神经网络逆控制方法研究及其在生物发酵过程中的应用
|
摘要
生物发酵技术是经济发展的重要技术之一,在农业、化工等领域发挥着重要的作用。随着生产规模的扩大,发酵工业对自动控制技术的要求不断提高,实现生物发酵过程的高性能控制对提高发酵产物的品质和产量具有重要意义。生物发酵过程涉及生命体的生长繁殖,机理复杂,传统的非线性系统控制方法难以达到满意的控制性能。将逆系统方法与神经网络相结合,提出的神经网络逆控制方法,不依赖系统的精确模型,结构简单,适用于具有不确定性的生物发酵过程控制。
神经网络逆控制方法虽已取得许多研究成果,但在复杂工业过程控制中,其解耦控制性能仍有待于进一步提高。为提高发酵过程的神经网络逆控制性能,本文在课题组已有的研究基础上,对神经网络逆控制方法做了进一步研究,主要工作如下
1、提出一种在线学习的神经网络逆控制方法。在分析被控系统可逆性的基础上,构造神经网络近似被控系统的逆系统,将离线训练的神经网络连接权值作为在线学习的初值,基于基函数思想,由神经网络逆系统输入与被控系统输出的误差设计神经网络权值参数的在线学习算法,并给出了在线神经网络收敛性的分析。当被控系统参数发生较大变化时,无需重新训练神经网络近似逆系统,通过神经网络连接权值参数的在线调整可减少逆系统建模误差,使控制系统始终保持良好的控制性能,满足了过程控制的实时性。
2、提出一种基于神经网络逆的自适应反馈补偿控制方法。将神经网络逆系统与被控系统串联成伪线性复合系统,考虑到神经网络逆系统建模误差对解耦控制性能的影响,设计自适应反馈补偿控制器来消除控制过程中的逆系统建模误差,提高控制系统的稳定性及神经网络逆系统的解耦性能。构造神经网络估计逆系统建模误差,将神经网络的连接权值作为自适应补偿控制器参数的初值,基于Lyapunov稳定性理论设计的补偿控制器参数自适应律,保证了闭环控制系统的稳定性及神经网络参数的最终一致有界性。神经网络逆系统解耦方法结合自适应反馈补偿控制方法,提高了非线性系统的神经网络逆控制性能。
3、提出一种基于神经网络逆的无模型自适应控制方法。该方法针对多变量耦合的非线性系统,构造的神经网络逆系统与原系统串联成包含多个独立子系统的伪线性复合系统。将逆系统建模误差及外界干扰等不确定因素看作各子系统的弱非线性项,对各子系统分别设计无模型自适应控制器。无模型自适应控制器的设计仅利用各子系统的输入输出信息,控制器的结构和参数具有自适应性。基于神经网络逆的无模型自适应控制方法结构简单,鲁棒性强,易于实现。
4、将神经网络逆控制方法与文中所提出的三种神经网络逆控制改进方法,分别应用于生物发酵过程的解耦控制中,通过数值仿真实验研究,验证了所提出的神经网络逆控制改进方法的有效性。
Biological fermentation technology is one of the important technologies for economic development and plays an important role in many fields such as agriculture and chemical. There have higher demands for automation technology in fermentation industry with the expanding of manufacturing scale. It is important for improving the quality and quantity of products to achieve high quality control in biological fermentation process. Biological fermentation process that involves the growth of organisms is complex. It is difficult to obtain high control performance by using the traditional control method. Neural network inverse (NNI) control method is presented which combines inverse system and neural network method. It is independent of precise mathematical model and applicable for fermentation process which is uncertainties.
NNI control method has been achieved considerable success, but the control performance still needs to be improved in the complex industry process. The improved neural network inverse control methods are investigated to achieve better control performance. The main contents of this thesis:
1. Online learning NNI control method is proposed. The initial values of online learning neural network are the parameters of neural network which is trained offline. According to the error between NNI system inputs and the original system outputs, a learning algorithm for neural network is designed based on the basis function theory, and then the convergence of neural network is analyzed. When the parameters of the original system vary, neural network does not need to be retrained again. The weights of neural network can be adjusted to reduce the inverse system inverse error and keep good control performance. The proposed control method satisfies the real time requirements of process control.
2. Adaptive feedback compensating control method based on NNI system is proposed. A pseudo-linear composite system can be obstained by cascading neural network well trained. Considering the effect of neural network inversion error on the control performance, adaptive feedback compensating controller is designed to eliminate the inversion error. It can improve the stability of controlled system and decoupling performance of NNI system. The initial values of adaptive compensating controller are the connective weights of neural network which is trained well to estimate the inversion error. The parameters adaptation rule is derived from Lyapunov stability analysis and guarantees that the parameter estimation errors and the tracking errors are bounded.
3. Model free adaptive control method based on NNI system is proposed for the multivariable coupling nonlinear system. A pseudo-linear composite system which includes multiple independent subsystems can be gotten by cascading NNI system and the original system. The uncertainties such as NNI modeling error and outside distraction can be regarded as the weak point of every subsystem. Then model free adaptive control method is designed for the subsystem. Input and output information are used in designing of model free adaptive control and the controller structure and parameters are adaptive. The proposed control method has the advantages of simple structure, good robustness and easy to implement.
4. NNI control method and its three improved methods are applied in biological fermentation decoupling control problem. The numerical simulation results show that the improved NNI control method is effective, feasible, and has good control performance.
神经网络逆控制方法虽已取得许多研究成果,但在复杂工业过程控制中,其解耦控制性能仍有待于进一步提高。为提高发酵过程的神经网络逆控制性能,本文在课题组已有的研究基础上,对神经网络逆控制方法做了进一步研究,主要工作如下
1、提出一种在线学习的神经网络逆控制方法。在分析被控系统可逆性的基础上,构造神经网络近似被控系统的逆系统,将离线训练的神经网络连接权值作为在线学习的初值,基于基函数思想,由神经网络逆系统输入与被控系统输出的误差设计神经网络权值参数的在线学习算法,并给出了在线神经网络收敛性的分析。当被控系统参数发生较大变化时,无需重新训练神经网络近似逆系统,通过神经网络连接权值参数的在线调整可减少逆系统建模误差,使控制系统始终保持良好的控制性能,满足了过程控制的实时性。
2、提出一种基于神经网络逆的自适应反馈补偿控制方法。将神经网络逆系统与被控系统串联成伪线性复合系统,考虑到神经网络逆系统建模误差对解耦控制性能的影响,设计自适应反馈补偿控制器来消除控制过程中的逆系统建模误差,提高控制系统的稳定性及神经网络逆系统的解耦性能。构造神经网络估计逆系统建模误差,将神经网络的连接权值作为自适应补偿控制器参数的初值,基于Lyapunov稳定性理论设计的补偿控制器参数自适应律,保证了闭环控制系统的稳定性及神经网络参数的最终一致有界性。神经网络逆系统解耦方法结合自适应反馈补偿控制方法,提高了非线性系统的神经网络逆控制性能。
3、提出一种基于神经网络逆的无模型自适应控制方法。该方法针对多变量耦合的非线性系统,构造的神经网络逆系统与原系统串联成包含多个独立子系统的伪线性复合系统。将逆系统建模误差及外界干扰等不确定因素看作各子系统的弱非线性项,对各子系统分别设计无模型自适应控制器。无模型自适应控制器的设计仅利用各子系统的输入输出信息,控制器的结构和参数具有自适应性。基于神经网络逆的无模型自适应控制方法结构简单,鲁棒性强,易于实现。
4、将神经网络逆控制方法与文中所提出的三种神经网络逆控制改进方法,分别应用于生物发酵过程的解耦控制中,通过数值仿真实验研究,验证了所提出的神经网络逆控制改进方法的有效性。
Biological fermentation technology is one of the important technologies for economic development and plays an important role in many fields such as agriculture and chemical. There have higher demands for automation technology in fermentation industry with the expanding of manufacturing scale. It is important for improving the quality and quantity of products to achieve high quality control in biological fermentation process. Biological fermentation process that involves the growth of organisms is complex. It is difficult to obtain high control performance by using the traditional control method. Neural network inverse (NNI) control method is presented which combines inverse system and neural network method. It is independent of precise mathematical model and applicable for fermentation process which is uncertainties.
