Generalized hybrid control synthesis for affine systems using sequential adaptive networks

BACKGROUND: A generalized methodology for the synthesis of a hybrid controller for affine systems using sequential adaptive networks (SAN) is presented. SAN consists of an assembly of neural networks that are ordered in a chronological sequence, with one network assigned to each sampling interval. Using a suitable process model based on oxygen metabolism and an a priori objective function, a hybrid control law is derived that can use online measurements and the states predicted by SAN for computing the desired control action. RESULTS: The performance of the SAN–hybrid controller is tested for simulated fed-batch production of methionine for three different process conditions. Simulations assume that online measurements of dissolved oxygen (DO) concentration are available. The performance of the SAN–hybrid controller gave an NRMSE of ∼10−4 in the absence of noise, ∼10−3 and ∼10−2 for ± 5% and ± 10% noise in the DO measurement and ∼10−2 for parameter uncertainty when compared with the ideal model prediction. CONCLUSIONS: The observed performance for unmeasured state prediction and control implementation shows that the proposed SAN–hybrid controller can efficiently compute the manipulated variable required to maintain methionine production along the optimized trajectory for different conditions. The test results show that the SAN–hybrid controller can be used for online real-time implementation in fed-batch bioprocesses. Copyright © 2009 Society of Chemical Industry

[1]  Naonori Ueda,et al.  Optimal Linear Combination of Neural Networks for Improving Classification Performance , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  T. R. Sreekrishnan,et al.  Production of methionine by a multi-analogue resistant mutant of Corynebacterium lilium , 2003 .

[3]  James Gomes,et al.  Methionine production by fermentation. , 2005, Biotechnology advances.

[4]  Philippe Bogaerts,et al.  Parameter identification for state estimation—application to bioprocess software sensors , 2004 .

[5]  Pablo M. Granitto,et al.  Neural network ensembles: evaluation of aggregation algorithms , 2005, Artif. Intell..

[6]  Y.-H. Zhu,et al.  Application of neural networks to lysine production , 1996 .

[7]  Kapil G. Gadkar,et al.  On-line adaptation of neural networks for bioprocess control , 2005, Comput. Chem. Eng..

[8]  Jyh-Shyong Chang,et al.  Neural-network rate-function modeling of submerged cultivation of Monascus anka , 2006 .

[9]  Vladimir M. Krasnopolsky,et al.  Ensemble of Neural Network Emulations for Climate Model Physics: The Impact on Climate Simulations , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[10]  James Gomes,et al.  Effect of Dissolved Oxygen on Continuous Production of Methionine , 2001 .

[11]  James Gomes,et al.  Sequential adaptive networks: An ensemble of neural networks for feed forward control of L-methionine production , 2009 .

[12]  G. Ibarra-Berastegi,et al.  Neural networks as a tool for control and management of a biological reactor for treating hydrogen sulphide , 2006, Bioprocess and biosystems engineering.

[13]  Kin Keung Lai,et al.  A Novel Nonlinear Neural Network Ensemble Model for Financial Time Series Forecasting , 2006, International Conference on Computational Science.

[14]  Jie Zhang,et al.  Neural network model-based on-line re-optimisation control of fed-batch processes using a modified iterative dynamic programming algorithm , 2005 .

[15]  Wei Wu,et al.  Model Predictive Control of Nonlinear Distributed Parameter Systems Using Spatial Neural-Network Architectures , 2008 .

[16]  Zoltan K. Nagy,et al.  Model based control of a yeast fermentation bioreactor using optimally designed artificial neural networks , 2007 .

[17]  James Gomes,et al.  A model for L‐methionine production describing oxygen–productivity relationship , 2009 .

[18]  Jie Zhang,et al.  Combination of multiple neural networks using data fusion techniques for enhanced nonlinear process modelling , 2005, Comput. Chem. Eng..

[19]  Ana P. Teixeira,et al.  Modelling and optimization of a recombinant BHK-21 cultivation process using hybrid grey-box systems. , 2005, Journal of biotechnology.

