Automatization of a penicillin production process with soft sensors and an adaptive controller based on neuro fuzzy systems

Abstract This paper addresses the automatization of a penicillin production process with the development of soft sensors as well as Internal Model Controllers (IMC) for a penicillin fermentation plant using modules based on FasArt and FasBack neuro-fuzzy systems. While soft sensors are intended to aid the human supervision of the process currently being conducted at pilot plants, the proposed controller will make the automatization feasible and eliminate the need for human operator. FasArt and FasBack feature fast stable learning and good MIMO identification, which makes them suitable for the development of adaptive controllers and soft sensors. In this paper, these modules are evaluated by training the neuro-fuzzy systems first on simulated data and then applying the resulting IMC controllers to a simulated plant. Moreover, training the systems on data coming from a real pilot plant, and evaluating the controller performance on the same real plant. Results show that the trend of reference is captured, thus allowing high penicillin production. Moreover, soft sensors derived for biomass, viscosity and penicillin are very accurate. In addition, on-line adaptive capabilities were implemented and tested with FasBack, since this system presents learning guided by error minimization as new data samples arrive. With these features, adaptive IMC controllers can be implemented and are helpful when dynamics have been poorly learned or the plant parameters vary with time, since the performance of static models and controllers can be improved through adaptation.

[1]  M. Morari,et al.  Internal Model Control: extension to nonlinear system , 1986 .

[2]  Li-Xin Wang,et al.  Adaptive fuzzy systems and control , 1994 .

[3]  Y.A. Dimitriadis,et al.  Control of the penicillin production using fuzzy neural networks , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

[4]  Henry J. Fastert,et al.  Fermentation Exhaust Gas Analysis Using Mass Spectrometry , 1985, Bio/Technology.

[5]  S Shioya,et al.  Knowledge-based design and operation of bioprocess systems. , 1999, Journal of bioscience and bioengineering.

[6]  Rimvydas Simutis,et al.  A fuzzy-supported Extended Kalman Filter: a new approach to state estimation and prediction exemplified by alcohol formation in beer brewing , 1992 .

[7]  D I Wang,et al.  Computer control of the penicillin fermentation using the filtration probe in conjunction with a structured process model , 1983, Biotechnology and bioengineering.

[8]  Stanley J. Farlow,et al.  Self-Organizing Methods in Modeling: Gmdh Type Algorithms , 1984 .

[9]  Stephen Grossberg,et al.  Adaptive pattern classification and universal recoding: II. Feedback, expectation, olfaction, illusions , 1976, Biological Cybernetics.

[10]  Michimasa Kishimoto,et al.  Application of fuzzy control to industrial bioprocesses in Japan , 2002, Fuzzy Sets Syst..

[11]  Rimvydas Simutis,et al.  Direct comparison of four different biomass estimation techniques against conventional dry weight measurements , 1998 .

[12]  William S. Levine,et al.  The Control Handbook , 2005 .

[13]  Kun Soo Chang,et al.  Hybrid neural network modeling of a full-scale industrial wastewater treatment process. , 2002, Biotechnology and bioengineering.

[14]  S. J. Parulekar,et al.  A morphologically structured model for penicillin production , 2002, Biotechnology and bioengineering.

[15]  Carlos E. Garcia,et al.  Internal model control. 2. Design procedure for multivariable systems , 1985 .

[16]  A. Johnson,et al.  The control of fed-batch fermentation processes - A survey , 1987, Autom..

[17]  C. A. Kent,et al.  Viability testing and characterization of germination of fungal spores by automatic image analysis , 1993, Biotechnology and bioengineering.

[18]  J. L. Coronado,et al.  Control of the Penicillin Production with Adaptive IMC Using Fuzzy Neural Networks , 1999 .

[19]  William E. Schmitendorf,et al.  Methods for Obtaining Robust Tracking Control Laws , 1986, 1986 American Control Conference.

[20]  A. Isidori.  Nonlinear Control Systems , 1985 .

[21]  Gary A. Montague,et al.  Application of radial basis function and feedforward artificial neural networks to the Escherichia coli fermentation process , 1998, Neurocomputing.

[22]  J. Martín,et al.  Carbon catabolite repression of penicillin biosynthesis by Penicillium chrysogenum. , 1984, The Journal of antibiotics.

[23]  M.J. Willis,et al.  Artificial Neural Networks: -A Panacea to Modelling Problems? , 1991, 1991 American Control Conference.

[24]  Jovan D. Bošković,et al.  Comparison of linear, nonlinear and neural-network-based adaptive controllers for a class of fed-batch fermentation processes , 1995, Autom..