NNI control method has been achieved considerable success, but the control performance still needs to be improved in the complex industry process. The improved neural network inverse control methods are investigated to achieve better control performance. The main contents of this thesis:
1. Online learning NNI control method is proposed. The initial values of online learning neural network are the parameters of neural network which is trained offline. According to the error between NNI system inputs and the original system outputs, a learning algorithm for neural network is designed based on the basis function theory, and then the convergence of neural network is analyzed. When the parameters of the original system vary, neural network does not need to be retrained again. The weights of neural network can be adjusted to reduce the inverse system inverse error and keep good control performance. The proposed control method satisfies the real time requirements of process control.
2. Adaptive feedback compensating control method based on NNI system is proposed. A pseudo-linear composite system can be obstained by cascading neural network well trained. Considering the effect of neural network inversion error on the control performance, adaptive feedback compensating controller is designed to eliminate the inversion error. It can improve the stability of controlled system and decoupling performance of NNI system. The initial values of adaptive compensating controller are the connective weights of neural network which is trained well to estimate the inversion error. The parameters adaptation rule is derived from Lyapunov stability analysis and guarantees that the parameter estimation errors and the tracking errors are bounded.
3. Model free adaptive control method based on NNI system is proposed for the multivariable coupling nonlinear system. A pseudo-linear composite system which includes multiple independent subsystems can be gotten by cascading NNI system and the original system. The uncertainties such as NNI modeling error and outside distraction can be regarded as the weak point of every subsystem. Then model free adaptive control method is designed for the subsystem. Input and output information are used in designing of model free adaptive control and the controller structure and parameters are adaptive. The proposed control method has the advantages of simple structure, good robustness and easy to implement.
4. NNI control method and its three improved methods are applied in biological fermentation decoupling control problem. The numerical simulation results show that the improved NNI control method is effective, feasible, and has good control performance.
引文
[1]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,2005.
[2]王鲜芳.生化过程动态建模及优化控制研究[D].江南大学,2009.
[3]黄丽.基于数据驱动的生物反应过程软测量与优化控制[D].江苏大学,2011.
[4]钱铭镛.发酵过程最优化控制[M].南京：江苏科学技术出版社,1998.
[5]陈允平.人工神经网络原理及其应用[M].北京：中国电力出版社,2002.
[6]戴先中.多变量非线性系统的神经网络逆控制方法[M].北京：科学出版史,2005.
[7]Ashoori A, Moshiri B, Ramezani A, et al. PH control of a fed-batch fermentation process using model predictive control [C]. Proceeding of the 14th International Congress of Cybernetics and Systems of WOSC,2008:730-738.
[8]狄轶娟,陈照章,朱湘临等.基于模糊PID控制的生物发酵温度过程控制系统[J].自动化仪表,2006,27(8)：43-45.
[9]Guo B J, Jiang A P, Hua X M, et al. Nonlinear adaptive control for multivariable chemical processes [J]. Chemical Engineering Science,2001.56:6781-6791.
[10]冯茜,李胜玉.基于仿人智能模糊控制算法的青霉素发酵pH值优化系统[J].中国酿造,2008,11：55-58.
[11]Constlantino D, Pierre D, Claude F, et al. Adaptive predictive control of dissolved oxygen concentration in a laboratory-scale bioreactor [J]. Journal of Biotechnology, 1995,43(1):21-32.
[12]殷铭,张兴华,戴先中.基于模糊神经网络的发酵过程溶解氧预估控制[J].控制与决策,2000,15(5)：523-526.
[13]Traore A, Grieu S, Puig S, et al. Fuzzy control of dissolved oxygen in a sequencing batch reactor pilot plant [J]. Chemical Engineering Journal,2005,111(1):13-19.
[14]Han H G, Qiao J F. Adaptive dissolved oxygen control based on dynamic structure neural network [J]. Applied Soft Computing,2011,11(4):3812-3820.
[15]Han H G, Qiao J F, Chen Q L. Model predictive control of dissolved oxygen concentration based on a self-organizing RBF neural network [J]. Control Engineering Practice, 2012,20(4):465-476.
[16]Hussain M A. Review of the application of neural networks in chemical process control-simulation and online implementation [J]. Artificial Intelligence in Engineering, 1999,13(1):55-68.
[17]M. Maher, B. Dahhou, F.Y. Zeng. Experimental results in model reference adaptive estimation and control of a fermentation process [J]. Control Engineer Practice, 1995,3(3):313-320.
[18]赵娟平,姜长洪.谷氨酸发酵菌体浓度的内模控制[J].控制工程,2009,16：18-23.
[19]Ferreira L S, Souza J M B D, Folly ROM. Development of an alcohol fermentation control system based on biosensor measurements interpreted by neural networks [J]. Sensors and Actuators B:Chemical,2001,75(3):166-171.
[20]常玉清,李玉朝,吕哲等.丛于两级神经网络的发酵过程多变量前馈解耦控制[J].东北大学学报(自然科学版),2007,28(7)：925-928.
[21]Nagy Z K. Model based control of a yeast fermentation bioreactor using optimally designed artificial neural networks [J]. Chemical Engineering Journal,2007,127(1):95-109.
[22]隋青美,王正欧.丛于神经网络的多变量发酵过程自适应控制[J].信息与控制,2002,31(4)：371-374.
[23]郑大钟.线性系统理论[M].第一版,北京：清华大学出版社,1999.
[24]廖晓昕.稳定性的理论,方法和应用[M].武汉：华中理工大学出版社,1999.
[25]TakabaK, Morihira N, Katayama T. A generalized lyapunov theorem for descriptor system [J]. System and Control Letters,1995,24(1):49-51.
[26]夏小华,高为炳.非线性系统控制及解耦[M].北京：科学出版社,1993.
