features[C]. Proceeding of the European Conference on Machine learning,Springer, Berlin,1998,137-142.
6. Brown MPS, Grundy WN, Lin D, et al. Support vector machine classification of microarray gene expression data[R], Technical Report UCSC-CRL-99-09, University ofCalifornia, Santa Cruz,1999.
7. Smola AJ, Scholkopf B. A tutorial on support vector regression[R]. NeuroCOLT TRNC-TR-98-030. Royal Holloway College University of London, UK,1998.
8. Theiler MJ, Perkins S. Accurate on-line support vector regression[J], Neural Computer,2003,15:2683–2703.
9.王定成,姜斌.支持向量机控制与在线学习方法研究的进展[J].系统仿真学报,2007,19(6):1177-1181.
10. Kudo T, Matsumoto Y. Chunking with support vector machines[C]. Association forComputational Linguistics,2001,1-8.
11. Gurevich Y, Bjorner NS, Teodosiu D. Efficient chunking algorithm[P].2004, US PatentApp.20060/047855.
12. Rychetsky M, Ortmann S, Ullmann M, et al. Accelerated training of support vectormachines[C]. International Joint Conference on Neural Networks,1999,2:998-1003
13. Joachims T. Making large-scale support vector machine learning practical[J]. In Advancesin kernel methods: Support Vector Machines. MIT Press,1999,169-184.
14. Laskov P. An improved decomposition algorithm for regression support vector machines[J]. Advances in neural information processing systems,2000,12:484-490.
15. Platt J.C. Fast training of support vector machines using sequential minimal optimization[J]. In Advances in kernel methods: Support Vector Machines, MIT Press,1999,185-208.
16. Li JM, Zhang B, Lin FZ. An Improvement Algorithm to Sequential Minimal Optimization[J]. Journal of Software,2003,14(5):918-924.
17. Cao LJ, Keerthi S, Ong CJ, et al. Parallel sequential minimal optimization for the trainingof support vector machines[J]. IEEE Transactions on Neural Networks,2006,17(4):1039-1049.
18. Suykens JAK, Vandewalle J. Least square support vector machine classifiers[J]. NeuralProcess Letters,1999,9(3):293-300.
19. Lee YJ, Mangasarian OL. RSVM: Reduced support vector machines[C]: SIAMPhiladelphia.2001:5-7.
20. Gert C, Tomaso P. Incremental and decremental support vector machine learning[J]. InAdvances in Neural Information Processing Systems,(NIPS’2000), MIT Press,2001,13:409–415.
21. Martin M. On-line support vector machines for function approximation [R]. TechnicalReport LSI-02-11-R, University of Politecnica Catalunya, Spain,2004.
22. Parrella F. Online Support Vector Regression[D]. Genoa, Italy: University of Genoa,2007.
23.王小燕.基于加权增量的支持向量机分类算法研究[D]:[硕士学位论文].杭州:浙江大学,2008.
24. Romero E, Barrio I, Belanche L. Incremental and decremental learning for linear supportvector machines[C]. Artificial Neural Networks–ICANN2007,2007:209-218.
25.汪辉,皮道映,孙优贤.支持向量机在线训练算法及其应用[J].浙江大学学报:工学版,2004,38(12):1642-1645.
26.刘大同,彭宇,彭喜元.基于残差预测修正的局部在线时间序列预测方法[J].电子学报,2008,36(B12):81-85.
27.孔锐,张冰.一种快速支持向量机增量学习算法[J].控制与决策,2005,20(10):1129-1132.
28. Müller K, Smola A, R tsch G, et al. Predicting time series with support vectormachines[C]. Artificial Neural Networks—ICANN'97,1997:999-1004.
29. Mukherjee S, Osuna E, Girosi F. Nonlinear prediction of chaotic time series using supportvector machines[C]. Neural Networks for Signal Processing [1997] VII. Proceedings ofthe1997IEEE Workshop.1997:511-520.
30. Frontzek T, Navin Lal T, Eckmiller R. Predicting the nonlinear dynamics of biologicalneurons using support vector machines with different kernels[C]. Neural Networks,2001.Proceedings. IJCNN '01. International Joint Conference on.2001,2:1492-1497
31. Drezet PML, Harrison RF. Support vector machines for system identification[C]. Control'98. UKACC International Conference on (Conf. Publ. No.455).1998,1:688-692.
32. Rojo-álvarez JL, Martínez-Ramón M, de Prado-Cumplido M, et al. Support vectormethod for robust ARMA system identification[J]. IEEE Transactions on SignalProcessing,2004,52(1):155-164.
33. Martínez-Ramón M, Rojo-álvarez JL, Camps-Valls, G, et al. Support vector machines fornonlinear kernel ARMA system identification[J]. IEEE Transactions on Neural Networks,2006,17(6):1617-1622.
34. Byung-hwa L, Sang-un K, Jin-wook S, et al. Nonlinear System Identification based onSupport Vector Machine using Particle Swarm Optimization[C]. SICE-ICASEInternational Joint Conference,2006,5614-5618.
35. Huang CL, Wang CJ. A GA-based feature selection and parameters optimizationforsupport vector machines[J]. Expert Systems with Applications,2006,31(2):231-240.
36. Zhang HM, Wei ZN, Gong DC, et al. A short-term load forecasting approach based onPSO support vector machine[J]. Relay,2006,34(3):28-31.
37. Niu D, Wang Y, Wu DD. Power load forecasting using support vector machine and antcolony optimization[J]. Expert Systems with Applications,2010,37(3):2531-2539.
38. Yuan X, Wang Y. Parameter selection of support vector machine for functionapproximation based on chaos optimization[J]. Journal of Systems Engineering andElectronics,2008,19(1):191-197.
39. Wang X, Chen J, Liu C, et al. Hybrid modeling of penicillin fermentation process basedon least square support vector machine[J]. Chemical Engineering Research and Design,2010,88(4):415-420.
40. Suykens J, Vandewalle J, De Moor B. Optimal control by least squares support vectormachines[J]. Neural Networks,2001,14(1):23-35.
41. de Kruif BJ, de Vries TJA. On using a support vector machine in learning feed-forwardcontrol[C]. Advanced Intelligent Mechatronics,2001. Proceedings.2001IEEE/ASMEInternational Conference on.2001,1:272-277.
42.王定成,方廷健.一种基于支持向量机的内模控制方法[J].控制理论与应用,2004,21(1):85-88.