[20]  Yuan Tian,et al.  Optimal control of a fed-batch bioreactor based upon an augmented recurrent neural network model , 2002, Neurocomputing.

[21]  Eric B. Bartlett,et al.  Process modeling using stacked neural networks , 1996 .

[22]  David H. Wolpert,et al.  Stacked generalization , 1992, Neural Networks.

[23]  Thomas Scheper,et al.  Biosensors in bioprocess monitoring , 1996 .

[24]  James Gomes,et al.  Production of l-methionine by submerged fermentation: A review , 2005 .

[25]  Jin Park,et al.  A sequential neural network model for diabetes prediction , 2001, Artif. Intell. Medicine.

[26]  Lyle H. Ungar,et al.  A hybrid neural network‐first principles approach to process modeling , 1992 .

[27]  Carl-Fredrik Mandenius,et al.  Integration of distributed multi-analyzer monitoring and control in bioprocessing based on a real-time expert system. , 2003, Journal of biotechnology.

[28]  Joaquim M. S. Cabral,et al.  Real-time bioprocess monitoring: Part I: In situ sensors , 2006 .

[29]  W. Fred Ramirez,et al.  Dynamic hybrid neural network model of an industrial fed-batch fermentation process to produce foreign protein , 2007, Comput. Chem. Eng..

[30]  C. Willmott.  Some Comments on the Evaluation of Model Performance , 1982 .

[31]  B. Kulkarni,et al.  Modeling and monitoring of batch processes using principal component analysis (PCA) assisted generalized regression neural networks (GRNN) , 2004 .

[32]  Michael I. Jordan,et al.  Hierarchical Mixtures of Experts and the EM Algorithm , 1994, Neural Computation.

[33]  Yuan Tian,et al.  Modeling and optimal control of a batch polymerization reactor using a hybrid stacked recurrent neural network model , 2001 .

[34]  Zhongping Shi,et al.  An on-line adaptive control based on DO/pH measurements and ANN pattern recognition model for fed-batch cultivation , 2006 .

[35]  Scott C. James,et al.  Comparative study of black-box and hybrid estimation methods in fed-batch fermentation , 2002 .

[36]  Lyle H. Ungar,et al.  A NEURAL NETWORK ARCHITECTURE THAT COMPUTES ITS OWN RELIABILITY , 1992 .

[37]  Pratap R. Patnaik,et al.  Neural and Hybrid Neural Modeling and Control of Fed‐Batch Fermentation for Streptokinase: Comparative Evaluation under Nonideal Conditions , 2008 .

[38]  Claire Komives,et al.  Bioreactor state estimation and control. , 2003, Current opinion in biotechnology.

[39]  P. Patnaik,et al.  Neural control of an imperfectly mixed fed-batch bioreactor for recombinant β-galactosidase , 1999 .

[40]  Maciej Ławryńczuk,et al.  Modelling and nonlinear predictive control of a yeast fermentation biochemical reactor using neural networks , 2008 .

[41]  John Villadsen,et al.  Modelling of microbial kinetics , 1992 .

[42]  Sanjeev S. Tambe,et al.  Soft-sensor development for fed-batch bioreactors using support vector regression , 2006 .

[43]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[44]  Enmin Feng,et al.  Nonlinear hybrid kinetic system of microbial bioconversion in fed-batch culture , 2008 .

[45]  Maurício Bezerra de Souza,et al.  A hybrid neural model (HNM) for the on-line monitoring of lipase production by Candida rugosa , 2007 .

[46]  James Gomes,et al.  Substrate trajectory tracking for methionine production in a fed-batch bioreactor using nonlinear adaptive control , 2007 .

[47]  K. B. Ramachandran,et al.  The study of neural network-based controller for controlling dissolved oxygen concentration in a sequencing batch reactor , 2006, Bioprocess and biosystems engineering.

[48]  Claudio O. Stöckle,et al.  Evaluation of estimated weather data for calculating Penman-Monteith reference crop evapotranspiration , 2004, Irrigation Science.