[27]Francesco B, Ricard M M. Tracking for fully actuated mechanical systems:a geometric framework [J], Automatica,1999,35:17-34.
[28]王红.非线性控制系统与状态空间的几何结构[J],控制理论与应用,2001,18(5)：702-708.
[29]Chien T L, Chen C C, Hsu C Y. Tracking control of nonlinear automobile idle-speed time-delay system via differential geometry approach [J]. Journal of the Franklin Institute, 2005,342(7):760-775.
[30]宫清先,张化光,孟祥萍.一类MIMO非线性系统的稳定干扰解耦控制[J].控制理论与应用,2006,23(2)：199-203.
[31]孟昭军,孙昌志,安跃军等.基于状态反馈与微分几何的PMSM控制[J].沈阳工业大学学报,2007,29(4)：418-421.
[32]张亮,孙玉坤.基于微分几何的磁悬浮开关磁阻电机径向力的变结构控制[J].中国电机工程学报,2005,26(19)：121-126.
[33]李春文,冯元琨.多变量非线性控制的逆系统方法[M].北京：清华大学出版社,1990.
[34]易继锴,侯媛彬.智能控制技术[M].北京：北京工业大学出版社,1999.
[35]李人厚.智能控制理论和方法[M].西安：西安电子科技大学出版社,1999.
[36]姜培刚,李春文,龙图景等.参数和时延不确定离散时间系统的H∞鲁棒控制[J].控制与决策,2003,18(2)：190-194.
[37]徐胜元,杨成梧.一类不确定性广义非线性系统的鲁棒控制[J].控制理论与应用,2000,17(4)：624-626.
[38]Haddad W M, Chellaboina V S, Fausz J Z. Robust nonlinear feedback control for uncertain linear systems with nonquadratic performance criteria [J]. Systems and Control Letters, 1998,33(5):327-338.
[39]Riccardo M. Adaptive control of nonlinear systems:Basic results and applications [J]. Annual Reviews in Control,1997,21:55-66.
[40]Shah S, Iwai Z, Mizumoto I, et al. Simple adaptive control of processes with time-delay [J]. Journal of Process Control,1997,7(6):439-449.
[41]袁震东.自适应控制理论及其应用[M].上海：华东师范大学出版社,1988.
[42]Sliva G J, Datta A, Bhattacharyya S P. New results on the synthesis of PID controllers [J]. Automatic Control,2002,47(2):241-252.
[43]侯忠生,许建新.数据驱动控制理论及方法的回顾和展望[J].自动化学报,2009,35(6)：650-667.
[44]Hjalmarsson H. Control 1 of nonlinear systems using iterative feedback tuning [C]. Proceeding of the American Control Conference,1998:2083-2087.
[45]Campi M C, Savaresi S M, Direct nonlinear control design:the virtual reference feedback tuning approach [J]. Automatic Control,2000,45(5):954-959.
[46]李春文.多变量非线性控制的逆系统方法：理论及应用[D].清华大学,1989.
[47]Kotta U, Application of inverse system for linearization and decoupling [J]. 1987,8(5):453-457.
[48]Li D H, Jiang X Z, Li L Q, et al. The inverse system method applied to the derivation of power system nonlinear control laws [J]. Communications in Nonlinear Science and Numerical Simulation,1997,2(2):120-125.
[49]李春文,苗原,冯元琨等.非线性系统控制的逆系统方法(Ⅱ)-多变量控制理论[J].控制与决策,1997,12(6)：625-630.
[50]Hirschorn R M. Invertibility of multivariable nonlinear control systems [J]. Automatic Control,1979,24(6):855-865.
[51]Sign S N. A modified algorithm for invertibility in nonlinear system [J]. Automatic Control, 1981,26(2):595-598.
[52]Benedetto M D D, Gluminear A, Moog C H. The nonlinear interactor and its application to input-output decoupling [J]. Automatic Control,1994,39(6):1246-1250.
[53]吴热冰,李春文.一般非线性系统的构造性逆系统方法[J].控制理论与应用,2003,20(3)：345-350.
[54]Wang W C, Dai X Z. An interactor algorithm for invertibility in general nonlinear systems [C]. Word Congress on Intelligent Control and Automation,2004:59-63.
[55]Wang W C, Dai X Z, Ding Y H. Improved ANN AIS1 and its application in erythromycin fermentation process [C]. International Conference on Networking Sensing and Control, 2006:1059-1063.
[56]Ding Y H, Dai X Z, Wang W C. Modified soft-sensing method of erythromycin fermentation process variables based on assumed inherent sensor inversion [C], International Conference on Information Acquisition,2007,201-205.
[57]王万成,张媛.神经网络逆软测量方法的拓展及在生物浸出过程中的应用[J].仪器仪表学报,2012,33(3)：661-669.
[58]张兴华,戴先中.丛于逆系统方法的感应电机调速控制系统[J].控制与决策,2000,15(6)：708-711.
[59]葛友,李存文,孙政顺.逆系统方法在电力系统综合控制中的应用[J].中国电机工程学报,2001,21(4)：1-4.
[60]徐丽娜,神经网络控制[M].北京：电子工业出版社,2003.
[61]Levin A U, Narendra K S. Control of nonlinear dynamical systems using neural network: controllability and stabilization [J]. Neural Networks,1993,4(2):192-206.
[62]Narandra K S, Parthsarathy K. Identification and control of dynamic system using neural networks [J]. Neural networks,1990,1:4-27.
[63]Pham D T, Oh S J. Identification of plant inverse dynamics using neural networks [J]. Artificial Intelligence in Engineering,1999,13(3):309-320.
[64]Eimei O, Arvin A, Karl F M, et al. A modular neural network architecture for inverse kinematics model learning [J]. Neurocomputing,2001:797-805.
[65]Dai X Z, Yu D C, Ding Y H, et al. Application of ann-inversion soft-sensing method in biochemical fermentation [J]. International Journal of Information Acquisition, 2004,1(4):371-379.
[66]Ding Y H, Dai X Z, Zhang T. Low-cost fiber-optic temperature measurement system for high-voltage electrical power equipment [J]. Instrument and Measurement,2010, 59(4):923-933.
[67]Lee J W. Oh H H. Inversion control of nonlinear systems with neural network modeling [J]. Control Theory and Application,1997.144(5):481-487.
[68]Wachira D, Piyanuch T, Amornchai A, et al. Neural network inverse model-based controller for the control of a steel picking process [J]. Computers and Chemical Engineering, 2005,29(10):2110-2119.
[69]戴先中,刘军,冯纯伯.神经网络α阶逆系统在离散非线性系统控制中的应用[J].控制与决策,1997,12(3)：217-221.
[70]Dai X Z. Liu J, Tang Y. et al. Neural network ath-order inverse control of thyristor controller series compensator, Electric Power Systems Research,1998,45 (1):19-27.
[71]Dai X Z, Liu J. Neural network ath-order inverse system method for control of nonlinear continuous system [J]. Control Theory and Application,1998,145(6):519-522.