43.张浩然,韩正之,李昌刚.基于支持向量机的非线性模型预测控制[J].系统工程与电子技术,2003,25(3):330-334.
44.王宇红,黄德先,高东杰, et al.基于LS-SVM的非线性预测控制技术[J].控制与决策,2004,19(4):383-387.
45. Zhong W, Pi D, Sun Y. Study on SVM based model predictive control[C]. WCICA2004.Fifth World Congress on Intelligent Control and Automation,2004,1:607-10A.
46. Kulkarni A, Jayaraman V, Kulkarni B. Control of chaotic dynamical systems usingsupport vector machines[J]. Physics Letters A,2003,317(5-6):429-435.
47. Iplikci S. Online trained support vector machines based generalized predictive control ofnonlinear systems[J]. International Journal of Adaptive Control and Signal Processing,2006,20(10):599-621.
48. Wang H, Pi D, Sun Y, Online SVM regression algorithm-based adaptive inverse control.Neurocomputing,2007,70(4):952-959.
49. Castro-Neto M., Jeong Y.S., Jeong M.K., et al. Online-SVR for short-term traffic flowprediction under typical and atypical traffic conditions. Expert Systems with Applications,2009,36(3):6164-6173.
50. Wang X, Du Z, Chen J, et al. Dynamic modeling of biotechnical process based on onlinesupport vector machine[J]. Journal of Computers,2009,4(3):251-258.
51. Asuncion A, Newman DJ. UCI machine learning repository.2007.
52. Chang CC, Lin CJ. LIBSVM: a library for support vector machines[J]. ACM Transactionson Intelligent Systems and Technology (TIST),2011,2(3):27.
53. Burges CJC. A tutorial on support vector machines for pattern recognition[J]. Data miningand knowledge discovery,1998,2(2):121-167.
54. Lin CF, Wang SD. Fuzzy support vector machines[J]. IEEE Transactions on NeuralNetworks,2002,13(2):464-471.
55. Tax DMJ, Duin RPW. Data domain description using support vectors [A]. Proceedings of7th European Symposium on Artificial Neural Networks. Brussels: D-Facto,1999,251-256.
56.张英,苏宏业,褚健.基于数据域描述的模糊支持向量回归[J].信息与控制,2005,34(1):1-6.
57.韦革宏,杨祥.发酵工程[M].北京:科学出版社.2008,1-5.
58.余龙江.发酵工程原理与技术应用[M].北京:化学工业出版社.2006,1-20.
59.陈坚,李寅.发酵过程优化原理与实践[M].北京:化学工业出版社.2002,2-6.
60. Yoshida F, Yamane T, Nakamoto KI. Fed-batch hydrocarbon fermentation with colloidalemulsion feed[J]. Biotechnology and Bioengineering,1973,15(2):257-270.
61.潘丰.补料分批发酵过程优化控制[J].自动化仪表,2004,25(8):51-54.
62.王树青,元英进.生化过程自动化技术[M].北京:化学工业出版社.1999:23-45.
63. Holms H. Flux analysis and control of the central metabolic pathways in Escherichiacoli[J]. FEMS microbiology reviews,1996,19(2):85-116.
64.叶勤,李志敏.大肠杆菌乙酸耐受株的代谢流分布[J].华东理工大学学报:自然科学版,2002,28(003):248-251.
65. Takaē S, ēalIk G, Mavituna F, et al. Metabolic flux distribution for the optimizedproduction of L-glutamate[J]. Enzyme and microbial technology,1998,23(5):286-300.
66. Takiguchi N, Shimizu H, Shioya S. An on-line physiological state recognition system forthe lysine fermentation process based on a metabolic reaction model[J]. Biotechnologyand Bioengineering,1997,55(1):170-181.
67. Tada K, Kishimoto M, Omasa T, et al. Constrained optimization of-lysine productionbased on metabolic flux using a mathematical programming method[J]. Journal ofbioscience and bioengineering,2001,91(4):344-351.
68.张成燕,郜培,史仲平, et al.基于代谢网络模型的谷氨酸发酵产酸速率在线预测[J].食品与发酵工业,2005,31(4):54-56.
69.史仲平,潘丰.发酵过程解析,控制与检测技术[M].北京:化学工业出版社现代生物技术与医药科技出版中心.2005:26-53.
70.王鲜芳.生化过程动态建模及优化控制研究[D]:[博士学位论文]无锡:江南大学,2009.
71. de Assis AJ. Soft sensors development for on-line bioreactor state estimation[J].Computers&chemical engineering,2000,24(2-7):1099-1103.
72. Petrova M, Koprinkova P, Patarinska T, et al. Neural network modelling of fermentationprocesses[J]. Bioprocess and Biosystems Engineering,1998,18(4):281-287.
73. Petrova M, Koprinkova P, Patarinska T. Neural network modelling of fermentationprocesses. Microorganisms cultivation model[J]. Bioprocess and Biosystems Engineering,1997,16(3):145-149.
74. Warnes MR, Glassey J, Montague GA, et al. On data-based modelling techniques forfermentation processes[J]. Process Biochemistry,1996,31(2):147-155.
75. Desai K, Badhe Y, Tambe SS, et al. Soft-sensor development for fed-batch bioreactorsusing support vector regression[J]. Biochemical Engineering Journal,2006,27(3):225-239.
76. Lei LY, Sun ZH. Soft sensor based on generalized support vector machines formicrobiological fermentation[C]. Proceedings of2005International Conference onMachine Learning and Cybernetics,2005,7:4305-4309.
77. Yamashita S, Hoshi H, Inagaki T. Automatic control and optimization of fermentationprocesses: Glutamie acid[M]. In: Perlman D (ed) Fermentation advances. Academic Press,New York,1969:441-463.
78.刘春波.统计建模方法的理论研究及应用D]:[博士学位论文]无锡:江南大学,2011.
79. Pollard JF, Broussard MR, Garrison DB, et al. Process identification using neuralnetworks[J]. Computer Chemical Engineering,1992,16(4):253–270.
80.高学金,王普,孙崇正, et al.基于支持向量机的青霉素发酵过程建模.系统仿真学报,2006,18(007):2052-2055.
81.冯瑞,张玥杰,张艳珠, et al.基于加权支持向量机的移动建模方法及其在软测量中的应用.自动化学报,2004,30(3):436-441.
82.李允公,张金萍,吴宁祥, et al.基于主元分析的频谱整体识别方法.东北大学学报:自然科学版,2008,29(9):1322-1325.