[25]  A. J. Morris,et al.  Artificial Neural Networks: -A Panacea to Modelling Problems? , 1991 .

[26]  Carlos E. Garcia,et al.  Internal model control. A unifying review and some new results , 1982 .

[27]  G.A. Montague,et al.  Considerations in control scheme development for fermentation process control , 1988, IEEE Control Systems Magazine.

[28]  Ron Meir,et al.  Best estimated inverse versus inverse of the best estimator , 2001, Neural Networks.

[29]  S Linko,et al.  Applying neural networks as software sensors for enzyme engineering. , 1999, Trends in biotechnology.

[30]  J. L. Coronado,et al.  FLAS: a fuzzy linear adaptive system for identification of non-linear noisy functions , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

[31]  A. J. Morris,et al.  Towards improved penicillin fermentation via artificial neural networks , 1992 .

[32]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[33]  S. Grossberg.  Studies of mind and brain : neural principles of learning, perception, development, cognition, and motor control , 1982 .

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

[35]  S Vlassides,et al.  Using historical data for bioprocess optimization: modeling wine characteristics using artificial neural networks and archived process information. , 2001, Biotechnology and bioengineering.

[36]  T J McAvoy,et al.  A comparison of neural networks and partial least squares for deconvoluting fluorescence spectra , 1992, Biotechnology and bioengineering.

[37]  Duen-Gang Mou,et al.  Toward an optimum penicillin fermentation by monitoring and controlling growth through computer-aided mass balancing. w , 1979 .

[38]  J A Spriet,et al.  A Computer‐aided noninterfering on‐line technique for monitoring oxygen‐transfer characteristics during fermentation processes , 1982, Biotechnology and bioengineering.

[39]  M. Reuss,et al.  Evaluation of feeding strategies in carbon‐regulated secondary metabolite production through mathematical modeling , 1981 .

[40]  J. López Coronado,et al.  Adaptive IMC using fuzzy neural networks for the control on non linear systems , 2002 .

[41]  R. Agrawal,et al.  Strain improvement of Aspergillus sp. and Penicillium sp. by induced mutation for biotransformation of alpha-pinene to verbenol. , 1999, Biotechnology and bioengineering.

[42]  Wen-Teng Wu,et al.  Semi-realtime optimization and control of a fed-batch fermentation system , 2000 .

[43]  S. Grossberg,et al.  Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectors , 1976, Biological Cybernetics.

[44]  Yannis A. Dimitriadis,et al.  Learning from noisy information in FasArt and FasBack neuro-fuzzy systems , 2001, Neural Networks.

[45]  Stephen Grossberg,et al.  Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps , 1992, IEEE Trans. Neural Networks.

[46]  Jose A. Romagnoli,et al.  On-line optimal trajectory control for a fermentation process using multi-linear models , 2001 .

[47]  J J Heijnen,et al.  Application of balancing methods in modeling the penicillin fermentation , 1979, Biotechnology and bioengineering.

[48]  Eduardo F. Camacho,et al.  Model predictive control in the process industry , 1995 .

[49]  J. M. Cano Izquierdo,et al.  Fuzzy adaptive system ART-based : Theory and application to identification of biochemical systems , 1996 .

[50]  Ah-Hwee Tan,et al.  Rule Extraction: From Neural Architecture to Symbolic Representation , 1995 .

[51]  Evanghelos Zafiriou,et al.  Robust process control , 1987 .

[52]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[53]  J. Richalet,et al.  Industrial applications of model based predictive control , 1993, Autom..

[54]  Jarka Glassey,et al.  An assessment of seed quality and its influence on productivity estimation in an industrial antibiotic fermentation. , 2002, Biotechnology and bioengineering.

[55]  Richard D. Braatz,et al.  On the "Identification and control of dynamical systems using neural networks" , 1997, IEEE Trans. Neural Networks.

[56]  B Lennox,et al.  Process monitoring of an industrial fed-batch fermentation. , 2001, Biotechnology and bioengineering.

[57]  K Schügerl,et al.  Segregated mathematical model for the fed-batch cultivation of a high-producing strain of Penicillium chrysogenum. , 1994, Journal of biotechnology.

[58]  A. J. Morris,et al.  Modelling and adaptive control of fed-batch penicillin fermentation , 1986 .

[59]  S. Grossberg.  How does a brain build a cognitive code , 1980 .

[60]  Daniel Sbarbaro,et al.  Neural Networks for Nonlinear Internal Model Control , 1991 .

[61]  Jens Nielsen,et al.  Physiological Engineering Aspects Of Penicillium Chrysogenum , 1997 .