[72]Dai X Z, He D, Zhang T. MIMO system invertibility and decoupling control strategies based on ANN ath-order inversion [J]. Control Theory and Application, 2001,148(2):125-136.
[73]Dai X Z, Wang W C, Ding Y H. Estimation of some crucial variables in erythromycin fermentation process based on ANN left-inversion [J]. Lecture Notes in Computer Science, 2006,3937(3):1085-1090.
[74]Aziz N, Hussain M A, Mujtaba I M. Implementation of neural network inverse-model-based control strategy in batch reactors [J]. Computer Aided Chemical Engineering, 2003,15:708-713.
[75]陆翔,戴先中,张腾等.多目标励磁控制器的神经网络逆系统方法[J].电力系统自动化,2002,26(12)：35-38.
[76]孟正大,戴先中.基于神经网络逆系统的机器人柔顺性控制[J].东南大学学报(自然科学版),2004,35：108-112.
[77]刘贤兴,胡育文.永磁同步电机的神经网络逆动态解耦[J].中国电机工程学报,2007,27(27)：72-76.
[78]刘国海,张浩,戴先中.神经网络逆系统在电机变频调速系统中的应用[J].电工技术学报,2003,18(3)：67-71.
[79]刘国海,孙玉坤,全力等.丛于神经网络逆系统的发酵过程多变量解耦控制[J].仪器仪表学报,2006,27(3)：245-248.
[80]张今朝.丛于数据驱动的多电机同步系统建模与控制方法研究[D].江苏大学,2009.
[81]陆翔,戴先中,张凯锋.电力系统神经网络逆控制中的闭环控制器设计[J].东南大学学报(自然科学版),2004,34(1)：1]7-121.
[82]SUN Y K, Wang B, Ding S P.Multivariable decoupling control based on fuzzy-neural networkath-order inverse system in fermentation process [C], Proceedings of the 27th Chinese Control Conference,2008:500-505.
[83]冯伯纯,自适应控制[M].北京：电子工业出版社,1999.
[84]Krstic M, Kanellakopoulos I, Kolotovic P V. Nonlinear and adaptive control design [M]. New York:Wiley,1995.
[85]Wang D, Huang J. Adaptive neural network control for a class of uncertain nonlinear systems in pure-feedback form [J]. Automatica,2002,38:1365-1372.
[86]Chen F C, Khalil H K. Adaptive control of nonlinear systems using neural networks [J]. International Journal of Control,1992,55(6):1299-1317.
[87]Zhang T, Ge S S, Hang C C. Adaptive neural network control for strict-feedback nonlinear systems using back stepping design [J]. Automatica,2000,36(12):1835-1846.
[88]Hsu C F. Adaptive dynamic RBF neural controller design for a class of nonlinear systems [J]. Applied Soft Computing,2011,11:4607-4613.
[89]夏长亮,祁温雅,杨荣等.基于RBF神经网络的超声波电机参数辨识与模型参考自适应控制[J].中国电机工程学报,2004,24(7)：117-121.
[90]陈道炯,单世宝,宫赤坤等.丛于神经网络PID控制的系统非线性校正的研究[J].仪器 仪表学报,2006,27(7)：715719.
[91]Noriega J R. Wang H. A direct adaptive neural network control for unknown nonlinear systems and its application [J]. Neural networks,1998,9(1):27-34.
[92]Salem Z, Fabrice D, Edouard L, et al. Stable adaptive control with recurrent neural networks for square MIMO nonlinear systems [J]. Engineering Applications of Artificial Intelligence, 2009,22:702-717.
[93]Ciliz M K. Combined direct and indirect adaptive control for a class of nonlinear systems [J]. Control Theory and Applications,2009,3(1):151-159.
[94]Ge S S, Hang C C, Zhang T. Nonlinear adaptive control using neural network and its application to CSTR systems [J]. Journal of Process Control,1998,9:313-323.
[95]Chen L, Narendra K S. Nonlinear adaptive control using neural networks and multiple models [J]. Autolmatica,2001,37:1245-1255.
[96]Ge S S, Wang C. Adaptive neural control of uncertain MIMO nonlinear systems [J]. Neural Networks,2004,15(3):674-692.
[97]Lee C Y. Lee J J. Adaptive control for uncertain nonlinear systems based on multiple neural networks [J]. Systems, Man and Cybernetics,2004,34(1):325-333.
[98]游大海.部分状态可测的鲁棒自适应控制[J].华中理工大学学报,1990,18(4)：55-60.
[99]谢小荣,崔文进,唐义良等.静止同步补偿器无功电流的鲁棒自适应控制[J].清华大学学报(自然科学版),2001,41(3)：32-35.
[100]Chi R H, Hou Z S. A model free adaptive control approach for freeway traffic density via ramp metering [J]. International Journal of Innovative Computing, Information and Control, 2008,4(11):2829-2892.
[101]韩志刚.无模型控制方法在化肥生产中的应用[J].控制理论与应用,2004,21(6)：858-863.
[102]曹荣敏,侯忠生.永磁直线电机的无模型自适应控制方法研究[J].计算机工程与设计,2007,28(6)：1433-1436.
[103]Leandro S C, Marcelo W P, Rodrigo R S, et al. Model free adaptive control design using evolutionary neural compensator [J]. Expert Systems with Applications,2010,37:499-508.
[104]Feng Y C, Shi D L. Model free adaptive predictive control for main stream pressure system of power plant [J]. Energy Procedia,2012,17:1682-1688.
[105]曹荣敏,侯忠生.PH值中和反应过程的无模型学习自适应控制[J].计算机工程与应用,2006,28：191-194.
[106]蒋爱平,李秀英,韩志刚.从P1D到无模型控制器[J].控制工程,2005,12(3)：217-220.
[107]Hou Z S, Huang W H. The model-free learning adaptive control of a class of SISO nonlinear systems [J]. Proceedings of American Control Conference,1997:343-344.
[108]王卫卫红.无模型自适应控制理论几类问题的研究[D].北京交通大学,2008.
[109]李明忠,王福利.基于递归神经网络的一类非线性无模型系统的自适应控制[J].控制与决策,1997,12(1)：64-72.
[110]刘国海,孙玉坤,全力等.多变量生物发酵过程的解耦控制[J].东南大学学报(自然科学版),2004,34：155-159.
[111]Simone S, Alberto D B. Properties of block feedback neural networks [J]. Neural networks, 1993,8(4):975-990.
[112]Funahashi K I. On the approximate realization of continuous mappings by neural networks [J]. Neural Networks,1989,2(3):183-192.
[113]Narandra K S, Parthsarathy K. Neural networks and dynamical systems[J]. International Journal of Approximate Reasoning.1992.6(2):109-131.
[114]Wu W, Wang J, Cheng M S, et al. Convergence analysis of online gradient method for BP neural networks [J]. Neural Networks,2011,24(1):91-98.
[115]Gadkar K G, Mehra S, Gomes J. On-line adaptation of neural networks for bioprocess control [J]. Computers and Chemical Engineering,2005,29(5):1047-1057.