83. Ahmad A, Samad A, Fazli NA, et al. Mathematical modeling and analysis of dynamicbehaviour of a fed-batch penicilin G fermentation process[R]: Universiti Malaysia Sabah.2003:387-394.
84.吕光帅.基于支持向量机的发酵过程建模研究与控制系统设计[D]:[硕士学位论文].无锡:江南大学硕,2005.
85. Nandi S, Badhe Y, Lonari J, et al. Hybrid process modeling and optimization strategiesintegrating neural networks/support vector regression and genetic algorithms: study ofbenzene isopropylation on Hbeta catalyst[J]. Chemical Engineering Journal,2004,97(2-3):115-129.
86.戚以政,汪叔雄.生化反应动力学与反应器[M].北京:化学工业出版社,1999:100-106.
87. Michael LT, Mark AK. Modeling Chemical Processes Using Prior Knowledge and NeuralNetworks [J]. AIChE Joruna1,1994,40(8):1328-1331.
88. Psichogois DC, Ungar LH. A hybrid neural network-first principles approach to processmodeling [J]. AICHE Journal,1992,38(10):1499-1511.
89. Thompson ML, Kramer MA. Modeling chemical processes using prior knowledge andneural networks[J]. AIChE Journal,1994,40(8):1328-1340.
90. Oliveira R. Combining first principles modelling and artificial neural networks: a generalframework[J]. Computers&chemical engineering,2004,28(5):755-766.
91. Fu PC, Barford J. A hybrid neural network--first principles approach for modelling of cellmetabolism[J]. Computers&chemical engineering,1996,20(6-7):951-958.
92. Eikens B, Karim MN, Simon L. Neural networks and first principle models forbioprocesses. Proceedings of the14th IFAC, Beijing, P. R. China,1999(N-7a-12-4):367-372.
93.许光,俞欢军,陶少辉, et al.与机理杂交的支持向量机为发酵过程建模[J].化工学报,2005,56(004):653-658.
94.桑海峰,王福利,何大阔, et al.基于最小二乘支持向量机的发酵过程混合建模[J].仪器仪表学报,2006,27(6):629-633.
95.桑海峰,苑玮琦,王福利, et al.基于机理知识与最小二乘支持向量机的诺西肽发酵过程混合建模方法[J].系统仿真学报,2008,20(2):468-472.
96.舒迪前.预测控制系统及其应用[M].北京:机械工业出版社.1996:45.
97.席裕庚.预测控制[M].北京:国防工业出版社,1993:86.
98.陈虹,刘志远,解小华.非线性模型预测控制的现状与问题[J].控制与决策,2001,16(4):385-391.
99. Tsen AYD, Jang SS, Wong DSH, et al. Predictive control of quality in batchpolymerization using hybrid ANN models. AIChE Journal,1996,42(2):455-465.
100. Buescher KL, Baum CC. A two-timescale approach to nonlinear model predictivecontrol[C]. Proceedings of the American Control Conference,1995,3:2250-2256
101. Zamarreno J, Vega P. Neural predictive control. Application to a highly non-linearsystem[J]. Engineering Applications of Artificial Intelligence,1999,12(2):149-158.
102.刘军,赵霞,许晓鸣.基于神经网络非线性模型的扩展DMC预测控制[J].信息与控制,1998,27(5):391-393.
103. Zhong W, He G, Pi D, et al. SVM with quadratic polynomial kernel function basednonlinear model one-step-ahead predictive control[J]. Chinese Journal of ChemicalEngineering,2005,13(3):373-379.
104. Zhong W, Pi D, Sun Y. Support vector machine based nonlinear modelmulti-step-ahead optimizing predictive control[J]. Journal of Central South University ofTechnology,2005,12(5):591-595.
105.张日东,王树青,李平.基于支持向量机的非线性系统预测控制[J].自动化学报,2007,33(10):1066-1073.
106.赵璐华,王晋云,陈翔, et al.无人飞行器编队队形控制研究[J].电光与控制,2011,18(8):34-39.
107.王世虎,沈炯,李益国.300MW火电机组神经网络预测控制策略[J].发电设备,2007,6:435-439.
108.张涛,陈立,李治. NARMA模型预测控制滚动优化的两级协调法[J].西南交通大学学报,1997,32(4):451-456.
109. Wang X, Xiao J. PSO-based model predictive control for nonlinear processes[J].Advances in Natural Computation,2005:424-424.
110. Kennedy J, Eberhart RC. Particle swarm optimization [C]. Proceedings of IEEEInternational Conference on Neural Networks,1995:1942-1948.
111.方剑,席裕庚.基于遗传算法的滚动调度策略[J].控制理论与应用,1997,14(004):589-594.
112.高异,杨延西,刘军.模糊遗传滚动优化的LS-SVM预测控制研究[J].系统仿真学报,2007,19(6):1277-1280.
113.王娟,刘明治.蚁群算法滚动优化的LS-SVM预测控制研究[J].控制与决策,2009,24(7):1087-1091.
114. Sch n T. Identification for Predictive Control-A Multiple Model Approach[R].Link ping, Sweden: Link ping University,2001.
115.席裕庚,许晓呜,张钟俊.预测控制的研究现状和多层智能预测控制[J].控制理论与应用,1989,6(2):1-7.
116.刘斌.非线性系统建模及预测控制若干问题研究[D]:[博士学位论文].杭州:浙江大学,2004.
117. Bao Z, Pi D, Sun Y. Nonlinear model predictive control based on support vectormachine with multi-kernel[J]. Chinese Journal of Chemical Engineering,2007,15(5):691-697.
118. Bai EW, Fu M. A blind approach to Hammerstein model identification[J]. IEEETransactions on Signal Processing,2002,50(7):1610-1619.
119. Narendra K, Gallman P. An iterative method for the identification of nonlinearsystems using a Hammerstein model[J]. Automatic Control, IEEE Transactions on,1966,11(3):546-550.
120.邹志云,于德弘,胡真.非线性HAMMERSTEIN系统的预测控制及其pH过程应用[J].计算机与应用化学,2006,23(002):137-142.
121. Liu Y, Wang H, Li P. Kernel learning adaptive one‐step‐ahead predictive controlfor nonlinear processes[J]. Asia‐Pacific Journal of Chemical Engineering,2008,3(6):673-679.
