Artificial intelligence and the supervision of bioprocesses (real-time knowledge-based systems and neural networks).

The ability to supervise and control a highly non-linear and time variant bioprocess is of considerable importance to the biotechnological industries which are continually striving to obtain higher yields and improved uniformity of production. Two AI methodologies aimed at contributing to the overall intelligent monitoring and control of bioprocess operations are discussed. The development and application of a real-time knowledge-based system to provide supervisory control of fed-batch bioprocesses is reviewed. The system performs sensor validation, fault detection and diagnosis and incorporates relevant expertise and experience drawn from both bioprocess engineering and control engineering domains. A complementary approach, that of artificial neural networks is also addressed. The development of neural network modelling tools for use in bioprocess state estimation and inferential control are reviewed. An attractive characteristic of neural networks is that with the appropriate topology any non-linear functional relationship can be modelled, hence significantly reducing model-process mismatch. Results from industrial applications are presented.

[1]  M. N. Karim,et al.  Reconciliation of Measurement Data in Fermentation Using On-line Expert System , 1989 .

[2]  B. Anderson,et al.  Optimal Filtering , 1979, IEEE Transactions on Systems, Man, and Cybernetics.

[3]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[4]  A. Morris,et al.  Multilayer feedforward neural networks : a canonical form approximation of nonlinearity , 1992 .

[5]  A J Morris,et al.  Fermentation monitoring and control: a perspective. , 1989, Biotechnology & genetic engineering reviews.

[6]  J Thibault,et al.  On‐line prediction of fermentation variables using neural networks , 1990, Biotechnology and bioengineering.

[7]  M.J. Willis,et al.  A Comparison of Adaptive Estimation with Neural based Techniques for Bioprocess Application , 1990, 1990 American Control Conference.

[8]  Pietro Laface,et al.  A Rule-Based System to Schedule Production , 1986, Computer.

[9]  Aarne Halme,et al.  Modelling and control of biotechnical processes : proceedings of the First IFAC Workshop, Helsinki, Finland, August 17-19, 1982 , 1983 .

[10]  A. Johnson,et al.  Modelling and control of biotechnological processes : proceedings of the 1st IFAC Symposium, Noordwijkerhout, the Netherlands, 11-13 December 1985 , 1986 .

[11]  Denis Dochain,et al.  Experimental Validation of a Methodology for On Line State Estimation in Bioreactors , 1989 .

[12]  R. L. Moore,et al.  Expert Systems Methodology for Real-time Process Control , 1987 .

[13]  W Y Svrcek,et al.  The extended Kalman filter applied to a continuous culture model , 1974, Biotechnology and bioengineering.

[14]  A. J. Morris,et al.  Parameter Adaptive Control of the Fed-Batch Penicillin Fermentation , 1985 .

[15]  A. J. Morris,et al.  Adaptive inferential control , 1987 .

[16]  Gregory Stephanopoulos,et al.  STATE ESTIMATION FOR COMPUTER CONTROL OF BIOCHEMICAL REACTORS , 1981 .

[17]  A. J. Morris,et al.  Artificial neural networks in process engineering , 1991 .

[18]  M. Hofmeister,et al.  Knowledge-based tools for batch processing systems , 1988 .

[19]  Suteaki Shioya,et al.  Measurement of State Variables and Controlling Biochemical Reaction Processes , 1983 .

[20]  G Stephanopoulos,et al.  Studies on on‐line bioreactor identification. I. Theory , 1984, Biotechnology and bioengineering.

[21]  D. S. Flynn.  Instrumentation for Fermentation Processes , 1983 .

[22]  Mike J. Chantler.  Real-time aspects of expert systems in process control , 1988 .

[23]  Gary Montague,et al.  Soft-sensors for process estimation and inferential control , 1991 .

[24]  Stephen W. Carleysmith.  Data Handling for Fermentation Development - An Industrial Approach , 1989 .

[25]  A. J. Morris,et al.  Non-Linear Estimation and Control of Mycelial Fermentations , 1989 .

[26]  Marie-Noëlle Pons,et al.  Extended Kalman Filtering Technique for the On-line Control of Candida Utilis Production , 1985 .

[27]  G. Bastin,et al.  Non Linear Adaptive Control Algorithms for Fermentation Processes , 1988, 1988 American Control Conference.

[28]  E. F. Codd,et al.  A relational model of data for large shared data banks , 1970, CACM.

[29]  Qi Chen,et al.  Application of Expert System to the Operation and Control of Industrial Antibiotic Fermentation Process , 1989 .

[30]  M. Aynsley,et al.  A Real-Time Knowledge-Based System for Fermentation Control , 1989, 1989 American Control Conference.

[31]  Lowell B. Hawkinson,et al.  A Real-Time Expert System for Process Control , 1986 .

[32]  Man Hee Ng,et al.  Estimation of biomass and secondary product in batch fermentation , 1984 .

[33]  George Stephanopoulos,et al.  Artificial intelligence in the development and design of biochemical processes , 1986 .

[34]  Iftekhar A. Karimi,et al.  Scheduling in batch processes , 1987 .

[35]  Gregory Stephanopoulos,et al.  Toward a Systematic Method for the Generalization of Fermentation Data , 1989 .

[36]  M. Sadler,et al.  Myco‐protein —a new food , 1990 .

[37]  R. Swiniarski,et al.  PROGRESS TOWARDS ESTIMATION OF BIOMASS IN A BATCH FERMENTATION PROCESS , 1983 .