[116]Nakama T. Theoretical analysis of batch and on-line training for gradient descent learning in neural networks [J]. Neurocomputing,2009,73:151-159.
[117]Xu Q H, Dai X Z. Online learning ANN-Inversion excitation controller of the multi-machine power system [C]. Proceedings of the Chinese Control and Decision Conference,2008:758-763.
[118]鲍立威,李玉泉,史良.关于BP算法模型的缺陷的讨论[J].模式识别与人工智能,1995,8(1)：1-5.
[119]李众立,王成端.神经网络学习算法的研究[J].系统工程与电子技术,1997,5：213-216.
[120]Oh S H. Error back-propagation algorithm for classification of imbalanced data [J]. Neurocomputing,2011,74(6):1058-1061.
[121]李炯城,黄汉雄.神经网络中LMBP算法收敛速度改进的研究[J].计算机工程与应用,2006,16：46-49.
[122]Draguna V, Frank L. Neural network approach to continuous-time direct adaptive optimal control for partially unknown nonlinear systems [J]. Neural Networks,2009,22:237-246.
[123]田雨波.混合神经网络技术[M].科学技术出版社,北京,2009.
[124]李明,林永君,马永光.自适应神经元非模型多变量系统解耦控制[J].计算机仿真,2003,20(3)：68-71.
[125]Ku C C, Lee K Y. Diagonal recurrent networks for dynamic systems control [J]. Neural Networks,1995,6(1):144-156.
[126]Ahmad A, Behzad M, Ali K S, et al. Optimal control of a nonlinear fed-batch fermentation process using model predictive approach [J]. Journal of Process Control, 2009,19:1162-1173.
[127]Johnson A. The control of fed-batch fermentation process-a survey [J]. Automatica, 1987,23:691-705.
[128]王金鹏,曾爱武,袁希钢.发酵生产酒精的动力学模型研究进展[J].化学工业与工程,2005,22(6)：482-486.
[129]Szederkenyi G, Kristensen N R, Hangos K M, et al. Nonlinear analysis andcontrol of a continuous fermentation process [J]. Computers and Chemical Engineering, 2002,26:659-670.
[130]Bajpai R, Reuss M. A mechanistic model for penicillin production [J]. Journal of Chemical Technology and Biotechnology,1980,30:330-344.
[131]Liu G H, Yu S, Mei C L, et al. A novel soft sensor model based on artificial neural network in the fermentation process [J]. African Journal of Biotechnology, 2011,10(85):19780-19787.
[132]Dai X Z, Wang W C, Ding Y H, et al. "Assumed inherent sensor" inversion based ANN dynamic soft-sensing method and its application in erythromycin fermentation process [J]. Computers and Chemical Engineering,2006,30:1203-1225.
[133]Anthony J C, Naira H, Moshe I. Adaptive output feedback control of nonlinear systems using neural networks [J]. Automatica,2001,37:1201-1211.
[134]朱家强,郭锁风.具有伪控制补偿的自适应动态逆控制系统设计与仿真[J].系统仿真 学报,2003.15(5)：727-730.
[135]徐庆宏,戴先中.丛于在线学习RBF神经网络的汽门开度自适应补偿控制方法[J].电机与控制学报,2010,14(2)：13-18.
[136]Naria H, Anthony J C. Adaptive output feedback control of uncertain multi-input multi-output systems using single hidden layer neural networks [C]. Proceedings of the American Control Conference,2002:1555-1560.
[137]Park J H, Kim S H. Direct adaptive output-feedback fuzzy controller for a non affine nonlinear system [J]. Control Theory and Application,2004,15(1):65-71.
[138]朱家强,朱纪洪,郭锁风等.丛于神经网络的鲁棒自适应逆飞行控制[J].控制理论与应用,2005,22(2)：182-188.
[139]朱家强,郭锁风.一种丛于神经网络补偿动态逆误差的方法[J].飞行力学,2003,21(1)：28-31.
[140]王源.不确定非线性系统的神经网络自适应重构控制[D],南京航空航天大学,2002.
[141]Ge S S. Wang C. Adaptive neural network control of uncertain MIMO nonlinear systems [J]. Neural Networks,2004,15(3):674-692.
[142]Wang D. Huang J. Adaptive neural network control for a class of uncertain nonlinear systems in pure-feedback form [J]. Automatica,2002,38:1365-1372.
[143]侯忠生.非参数系统参数辨识自适应控制及无模型学习自适应控制[D],东北大学,1994.
[144]侯忠生.1非参数模型及其自适应控制理论[M].北京：科学出版社,1999.
[145]卜旭辉.数据驱动无模型自适应控制与学习控制的鲁棒性问题研究[D].北京交通大学,2011.
[146]何丹,戴先中,张兴华等.非线性MIMO系统线性化解耦的一种新方法(Ⅱ)-离散时间系统[J].控制与决策,1999,14(6)：631-635.
[147]何丹.非线性控制系统的神经网络逆系统方法[D].东南大学,1999.
[148]吴黎明,柴天佑.一类非线性离散时间系统的神经网络解耦策略[J].自动化学报,1997,23(2)：207-212.
[2]王鲜芳.生化过程动态建模及优化控制研究[D].江南大学,2009.
[3]黄丽.基于数据驱动的生物反应过程软测量与优化控制[D].江苏大学,2011.
[4]钱铭镛.发酵过程最优化控制[M].南京：江苏科学技术出版社,1998.
[5]陈允平.人工神经网络原理及其应用[M].北京：中国电力出版社,2002.
[6]戴先中.多变量非线性系统的神经网络逆控制方法[M].北京：科学出版史,2005.
[7]Ashoori A, Moshiri B, Ramezani A, et al. PH control of a fed-batch fermentation process using model predictive control [C]. Proceeding of the 14th International Congress of Cybernetics and Systems of WOSC,2008:730-738.
[8]狄轶娟,陈照章,朱湘临等.基于模糊PID控制的生物发酵温度过程控制系统[J].自动化仪表,2006,27(8)：43-45.
[9]Guo B J, Jiang A P, Hua X M, et al. Nonlinear adaptive control for multivariable chemical processes [J]. Chemical Engineering Science,2001.56:6781-6791.
[10]冯茜,李胜玉.基于仿人智能模糊控制算法的青霉素发酵pH值优化系统[J].中国酿造,2008,11：55-58.
[11]Constlantino D, Pierre D, Claude F, et al. Adaptive predictive control of dissolved oxygen concentration in a laboratory-scale bioreactor [J]. Journal of Biotechnology, 1995,43(1):21-32.
[12]殷铭,张兴华,戴先中.基于模糊神经网络的发酵过程溶解氧预估控制[J].控制与决策,2000,15(5)：523-526.
[13]Traore A, Grieu S, Puig S, et al. Fuzzy control of dissolved oxygen in a sequencing batch reactor pilot plant [J]. Chemical Engineering Journal,2005,111(1):13-19.
[14]Han H G, Qiao J F. Adaptive dissolved oxygen control based on dynamic structure neural network [J]. Applied Soft Computing,2011,11(4):3812-3820.