122.汪辉.增量型支持向量机回归训练算法及在控制中的应用[D]:[博士学位论文].杭州:浙江大学,2006.
123. MACIEJOWSKI JM. Predictive Control with Constraints[M].New York, USA:Prentice Hall,2002.
124. Song Y, Chen Z, Yuan Z. Neural Network Nonlinear Predictive Control Based onTent-map Chaos Optimization[J]. Chinese Journal of Chemical Engineering,2007,15(4):539-544.
125. Noriega JR, Wang H. A direct adaptive neural-network control for unknownnonlinear systems and its application[J]. IEEE Transactions on Neural Networks,1998,9(1):27-34.
126. Cortes C. Prediction of generalization ability in learning machines[D]:[Ph. D.Thesis]. University of Rochester, Rechester, New York, USA,1995.
127. Eberhart RC, Shi Y. Comparing Inertia Weights and Constriction Factors in ParticleSwarm Optimization [J], IEEE Congress Evolutionary Computation,2000:84-88.
128. Eberhart RC, Shi Y. Particle swarm optimization developments, applications andresources [J]. IEEE,2001:81-86.
129. Kuntze HB, Jacubasch A, Richalet J, et al. On the predictive functional control of anelastic industrial robot[C].25th IEEE Conference on Decision and Control,1986:1877-1881.
130. Richalet J. Predictive Functional Control: Application to Fast and AccurateRobots[C]. Proc. of10th IFAC World Congress, Munich,1987.
131.金晓明.模糊控制、预测控制与工业过程的先进控制[D]:[博士学位论文].杭州:浙江大学,1998.
132.张泉灵,王树青.基于ARMAX模型自适应预测函数控制[J].信息与控制,2000,29(5):431-436.
133.修志芳.预测函数控制及其应用研究[D]:[博士学位论文].杭州:浙江大学,2008.
134.张泉灵,王树青.基于Hammerstein模型的非线性预测函数控制[J].浙江大学学报:工学版,2002,36(002):119-122.
135. Fruzzetti K, Palazo lu A, McDonald K. Nolinear model predictive control usingHammerstein models[J]. Journal of process control,1997,7(1):31-41.
136.苏成利,王树青.一种基于Wiener模型的非线性预测控制算法[J].信息与控制,2007,36(1):86-92.
137. Norquay SJ, Palazoglu A, Romagnoli JA. Model predictive control based on Wienermodels[J]. Chemical Engineering Science,1998,53(1):75-84.
138.潘红华,胡家升,朱森, et al.一种改进的预测函数控制法[J].系统工程与电子技术,2003,25(11):1389-1391.
139.杜晓宁,席裕庚.预测控制优化变量的集结策略[J].控制与决策,2002,17(5):563-566.
140. Zheng A. Reducing on-line computational demands in model predictive control byapproximating QP constraints[J]. Journal of process control,1999,9(4):279-290.
141.修志芳.预测函数控制及其应用研究[D]:[硕士学位论文].杭州:浙江大学,2008.
142.张泉灵.预测函数控制及应用研究[D]:[博士学位论文].杭州:浙江大学,1999.
143.金晓明.先进控制技术及应用第五讲预测函数控制(PFC)――一种新型预测控制策略[J].化工自动化及仪表,1999(06).
144.杨煜普,黄新民.非线性系统多步预测控制的复合神经网络实现[J].控制与决策,1999,14(4):314-318.
145.陈进东,张相胜,潘丰.基于Wiener模型的非线性预测函数控制.吉林大学学报(工学版),2011,41(S1):264-269.
146. C.C.古德温，孙贵生.自适应滤波预测与控制［M］.北京：科学出版社，1992.
147.郑军,颜文俊,诸静.基于小波基函数的预测函数控制[J].控制与决策,2005,20(9):1077-1080.
148. Hunt KJ, Sbarbaro D. Neural networks for nonlinear internal model control[J]. IEEProceedings-D,1991,138(5):431-438.
149. Goodwith GC., Sin K.S. Adaptive filtering prediction and control [M]. EnglewoodCliffs: Prentice-hall Inc,1984.
150.史芸,田学民.一种基于Wiener模型的非线性预测控制[J].江南大学学报(自然科学版),2006,5(4):387-390.
151. Daubechies I. The Wavelet Transform, Time-frequency Localization and SignalAnalysis[J]. IEEE Trans on Information Theory,1990,36(5):961-1005.
152. Albert B, Francis JN. A First Course in Wavelets with Fourier Analysis[M]. Beijing:Publishing House of Electronics Industry,2003:183-227.
153.飞思科技产品研发中心.小波分析理论与MATLAB7实现[M].北京:电子工业出版社,2005.
154. Daubechies I.小波十讲[M].李建平,杨万年译.北京:国防工业出版社,2004.
155.诸静.智能预测控制及其应用[M].杭州:浙江大学出版社,2002:174-184.
156. Kovárová-Kovar K, Gehlen S, Kunze A, et al. Application of model-predictivecontrol based on artificial neural networks to optimize the fed-batch process for riboflavinproduction[J]. Journal of biotechnology,2000,79(1):39-52.
157.习毅.发酵过程预测控制研究[D]:[硕士学位论文].无锡:江南大学,2008.
158. Ashoori A, Moshiri B, Khaki-Sedigh A, et al. Optimal control of a nonlinearfed-batch fermentation process using model predictive approach[J]. Journal of processcontrol,2009,19(7):1162-1173.
159. Ramaswamy S, Cutright T, Qammar H. Control of a continuous bioreactor usingmodel predictive control[J]. Process Biochemistry,2005,40(8):2763-2770.
160. Kiran AUM, Jana AK. Control of continuous fed-batch fermentation process usingneural network based model predictive controller[J]. Bioprocess and BiosystemsEngineering,2009,32(6):801-808.
161. Zhu GY, Zamamiri A, Henson MA, et al. Model predictive control of continuousyeast bioreactors using cell population balance models[J]. Chemical Engineering Science,2000,55(24):6155-6167.
162. Hooke R, Jeeves TA.``Direct Search'' Solution of Numerical and StatisticalProblems[J]. Journal of the ACM (JACM),1961,8(2):212-229.
2. Gunn SR, Brown M, Bossley KM. Network performance assessment for neuro fuzzy datamodeling[C]. In Proc. Intelligent Data Analysis, Lecture Notes in Computer Science,1997,313-323.
