A novel identification method for hybrid (N)PLS dynamical systems with application to bioprocesses

This paper presents a method for the identification of nonlinear partial least square (NPLS) models embedded in macroscopic material balance equations with application to bioprocess modeling. The proposed model belongs to the class of hybrid models and consists of a NPLS submodel, which mimics the cellular system, coupled to a set of material balance equations defining the reactor dynamics. The method presented is an analog to the non-iterative partial least square (NIPALS) algorithm where the PLS inner model is trained using the sensitivity method. This strategy avoids the estimation of the target fluxes from measurements of metabolite concentrations, which is rather unrealistic in the case of sparse and noisy off-line measurements. The method is evaluated with a simulation case study on the fed-batch production of a recombinant protein, and an experimental case study of Bordetella pertussis batch cultivations. The results show that the proposed method leads to more consistent models with higher statistical confidence, better calibration properties and reinforced prediction power when compared to other dynamic (N)PLS structures.

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

[2]  S. Feyo de Azevedo,et al.  Bioprocess hybrid parametric/nonparametric modelling based on the concept of mixture of experts , 2008 .

[3]  J. D. Stigter,et al.  Observer design and tuning for biomass growth and kLa using online and offline measurements , 2008 .

[4]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[5]  Hector M Budman,et al.  Application of spectrofluorometry to the prediction of PHB concentrations in a fed-batch process , 2005, Bioprocess and biosystems engineering.

[6]  W. Ramirez,et al.  Optimal production of secreted protein in fed‐batch reactors , 1988 .

[7]  Rimvydas Simutis,et al.  Bioprocess optimization and control: Application of hybrid modelling , 1994 .

[8]  Peter A Vanrolleghem,et al.  Parallel hybrid modeling methods for a full-scale cokes wastewater treatment plant. , 2005, Journal of biotechnology.

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

[10]  N. L. Ricker.  The use of biased least-squares estimators for parameters in discrete-time pulse-response models , 1988 .

[11]  Rimvydas Simutis,et al.  How to increase the performance of models for process optimization and control , 1997 .

[12]  Huazhong Wang,et al.  Application study on nonlinear dynamic FIR modeling using hybrid SVM-PLS method , 2004, Fifth World Congress on Intelligent Control and Automation (IEEE Cat. No.04EX788).

[13]  P. J. Werbos,et al.  Backpropagation: past and future , 1988, IEEE 1988 International Conference on Neural Networks.

[14]  David R. Anderson,et al.  Multimodel Inference , 2004 .

[15]  Karl Bayer,et al.  Improvement of bioprocess monitoring: development of novel concepts , 2006, Microbial cell factories.

[16]  Thomas J. McAvoy,et al.  Nonlinear FIR Modeling via a Neural Net PLS Approach , 1996 .

[17]  S. Qin,et al.  Partial least squares regression for recursive system identification , 1993, Proceedings of 32nd IEEE Conference on Decision and Control.

[18]  Jeff Gill,et al.  What are Bayesian Methods , 2008 .

[19]  Thomas J. McAvoy,et al.  Nonlinear PLS Modeling Using Neural Networks , 1992 .

[20]  Gerrit van Straten,et al.  Assessment of near infrared and “software sensor” for biomass monitoring and control , 2008 .

[21]  Luc BAUWENS,et al.  Bayesian Methods , 2011 .

[22]  Mark A. Kramer,et al.  Modeling chemical processes using prior knowledge and neural networks , 1994 .

[23]  R. Simutis,et al.  THE USE OF HYBRID MODELLING FOR THE OPTIMIZATION OF THE PENICILLIN FERMENTATION PROCESS , 1996 .

[24]  Sirish L. Shah,et al.  Modeling and control of multivariable processes: Dynamic PLS approach , 1997 .

[25]  M. Eslami,et al.  Introduction to System Sensitivity Theory , 1980, IEEE Transactions on Systems, Man, and Cybernetics.

[26]  S. Feyo de Azevedo,et al.  Knowledge based modular networks for process modelling and control , 2000 .

[27]  S. Wold,et al.  Nonlinear PLS modeling , 1989 .

[28]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[29]  Rui Oliveira.  Combining first principles modelling and artificial neural networks: a general framework , 2004, Comput. Chem. Eng..

[30]  A. J. Morris,et al.  Non-linear dynamic projection to latent structures modelling , 2000 .

[31]  L. Ljung,et al.  Issues in system identification , 1991, IEEE Control Systems.

[32]  Rimvydas Simutis,et al.  Hybrid modelling of yeast production processes – combination of a priori knowledge on different levels of sophistication , 1994 .

[33]  P. Eykhoff.  System Identification Parameter and State Estimation , 1974 .