[15]Han H G, Qiao J F, Chen Q L. Model predictive control of dissolved oxygen concentration based on a self-organizing RBF neural network [J]. Control Engineering Practice, 2012,20(4):465-476.
[16]Hussain M A. Review of the application of neural networks in chemical process control-simulation and online implementation [J]. Artificial Intelligence in Engineering, 1999,13(1):55-68.
[17]M. Maher, B. Dahhou, F.Y. Zeng. Experimental results in model reference adaptive estimation and control of a fermentation process [J]. Control Engineer Practice, 1995,3(3):313-320.
[18]赵娟平,姜长洪.谷氨酸发酵菌体浓度的内模控制[J].控制工程,2009,16：18-23.
[19]Ferreira L S, Souza J M B D, Folly ROM. Development of an alcohol fermentation control system based on biosensor measurements interpreted by neural networks [J]. Sensors and Actuators B:Chemical,2001,75(3):166-171.
[20]常玉清,李玉朝,吕哲等.丛于两级神经网络的发酵过程多变量前馈解耦控制[J].东北大学学报(自然科学版),2007,28(7)：925-928.
[21]Nagy Z K. Model based control of a yeast fermentation bioreactor using optimally designed artificial neural networks [J]. Chemical Engineering Journal,2007,127(1):95-109.
[22]隋青美,王正欧.丛于神经网络的多变量发酵过程自适应控制[J].信息与控制,2002,31(4)：371-374.
[23]郑大钟.线性系统理论[M].第一版,北京：清华大学出版社,1999.
[24]廖晓昕.稳定性的理论,方法和应用[M].武汉：华中理工大学出版社,1999.
[25]TakabaK, Morihira N, Katayama T. A generalized lyapunov theorem for descriptor system [J]. System and Control Letters,1995,24(1):49-51.
[26]夏小华,高为炳.非线性系统控制及解耦[M].北京：科学出版社,1993.
[27]Francesco B, Ricard M M. Tracking for fully actuated mechanical systems:a geometric framework [J], Automatica,1999,35:17-34.
[28]王红.非线性控制系统与状态空间的几何结构[J],控制理论与应用,2001,18(5)：702-708.
[29]Chien T L, Chen C C, Hsu C Y. Tracking control of nonlinear automobile idle-speed time-delay system via differential geometry approach [J]. Journal of the Franklin Institute, 2005,342(7):760-775.
[30]宫清先,张化光,孟祥萍.一类MIMO非线性系统的稳定干扰解耦控制[J].控制理论与应用,2006,23(2)：199-203.
[31]孟昭军,孙昌志,安跃军等.基于状态反馈与微分几何的PMSM控制[J].沈阳工业大学学报,2007,29(4)：418-421.
[32]张亮,孙玉坤.基于微分几何的磁悬浮开关磁阻电机径向力的变结构控制[J].中国电机工程学报,2005,26(19)：121-126.
[33]李春文,冯元琨.多变量非线性控制的逆系统方法[M].北京：清华大学出版社,1990.
[34]易继锴,侯媛彬.智能控制技术[M].北京：北京工业大学出版社,1999.
[35]李人厚.智能控制理论和方法[M].西安：西安电子科技大学出版社,1999.
[36]姜培刚,李春文,龙图景等.参数和时延不确定离散时间系统的H∞鲁棒控制[J].控制与决策,2003,18(2)：190-194.
[37]徐胜元,杨成梧.一类不确定性广义非线性系统的鲁棒控制[J].控制理论与应用,2000,17(4)：624-626.
[38]Haddad W M, Chellaboina V S, Fausz J Z. Robust nonlinear feedback control for uncertain linear systems with nonquadratic performance criteria [J]. Systems and Control Letters, 1998,33(5):327-338.
[39]Riccardo M. Adaptive control of nonlinear systems:Basic results and applications [J]. Annual Reviews in Control,1997,21:55-66.
[40]Shah S, Iwai Z, Mizumoto I, et al. Simple adaptive control of processes with time-delay [J]. Journal of Process Control,1997,7(6):439-449.
[41]袁震东.自适应控制理论及其应用[M].上海：华东师范大学出版社,1988.
[42]Sliva G J, Datta A, Bhattacharyya S P. New results on the synthesis of PID controllers [J]. Automatic Control,2002,47(2):241-252.
[43]侯忠生,许建新.数据驱动控制理论及方法的回顾和展望[J].自动化学报,2009,35(6)：650-667.
[44]Hjalmarsson H. Control 1 of nonlinear systems using iterative feedback tuning [C]. Proceeding of the American Control Conference,1998:2083-2087.
[45]Campi M C, Savaresi S M, Direct nonlinear control design:the virtual reference feedback tuning approach [J]. Automatic Control,2000,45(5):954-959.
[46]李春文.多变量非线性控制的逆系统方法：理论及应用[D].清华大学,1989.
[47]Kotta U, Application of inverse system for linearization and decoupling [J]. 1987,8(5):453-457.
[48]Li D H, Jiang X Z, Li L Q, et al. The inverse system method applied to the derivation of power system nonlinear control laws [J]. Communications in Nonlinear Science and Numerical Simulation,1997,2(2):120-125.
[49]李春文,苗原,冯元琨等.非线性系统控制的逆系统方法(Ⅱ)-多变量控制理论[J].控制与决策,1997,12(6)：625-630.
[50]Hirschorn R M. Invertibility of multivariable nonlinear control systems [J]. Automatic Control,1979,24(6):855-865.
[51]Sign S N. A modified algorithm for invertibility in nonlinear system [J]. Automatic Control, 1981,26(2):595-598.
[52]Benedetto M D D, Gluminear A, Moog C H. The nonlinear interactor and its application to input-output decoupling [J]. Automatic Control,1994,39(6):1246-1250.
[53]吴热冰,李春文.一般非线性系统的构造性逆系统方法[J].控制理论与应用,2003,20(3)：345-350.
[54]Wang W C, Dai X Z. An interactor algorithm for invertibility in general nonlinear systems [C]. Word Congress on Intelligent Control and Automation,2004:59-63.
[55]Wang W C, Dai X Z, Ding Y H. Improved ANN AIS1 and its application in erythromycin fermentation process [C]. International Conference on Networking Sensing and Control, 2006:1059-1063.
[56]Ding Y H, Dai X Z, Wang W C. Modified soft-sensing method of erythromycin fermentation process variables based on assumed inherent sensor inversion [C], International Conference on Information Acquisition,2007,201-205.
[57]王万成,张媛.神经网络逆软测量方法的拓展及在生物浸出过程中的应用[J].仪器仪表学报,2012,33(3)：661-669.
[58]张兴华,戴先中.丛于逆系统方法的感应电机调速控制系统[J].控制与决策,2000,15(6)：708-711.
[59]葛友,李存文,孙政顺.逆系统方法在电力系统综合控制中的应用[J].中国电机工程学报,2001,21(4)：1-4.
[60]徐丽娜,神经网络控制[M].北京：电子工业出版社,2003.