3. Vapnik VN. Statistical Learning Theory[M]. New York: Springer,1998,153-157.
4. Osuna E, Freund R, Griosi F. Training support vector machines: an application to facedetection[C]. Proceeding of the1997IEEE Computer Society Conference in ComputerVision and Pattern Recognition CVPR-97, Puerto Rico,1997,130-136.
5. Joachims T. Text categorization with support vector machines: learning with manyrelevant features[C]. Proceeding of the European Conference on Machine learning,Springer, Berlin,1998,137-142.
6. Brown MPS, Grundy WN, Lin D, et al. Support vector machine classification of microarray gene expression data[R], Technical Report UCSC-CRL-99-09, University ofCalifornia, Santa Cruz,1999.
7. Smola AJ, Scholkopf B. A tutorial on support vector regression[R]. NeuroCOLT TRNC-TR-98-030. Royal Holloway College University of London, UK,1998.
8. Theiler MJ, Perkins S. Accurate on-line support vector regression[J], Neural Computer,2003,15:2683–2703.
9.王定成,姜斌.支持向量机控制与在线学习方法研究的进展[J].系统仿真学报,2007,19(6):1177-1181.
10. Kudo T, Matsumoto Y. Chunking with support vector machines[C]. Association forComputational Linguistics,2001,1-8.
11. Gurevich Y, Bjorner NS, Teodosiu D. Efficient chunking algorithm[P].2004, US PatentApp.20060/047855.
12. Rychetsky M, Ortmann S, Ullmann M, et al. Accelerated training of support vectormachines[C]. International Joint Conference on Neural Networks,1999,2:998-1003
13. Joachims T. Making large-scale support vector machine learning practical[J]. In Advancesin kernel methods: Support Vector Machines. MIT Press,1999,169-184.
14. Laskov P. An improved decomposition algorithm for regression support vector machines[J]. Advances in neural information processing systems,2000,12:484-490.
15. Platt J.C. Fast training of support vector machines using sequential minimal optimization[J]. In Advances in kernel methods: Support Vector Machines, MIT Press,1999,185-208.
16. Li JM, Zhang B, Lin FZ. An Improvement Algorithm to Sequential Minimal Optimization[J]. Journal of Software,2003,14(5):918-924.
17. Cao LJ, Keerthi S, Ong CJ, et al. Parallel sequential minimal optimization for the trainingof support vector machines[J]. IEEE Transactions on Neural Networks,2006,17(4):1039-1049.
18. Suykens JAK, Vandewalle J. Least square support vector machine classifiers[J]. NeuralProcess Letters,1999,9(3):293-300.
19. Lee YJ, Mangasarian OL. RSVM: Reduced support vector machines[C]: SIAMPhiladelphia.2001:5-7.
20. Gert C, Tomaso P. Incremental and decremental support vector machine learning[J]. InAdvances in Neural Information Processing Systems,(NIPS’2000), MIT Press,2001,13:409–415.
21. Martin M. On-line support vector machines for function approximation [R]. TechnicalReport LSI-02-11-R, University of Politecnica Catalunya, Spain,2004.
22. Parrella F. Online Support Vector Regression[D]. Genoa, Italy: University of Genoa,2007.
23.王小燕.基于加权增量的支持向量机分类算法研究[D]:[硕士学位论文].杭州:浙江大学,2008.
24. Romero E, Barrio I, Belanche L. Incremental and decremental learning for linear supportvector machines[C]. Artificial Neural Networks–ICANN2007,2007:209-218.
25.汪辉,皮道映,孙优贤.支持向量机在线训练算法及其应用[J].浙江大学学报:工学版,2004,38(12):1642-1645.
26.刘大同,彭宇,彭喜元.基于残差预测修正的局部在线时间序列预测方法[J].电子学报,2008,36(B12):81-85.
27.孔锐,张冰.一种快速支持向量机增量学习算法[J].控制与决策,2005,20(10):1129-1132.
28. Müller K, Smola A, R tsch G, et al. Predicting time series with support vectormachines[C]. Artificial Neural Networks—ICANN'97,1997:999-1004.
29. Mukherjee S, Osuna E, Girosi F. Nonlinear prediction of chaotic time series using supportvector machines[C]. Neural Networks for Signal Processing [1997] VII. Proceedings ofthe1997IEEE Workshop.1997:511-520.
30. Frontzek T, Navin Lal T, Eckmiller R. Predicting the nonlinear dynamics of biologicalneurons using support vector machines with different kernels[C]. Neural Networks,2001.Proceedings. IJCNN '01. International Joint Conference on.2001,2:1492-1497
31. Drezet PML, Harrison RF. Support vector machines for system identification[C]. Control'98. UKACC International Conference on (Conf. Publ. No.455).1998,1:688-692.
32. Rojo-álvarez JL, Martínez-Ramón M, de Prado-Cumplido M, et al. Support vectormethod for robust ARMA system identification[J]. IEEE Transactions on SignalProcessing,2004,52(1):155-164.
33. Martínez-Ramón M, Rojo-álvarez JL, Camps-Valls, G, et al. Support vector machines fornonlinear kernel ARMA system identification[J]. IEEE Transactions on Neural Networks,2006,17(6):1617-1622.
34. Byung-hwa L, Sang-un K, Jin-wook S, et al. Nonlinear System Identification based onSupport Vector Machine using Particle Swarm Optimization[C]. SICE-ICASEInternational Joint Conference,2006,5614-5618.
35. Huang CL, Wang CJ. A GA-based feature selection and parameters optimizationforsupport vector machines[J]. Expert Systems with Applications,2006,31(2):231-240.
36. Zhang HM, Wei ZN, Gong DC, et al. A short-term load forecasting approach based onPSO support vector machine[J]. Relay,2006,34(3):28-31.
37. Niu D, Wang Y, Wu DD. Power load forecasting using support vector machine and antcolony optimization[J]. Expert Systems with Applications,2010,37(3):2531-2539.
38. Yuan X, Wang Y. Parameter selection of support vector machine for functionapproximation based on chaos optimization[J]. Journal of Systems Engineering andElectronics,2008,19(1):191-197.
39. Wang X, Chen J, Liu C, et al. Hybrid modeling of penicillin fermentation process basedon least square support vector machine[J]. Chemical Engineering Research and Design,2010,88(4):415-420.
40. Suykens J, Vandewalle J, De Moor B. Optimal control by least squares support vectormachines[J]. Neural Networks,2001,14(1):23-35.