[61]Levin A U, Narendra K S. Control of nonlinear dynamical systems using neural network: controllability and stabilization [J]. Neural Networks,1993,4(2):192-206.
[62]Narandra K S, Parthsarathy K. Identification and control of dynamic system using neural networks [J]. Neural networks,1990,1:4-27.
[63]Pham D T, Oh S J. Identification of plant inverse dynamics using neural networks [J]. Artificial Intelligence in Engineering,1999,13(3):309-320.
[64]Eimei O, Arvin A, Karl F M, et al. A modular neural network architecture for inverse kinematics model learning [J]. Neurocomputing,2001:797-805.
[65]Dai X Z, Yu D C, Ding Y H, et al. Application of ann-inversion soft-sensing method in biochemical fermentation [J]. International Journal of Information Acquisition, 2004,1(4):371-379.
[66]Ding Y H, Dai X Z, Zhang T. Low-cost fiber-optic temperature measurement system for high-voltage electrical power equipment [J]. Instrument and Measurement,2010, 59(4):923-933.
[67]Lee J W. Oh H H. Inversion control of nonlinear systems with neural network modeling [J]. Control Theory and Application,1997.144(5):481-487.
[68]Wachira D, Piyanuch T, Amornchai A, et al. Neural network inverse model-based controller for the control of a steel picking process [J]. Computers and Chemical Engineering, 2005,29(10):2110-2119.
[69]戴先中,刘军,冯纯伯.神经网络α阶逆系统在离散非线性系统控制中的应用[J].控制与决策,1997,12(3)：217-221.
[70]Dai X Z. Liu J, Tang Y. et al. Neural network ath-order inverse control of thyristor controller series compensator, Electric Power Systems Research,1998,45 (1):19-27.
[71]Dai X Z, Liu J. Neural network ath-order inverse system method for control of nonlinear continuous system [J]. Control Theory and Application,1998,145(6):519-522.
[72]Dai X Z, He D, Zhang T. MIMO system invertibility and decoupling control strategies based on ANN ath-order inversion [J]. Control Theory and Application, 2001,148(2):125-136.
[73]Dai X Z, Wang W C, Ding Y H. Estimation of some crucial variables in erythromycin fermentation process based on ANN left-inversion [J]. Lecture Notes in Computer Science, 2006,3937(3):1085-1090.
[74]Aziz N, Hussain M A, Mujtaba I M. Implementation of neural network inverse-model-based control strategy in batch reactors [J]. Computer Aided Chemical Engineering, 2003,15:708-713.
[75]陆翔,戴先中,张腾等.多目标励磁控制器的神经网络逆系统方法[J].电力系统自动化,2002,26(12)：35-38.
[76]孟正大,戴先中.基于神经网络逆系统的机器人柔顺性控制[J].东南大学学报(自然科学版),2004,35：108-112.
[77]刘贤兴,胡育文.永磁同步电机的神经网络逆动态解耦[J].中国电机工程学报,2007,27(27)：72-76.
[78]刘国海,张浩,戴先中.神经网络逆系统在电机变频调速系统中的应用[J].电工技术学报,2003,18(3)：67-71.
[79]刘国海,孙玉坤,全力等.丛于神经网络逆系统的发酵过程多变量解耦控制[J].仪器仪表学报,2006,27(3)：245-248.
[80]张今朝.丛于数据驱动的多电机同步系统建模与控制方法研究[D].江苏大学,2009.
[81]陆翔,戴先中,张凯锋.电力系统神经网络逆控制中的闭环控制器设计[J].东南大学学报(自然科学版),2004,34(1)：1]7-121.
[82]SUN Y K, Wang B, Ding S P.Multivariable decoupling control based on fuzzy-neural networkath-order inverse system in fermentation process [C], Proceedings of the 27th Chinese Control Conference,2008:500-505.
[83]冯伯纯,自适应控制[M].北京：电子工业出版社,1999.
[84]Krstic M, Kanellakopoulos I, Kolotovic P V. Nonlinear and adaptive control design [M]. New York:Wiley,1995.
[85]Wang D, Huang J. Adaptive neural network control for a class of uncertain nonlinear systems in pure-feedback form [J]. Automatica,2002,38:1365-1372.
[86]Chen F C, Khalil H K. Adaptive control of nonlinear systems using neural networks [J]. International Journal of Control,1992,55(6):1299-1317.
[87]Zhang T, Ge S S, Hang C C. Adaptive neural network control for strict-feedback nonlinear systems using back stepping design [J]. Automatica,2000,36(12):1835-1846.
[88]Hsu C F. Adaptive dynamic RBF neural controller design for a class of nonlinear systems [J]. Applied Soft Computing,2011,11:4607-4613.
[89]夏长亮,祁温雅,杨荣等.基于RBF神经网络的超声波电机参数辨识与模型参考自适应控制[J].中国电机工程学报,2004,24(7)：117-121.
[90]陈道炯,单世宝,宫赤坤等.丛于神经网络PID控制的系统非线性校正的研究[J].仪器 仪表学报,2006,27(7)：715719.
[91]Noriega J R. Wang H. A direct adaptive neural network control for unknown nonlinear systems and its application [J]. Neural networks,1998,9(1):27-34.
[92]Salem Z, Fabrice D, Edouard L, et al. Stable adaptive control with recurrent neural networks for square MIMO nonlinear systems [J]. Engineering Applications of Artificial Intelligence, 2009,22:702-717.
[93]Ciliz M K. Combined direct and indirect adaptive control for a class of nonlinear systems [J]. Control Theory and Applications,2009,3(1):151-159.
[94]Ge S S, Hang C C, Zhang T. Nonlinear adaptive control using neural network and its application to CSTR systems [J]. Journal of Process Control,1998,9:313-323.
[95]Chen L, Narendra K S. Nonlinear adaptive control using neural networks and multiple models [J]. Autolmatica,2001,37:1245-1255.
[96]Ge S S, Wang C. Adaptive neural control of uncertain MIMO nonlinear systems [J]. Neural Networks,2004,15(3):674-692.
[97]Lee C Y. Lee J J. Adaptive control for uncertain nonlinear systems based on multiple neural networks [J]. Systems, Man and Cybernetics,2004,34(1):325-333.
[98]游大海.部分状态可测的鲁棒自适应控制[J].华中理工大学学报,1990,18(4)：55-60.
[99]谢小荣,崔文进,唐义良等.静止同步补偿器无功电流的鲁棒自适应控制[J].清华大学学报(自然科学版),2001,41(3)：32-35.
[100]Chi R H, Hou Z S. A model free adaptive control approach for freeway traffic density via ramp metering [J]. International Journal of Innovative Computing, Information and Control, 2008,4(11):2829-2892.
[101]韩志刚.无模型控制方法在化肥生产中的应用[J].控制理论与应用,2004,21(6)：858-863.
[102]曹荣敏,侯忠生.永磁直线电机的无模型自适应控制方法研究[J].计算机工程与设计,2007,28(6)：1433-1436.
[103]Leandro S C, Marcelo W P, Rodrigo R S, et al. Model free adaptive control design using evolutionary neural compensator [J]. Expert Systems with Applications,2010,37:499-508.
[104]Feng Y C, Shi D L. Model free adaptive predictive control for main stream pressure system of power plant [J]. Energy Procedia,2012,17:1682-1688.
[105]曹荣敏,侯忠生.PH值中和反应过程的无模型学习自适应控制[J].计算机工程与应用,2006,28：191-194.
[106]蒋爱平,李秀英,韩志刚.从P1D到无模型控制器[J].控制工程,2005,12(3)：217-220.
[107]Hou Z S, Huang W H. The model-free learning adaptive control of a class of SISO nonlinear systems [J]. Proceedings of American Control Conference,1997:343-344.
[108]王卫卫红.无模型自适应控制理论几类问题的研究[D].北京交通大学,2008.
[109]李明忠,王福利.基于递归神经网络的一类非线性无模型系统的自适应控制[J].控制与决策,1997,12(1)：64-72.
[110]刘国海,孙玉坤,全力等.多变量生物发酵过程的解耦控制[J].东南大学学报(自然科学版),2004,34：155-159.
[111]Simone S, Alberto D B. Properties of block feedback neural networks [J]. Neural networks, 1993,8(4):975-990.
[112]Funahashi K I. On the approximate realization of continuous mappings by neural networks [J]. Neural Networks,1989,2(3):183-192.
[113]Narandra K S, Parthsarathy K. Neural networks and dynamical systems[J]. International Journal of Approximate Reasoning.1992.6(2):109-131.
[114]Wu W, Wang J, Cheng M S, et al. Convergence analysis of online gradient method for BP neural networks [J]. Neural Networks,2011,24(1):91-98.
[115]Gadkar K G, Mehra S, Gomes J. On-line adaptation of neural networks for bioprocess control [J]. Computers and Chemical Engineering,2005,29(5):1047-1057.
[116]Nakama T. Theoretical analysis of batch and on-line training for gradient descent learning in neural networks [J]. Neurocomputing,2009,73:151-159.
[117]Xu Q H, Dai X Z. Online learning ANN-Inversion excitation controller of the multi-machine power system [C]. Proceedings of the Chinese Control and Decision Conference,2008:758-763.
[118]鲍立威,李玉泉,史良.关于BP算法模型的缺陷的讨论[J].模式识别与人工智能,1995,8(1)：1-5.
[119]李众立,王成端.神经网络学习算法的研究[J].系统工程与电子技术,1997,5：213-216.
[120]Oh S H. Error back-propagation algorithm for classification of imbalanced data [J]. Neurocomputing,2011,74(6):1058-1061.
[121]李炯城,黄汉雄.神经网络中LMBP算法收敛速度改进的研究[J].计算机工程与应用,2006,16：46-49.
[122]Draguna V, Frank L. Neural network approach to continuous-time direct adaptive optimal control for partially unknown nonlinear systems [J]. Neural Networks,2009,22:237-246.
[123]田雨波.混合神经网络技术[M].科学技术出版社,北京,2009.
[124]李明,林永君,马永光.自适应神经元非模型多变量系统解耦控制[J].计算机仿真,2003,20(3)：68-71.
[125]Ku C C, Lee K Y. Diagonal recurrent networks for dynamic systems control [J]. Neural Networks,1995,6(1):144-156.
[126]Ahmad A, Behzad M, Ali K S, et al. Optimal control of a nonlinear fed-batch fermentation process using model predictive approach [J]. Journal of Process Control, 2009,19:1162-1173.
[127]Johnson A. The control of fed-batch fermentation process-a survey [J]. Automatica, 1987,23:691-705.
[128]王金鹏,曾爱武,袁希钢.发酵生产酒精的动力学模型研究进展[J].化学工业与工程,2005,22(6)：482-486.
[129]Szederkenyi G, Kristensen N R, Hangos K M, et al. Nonlinear analysis andcontrol of a continuous fermentation process [J]. Computers and Chemical Engineering, 2002,26:659-670.
[130]Bajpai R, Reuss M. A mechanistic model for penicillin production [J]. Journal of Chemical Technology and Biotechnology,1980,30:330-344.
[131]Liu G H, Yu S, Mei C L, et al. A novel soft sensor model based on artificial neural network in the fermentation process [J]. African Journal of Biotechnology, 2011,10(85):19780-19787.
[132]Dai X Z, Wang W C, Ding Y H, et al. "Assumed inherent sensor" inversion based ANN dynamic soft-sensing method and its application in erythromycin fermentation process [J]. Computers and Chemical Engineering,2006,30:1203-1225.
[133]Anthony J C, Naira H, Moshe I. Adaptive output feedback control of nonlinear systems using neural networks [J]. Automatica,2001,37:1201-1211.
[134]朱家强,郭锁风.具有伪控制补偿的自适应动态逆控制系统设计与仿真[J].系统仿真 学报,2003.15(5)：727-730.
[135]徐庆宏,戴先中.丛于在线学习RBF神经网络的汽门开度自适应补偿控制方法[J].电机与控制学报,2010,14(2)：13-18.
[136]Naria H, Anthony J C. Adaptive output feedback control of uncertain multi-input multi-output systems using single hidden layer neural networks [C]. Proceedings of the American Control Conference,2002:1555-1560.
[137]Park J H, Kim S H. Direct adaptive output-feedback fuzzy controller for a non affine nonlinear system [J]. Control Theory and Application,2004,15(1):65-71.
[138]朱家强,朱纪洪,郭锁风等.丛于神经网络的鲁棒自适应逆飞行控制[J].控制理论与应用,2005,22(2)：182-188.
[139]朱家强,郭锁风.一种丛于神经网络补偿动态逆误差的方法[J].飞行力学,2003,21(1)：28-31.
[140]王源.不确定非线性系统的神经网络自适应重构控制[D],南京航空航天大学,2002.
[141]Ge S S. Wang C. Adaptive neural network control of uncertain MIMO nonlinear systems [J]. Neural Networks,2004,15(3):674-692.
[142]Wang D. Huang J. Adaptive neural network control for a class of uncertain nonlinear systems in pure-feedback form [J]. Automatica,2002,38:1365-1372.
[143]侯忠生.非参数系统参数辨识自适应控制及无模型学习自适应控制[D],东北大学,1994.
[144]侯忠生.1非参数模型及其自适应控制理论[M].北京：科学出版社,1999.
[145]卜旭辉.数据驱动无模型自适应控制与学习控制的鲁棒性问题研究[D].北京交通大学,2011.
[146]何丹,戴先中,张兴华等.非线性MIMO系统线性化解耦的一种新方法(Ⅱ)-离散时间系统[J].控制与决策,1999,14(6)：631-635.
[147]何丹.非线性控制系统的神经网络逆系统方法[D].东南大学,1999.
[148]吴黎明,柴天佑.一类非线性离散时间系统的神经网络解耦策略[J].自动化学报,1997,23(2)：207-212.