41. de Kruif BJ, de Vries TJA. On using a support vector machine in learning feed-forwardcontrol[C]. Advanced Intelligent Mechatronics,2001. Proceedings.2001IEEE/ASMEInternational Conference on.2001,1:272-277.
42.王定成,方廷健.一种基于支持向量机的内模控制方法[J].控制理论与应用,2004,21(1):85-88.
43.张浩然,韩正之,李昌刚.基于支持向量机的非线性模型预测控制[J].系统工程与电子技术,2003,25(3):330-334.
44.王宇红,黄德先,高东杰, et al.基于LS-SVM的非线性预测控制技术[J].控制与决策,2004,19(4):383-387.
45. Zhong W, Pi D, Sun Y. Study on SVM based model predictive control[C]. WCICA2004.Fifth World Congress on Intelligent Control and Automation,2004,1:607-10A.
46. Kulkarni A, Jayaraman V, Kulkarni B. Control of chaotic dynamical systems usingsupport vector machines[J]. Physics Letters A,2003,317(5-6):429-435.
47. Iplikci S. Online trained support vector machines based generalized predictive control ofnonlinear systems[J]. International Journal of Adaptive Control and Signal Processing,2006,20(10):599-621.
48. Wang H, Pi D, Sun Y, Online SVM regression algorithm-based adaptive inverse control.Neurocomputing,2007,70(4):952-959.
49. Castro-Neto M., Jeong Y.S., Jeong M.K., et al. Online-SVR for short-term traffic flowprediction under typical and atypical traffic conditions. Expert Systems with Applications,2009,36(3):6164-6173.
50. Wang X, Du Z, Chen J, et al. Dynamic modeling of biotechnical process based on onlinesupport vector machine[J]. Journal of Computers,2009,4(3):251-258.
51. Asuncion A, Newman DJ. UCI machine learning repository.2007.
52. Chang CC, Lin CJ. LIBSVM: a library for support vector machines[J]. ACM Transactionson Intelligent Systems and Technology (TIST),2011,2(3):27.
53. Burges CJC. A tutorial on support vector machines for pattern recognition[J]. Data miningand knowledge discovery,1998,2(2):121-167.
54. Lin CF, Wang SD. Fuzzy support vector machines[J]. IEEE Transactions on NeuralNetworks,2002,13(2):464-471.
55. Tax DMJ, Duin RPW. Data domain description using support vectors [A]. Proceedings of7th European Symposium on Artificial Neural Networks. Brussels: D-Facto,1999,251-256.
56.张英,苏宏业,褚健.基于数据域描述的模糊支持向量回归[J].信息与控制,2005,34(1):1-6.
57.韦革宏,杨祥.发酵工程[M].北京:科学出版社.2008,1-5.
58.余龙江.发酵工程原理与技术应用[M].北京:化学工业出版社.2006,1-20.
59.陈坚,李寅.发酵过程优化原理与实践[M].北京:化学工业出版社.2002,2-6.
60. Yoshida F, Yamane T, Nakamoto KI. Fed-batch hydrocarbon fermentation with colloidalemulsion feed[J]. Biotechnology and Bioengineering,1973,15(2):257-270.
61.潘丰.补料分批发酵过程优化控制[J].自动化仪表,2004,25(8):51-54.
62.王树青,元英进.生化过程自动化技术[M].北京:化学工业出版社.1999:23-45.
63. Holms H. Flux analysis and control of the central metabolic pathways in Escherichiacoli[J]. FEMS microbiology reviews,1996,19(2):85-116.
64.叶勤,李志敏.大肠杆菌乙酸耐受株的代谢流分布[J].华东理工大学学报:自然科学版,2002,28(003):248-251.
65. Takaē S, ēalIk G, Mavituna F, et al. Metabolic flux distribution for the optimizedproduction of L-glutamate[J]. Enzyme and microbial technology,1998,23(5):286-300.
66. Takiguchi N, Shimizu H, Shioya S. An on-line physiological state recognition system forthe lysine fermentation process based on a metabolic reaction model[J]. Biotechnologyand Bioengineering,1997,55(1):170-181.
67. Tada K, Kishimoto M, Omasa T, et al. Constrained optimization of-lysine productionbased on metabolic flux using a mathematical programming method[J]. Journal ofbioscience and bioengineering,2001,91(4):344-351.
68.张成燕,郜培,史仲平, et al.基于代谢网络模型的谷氨酸发酵产酸速率在线预测[J].食品与发酵工业,2005,31(4):54-56.
69.史仲平,潘丰.发酵过程解析,控制与检测技术[M].北京:化学工业出版社现代生物技术与医药科技出版中心.2005:26-53.
70.王鲜芳.生化过程动态建模及优化控制研究[D]:[博士学位论文]无锡:江南大学,2009.
71. de Assis AJ. Soft sensors development for on-line bioreactor state estimation[J].Computers&chemical engineering,2000,24(2-7):1099-1103.
72. Petrova M, Koprinkova P, Patarinska T, et al. Neural network modelling of fermentationprocesses[J]. Bioprocess and Biosystems Engineering,1998,18(4):281-287.
73. Petrova M, Koprinkova P, Patarinska T. Neural network modelling of fermentationprocesses. Microorganisms cultivation model[J]. Bioprocess and Biosystems Engineering,1997,16(3):145-149.
74. Warnes MR, Glassey J, Montague GA, et al. On data-based modelling techniques forfermentation processes[J]. Process Biochemistry,1996,31(2):147-155.
75. Desai K, Badhe Y, Tambe SS, et al. Soft-sensor development for fed-batch bioreactorsusing support vector regression[J]. Biochemical Engineering Journal,2006,27(3):225-239.
76. Lei LY, Sun ZH. Soft sensor based on generalized support vector machines formicrobiological fermentation[C]. Proceedings of2005International Conference onMachine Learning and Cybernetics,2005,7:4305-4309.
77. Yamashita S, Hoshi H, Inagaki T. Automatic control and optimization of fermentationprocesses: Glutamie acid[M]. In: Perlman D (ed) Fermentation advances. Academic Press,New York,1969:441-463.
78.刘春波.统计建模方法的理论研究及应用D]:[博士学位论文]无锡:江南大学,2011.
79. Pollard JF, Broussard MR, Garrison DB, et al. Process identification using neuralnetworks[J]. Computer Chemical Engineering,1992,16(4):253–270.
80.高学金,王普,孙崇正, et al.基于支持向量机的青霉素发酵过程建模.系统仿真学报,2006,18(007):2052-2055.
81.冯瑞,张玥杰,张艳珠, et al.基于加权支持向量机的移动建模方法及其在软测量中的应用.自动化学报,2004,30(3):436-441.
82.李允公,张金萍,吴宁祥, et al.基于主元分析的频谱整体识别方法.东北大学学报:自然科学版,2008,29(9):1322-1325.
83. Ahmad A, Samad A, Fazli NA, et al. Mathematical modeling and analysis of dynamicbehaviour of a fed-batch penicilin G fermentation process[R]: Universiti Malaysia Sabah.2003:387-394.
84.吕光帅.基于支持向量机的发酵过程建模研究与控制系统设计[D]:[硕士学位论文].无锡:江南大学硕,2005.
85. Nandi S, Badhe Y, Lonari J, et al. Hybrid process modeling and optimization strategiesintegrating neural networks/support vector regression and genetic algorithms: study ofbenzene isopropylation on Hbeta catalyst[J]. Chemical Engineering Journal,2004,97(2-3):115-129.
86.戚以政,汪叔雄.生化反应动力学与反应器[M].北京:化学工业出版社,1999:100-106.
87. Michael LT, Mark AK. Modeling Chemical Processes Using Prior Knowledge and NeuralNetworks [J]. AIChE Joruna1,1994,40(8):1328-1331.
88. Psichogois DC, Ungar LH. A hybrid neural network-first principles approach to processmodeling [J]. AICHE Journal,1992,38(10):1499-1511.
89. Thompson ML, Kramer MA. Modeling chemical processes using prior knowledge andneural networks[J]. AIChE Journal,1994,40(8):1328-1340.
90. Oliveira R. Combining first principles modelling and artificial neural networks: a generalframework[J]. Computers&chemical engineering,2004,28(5):755-766.
91. Fu PC, Barford J. A hybrid neural network--first principles approach for modelling of cellmetabolism[J]. Computers&chemical engineering,1996,20(6-7):951-958.
92. Eikens B, Karim MN, Simon L. Neural networks and first principle models forbioprocesses. Proceedings of the14th IFAC, Beijing, P. R. China,1999(N-7a-12-4):367-372.
93.许光,俞欢军,陶少辉, et al.与机理杂交的支持向量机为发酵过程建模[J].化工学报,2005,56(004):653-658.
94.桑海峰,王福利,何大阔, et al.基于最小二乘支持向量机的发酵过程混合建模[J].仪器仪表学报,2006,27(6):629-633.
95.桑海峰,苑玮琦,王福利, et al.基于机理知识与最小二乘支持向量机的诺西肽发酵过程混合建模方法[J].系统仿真学报,2008,20(2):468-472.
96.舒迪前.预测控制系统及其应用[M].北京:机械工业出版社.1996:45.
97.席裕庚.预测控制[M].北京:国防工业出版社,1993:86.
98.陈虹,刘志远,解小华.非线性模型预测控制的现状与问题[J].控制与决策,2001,16(4):385-391.
99. Tsen AYD, Jang SS, Wong DSH, et al. Predictive control of quality in batchpolymerization using hybrid ANN models. AIChE Journal,1996,42(2):455-465.
100. Buescher KL, Baum CC. A two-timescale approach to nonlinear model predictivecontrol[C]. Proceedings of the American Control Conference,1995,3:2250-2256
101. Zamarreno J, Vega P. Neural predictive control. Application to a highly non-linearsystem[J]. Engineering Applications of Artificial Intelligence,1999,12(2):149-158.
102.刘军,赵霞,许晓鸣.基于神经网络非线性模型的扩展DMC预测控制[J].信息与控制,1998,27(5):391-393.
103. Zhong W, He G, Pi D, et al. SVM with quadratic polynomial kernel function basednonlinear model one-step-ahead predictive control[J]. Chinese Journal of ChemicalEngineering,2005,13(3):373-379.
104. Zhong W, Pi D, Sun Y. Support vector machine based nonlinear modelmulti-step-ahead optimizing predictive control[J]. Journal of Central South University ofTechnology,2005,12(5):591-595.
105.张日东,王树青,李平.基于支持向量机的非线性系统预测控制[J].自动化学报,2007,33(10):1066-1073.
106.赵璐华,王晋云,陈翔, et al.无人飞行器编队队形控制研究[J].电光与控制,2011,18(8):34-39.
107.王世虎,沈炯,李益国.300MW火电机组神经网络预测控制策略[J].发电设备,2007,6:435-439.
108.张涛,陈立,李治. NARMA模型预测控制滚动优化的两级协调法[J].西南交通大学学报,1997,32(4):451-456.
109. Wang X, Xiao J. PSO-based model predictive control for nonlinear processes[J].Advances in Natural Computation,2005:424-424.
110. Kennedy J, Eberhart RC. Particle swarm optimization [C]. Proceedings of IEEEInternational Conference on Neural Networks,1995:1942-1948.
111.方剑,席裕庚.基于遗传算法的滚动调度策略[J].控制理论与应用,1997,14(004):589-594.
112.高异,杨延西,刘军.模糊遗传滚动优化的LS-SVM预测控制研究[J].系统仿真学报,2007,19(6):1277-1280.
113.王娟,刘明治.蚁群算法滚动优化的LS-SVM预测控制研究[J].控制与决策,2009,24(7):1087-1091.
114. Sch n T. Identification for Predictive Control-A Multiple Model Approach[R].Link ping, Sweden: Link ping University,2001.
115.席裕庚,许晓呜,张钟俊.预测控制的研究现状和多层智能预测控制[J].控制理论与应用,1989,6(2):1-7.
116.刘斌.非线性系统建模及预测控制若干问题研究[D]:[博士学位论文].杭州:浙江大学,2004.
117. Bao Z, Pi D, Sun Y. Nonlinear model predictive control based on support vectormachine with multi-kernel[J]. Chinese Journal of Chemical Engineering,2007,15(5):691-697.
118. Bai EW, Fu M. A blind approach to Hammerstein model identification[J]. IEEETransactions on Signal Processing,2002,50(7):1610-1619.
119. Narendra K, Gallman P. An iterative method for the identification of nonlinearsystems using a Hammerstein model[J]. Automatic Control, IEEE Transactions on,1966,11(3):546-550.
120.邹志云,于德弘,胡真.非线性HAMMERSTEIN系统的预测控制及其pH过程应用[J].计算机与应用化学,2006,23(002):137-142.
121. Liu Y, Wang H, Li P. Kernel learning adaptive one‐step‐ahead predictive controlfor nonlinear processes[J]. Asia‐Pacific Journal of Chemical Engineering,2008,3(6):673-679.
122.汪辉.增量型支持向量机回归训练算法及在控制中的应用[D]:[博士学位论文].杭州:浙江大学,2006.
123. MACIEJOWSKI JM. Predictive Control with Constraints[M].New York, USA:Prentice Hall,2002.
124. Song Y, Chen Z, Yuan Z. Neural Network Nonlinear Predictive Control Based onTent-map Chaos Optimization[J]. Chinese Journal of Chemical Engineering,2007,15(4):539-544.
125. Noriega JR, Wang H. A direct adaptive neural-network control for unknownnonlinear systems and its application[J]. IEEE Transactions on Neural Networks,1998,9(1):27-34.
126. Cortes C. Prediction of generalization ability in learning machines[D]:[Ph. D.Thesis]. University of Rochester, Rechester, New York, USA,1995.
127. Eberhart RC, Shi Y. Comparing Inertia Weights and Constriction Factors in ParticleSwarm Optimization [J], IEEE Congress Evolutionary Computation,2000:84-88.
128. Eberhart RC, Shi Y. Particle swarm optimization developments, applications andresources [J]. IEEE,2001:81-86.
129. Kuntze HB, Jacubasch A, Richalet J, et al. On the predictive functional control of anelastic industrial robot[C].25th IEEE Conference on Decision and Control,1986:1877-1881.
130. Richalet J. Predictive Functional Control: Application to Fast and AccurateRobots[C]. Proc. of10th IFAC World Congress, Munich,1987.
131.金晓明.模糊控制、预测控制与工业过程的先进控制[D]:[博士学位论文].杭州:浙江大学,1998.
132.张泉灵,王树青.基于ARMAX模型自适应预测函数控制[J].信息与控制,2000,29(5):431-436.
133.修志芳.预测函数控制及其应用研究[D]:[博士学位论文].杭州:浙江大学,2008.
134.张泉灵,王树青.基于Hammerstein模型的非线性预测函数控制[J].浙江大学学报:工学版,2002,36(002):119-122.
135. Fruzzetti K, Palazo lu A, McDonald K. Nolinear model predictive control usingHammerstein models[J]. Journal of process control,1997,7(1):31-41.
136.苏成利,王树青.一种基于Wiener模型的非线性预测控制算法[J].信息与控制,2007,36(1):86-92.
137. Norquay SJ, Palazoglu A, Romagnoli JA. Model predictive control based on Wienermodels[J]. Chemical Engineering Science,1998,53(1):75-84.
138.潘红华,胡家升,朱森, et al.一种改进的预测函数控制法[J].系统工程与电子技术,2003,25(11):1389-1391.
139.杜晓宁,席裕庚.预测控制优化变量的集结策略[J].控制与决策,2002,17(5):563-566.
140. Zheng A. Reducing on-line computational demands in model predictive control byapproximating QP constraints[J]. Journal of process control,1999,9(4):279-290.
141.修志芳.预测函数控制及其应用研究[D]:[硕士学位论文].杭州:浙江大学,2008.
142.张泉灵.预测函数控制及应用研究[D]:[博士学位论文].杭州:浙江大学,1999.
143.金晓明.先进控制技术及应用第五讲预测函数控制(PFC)――一种新型预测控制策略[J].化工自动化及仪表,1999(06).
144.杨煜普,黄新民.非线性系统多步预测控制的复合神经网络实现[J].控制与决策,1999,14(4):314-318.
145.陈进东,张相胜,潘丰.基于Wiener模型的非线性预测函数控制.吉林大学学报(工学版),2011,41(S1):264-269.
146. C.C.古德温，孙贵生.自适应滤波预测与控制［M］.北京：科学出版社，1992.
147.郑军,颜文俊,诸静.基于小波基函数的预测函数控制[J].控制与决策,2005,20(9):1077-1080.
148. Hunt KJ, Sbarbaro D. Neural networks for nonlinear internal model control[J]. IEEProceedings-D,1991,138(5):431-438.
149. Goodwith GC., Sin K.S. Adaptive filtering prediction and control [M]. EnglewoodCliffs: Prentice-hall Inc,1984.
150.史芸,田学民.一种基于Wiener模型的非线性预测控制[J].江南大学学报(自然科学版),2006,5(4):387-390.
151. Daubechies I. The Wavelet Transform, Time-frequency Localization and SignalAnalysis[J]. IEEE Trans on Information Theory,1990,36(5):961-1005.
152. Albert B, Francis JN. A First Course in Wavelets with Fourier Analysis[M]. Beijing:Publishing House of Electronics Industry,2003:183-227.
153.飞思科技产品研发中心.小波分析理论与MATLAB7实现[M].北京:电子工业出版社,2005.
154. Daubechies I.小波十讲[M].李建平,杨万年译.北京:国防工业出版社,2004.
155.诸静.智能预测控制及其应用[M].杭州:浙江大学出版社,2002:174-184.
156. Kovárová-Kovar K, Gehlen S, Kunze A, et al. Application of model-predictivecontrol based on artificial neural networks to optimize the fed-batch process for riboflavinproduction[J]. Journal of biotechnology,2000,79(1):39-52.
157.习毅.发酵过程预测控制研究[D]:[硕士学位论文].无锡:江南大学,2008.
158. Ashoori A, Moshiri B, Khaki-Sedigh A, et al. Optimal control of a nonlinearfed-batch fermentation process using model predictive approach[J]. Journal of processcontrol,2009,19(7):1162-1173.
159. Ramaswamy S, Cutright T, Qammar H. Control of a continuous bioreactor usingmodel predictive control[J]. Process Biochemistry,2005,40(8):2763-2770.
160. Kiran AUM, Jana AK. Control of continuous fed-batch fermentation process usingneural network based model predictive controller[J]. Bioprocess and BiosystemsEngineering,2009,32(6):801-808.
161. Zhu GY, Zamamiri A, Henson MA, et al. Model predictive control of continuousyeast bioreactors using cell population balance models[J]. Chemical Engineering Science,2000,55(24):6155-6167.
162. Hooke R, Jeeves TA.``Direct Search'' Solution of Numerical and StatisticalProblems[J]. Journal of the ACM (JACM),1961,8(2):212-229.