Data Reconciliation Using Neural Networks for the Determination of KLa

  • Nilesh Patel
  • Jules Thibault
Chapter
Part of the Studies in Computational Intelligence book series (SCI, volume 218)

Abstract

The oxygen mass transfer coefficient (KLa) is of paramount importance in conducting aerobic fermentation. KLa also serves to compare the efficiency of bioreactors and their mixing devices as well as being an important scale-up factor. In submerged fermentations, four methods are available to estimate the overall oxygen mass transfer coefficient (KLa): the dynamic method, the stationary method based on a previous determination of the oxygen uptake rate (QO2X), the gaseous oxygen balance and the carbon dioxide balance. Each method provides a distinct estimation of the value of KLa. Data reconciliation can be used to obtain the most probable value of KLa by minimizing an objective function that includes measurement terms and oxygen conservation models, each being weighted according to their level of confidence. Another alternative, for a more rapid determination of KLa, is using a neural network which has been previously trained to predict KLa from the series of oxygen conservation models. Results obtained with this new approach show that KLa can be predicted rapidly and gives values that are equivalent to those obtained with the conventional data reconciliation algorithm.

Keywords

Neural Network Dissolve Oxygen Feedforward Neural Network Respiratory Quotient Oxygen Uptake Rate 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Jarai, M.: Factors Affecting the Scale-Up of Aerated Fermentation Processes. Int. Chem. Eng. 19, 701–708 (1979)Google Scholar
  2. 2.
    Moo-Young, M., Blanch, H.W.: Design of Biochemical Reactors – Mass Transfer Criteria for Simple and Complex Systems. Adv. Biochem. Eng./Biotechnol. 19, 1–69 (1981)Google Scholar
  3. 3.
    Yagi, H., Yoshida, F.: Oxygen Absorption in Fermenters: Effects of Surfactants, Antifoaming Agents, and Sterilized Cells. J. Ferment. Technol. 52, 905–916 (1974)Google Scholar
  4. 4.
    Gauthier, L., Thibault, J., LeDuy, A.: Measuring K La with Randomly Pulsed Dynamic Method. Biotechnol. Bioeng. 37, 889–893 (1991)CrossRefGoogle Scholar
  5. 5.
    Taguchi, H., Humphery, A.E.: Dynamic Measurement of the Volumetric Oxygen Transfer Coefficient in Fermentation Systems. J. Ferment. Technol. 14, 881–889 (1966)Google Scholar
  6. 6.
    Siegel, S.D., Gaden Jr., E.L.: Automatic Control of Dissolved Oxygen Levels in Fermentations. Biotechnol. Bioeng. 4, 345–356 (1962)CrossRefGoogle Scholar
  7. 7.
    Shuler, M.L., Kargi, F.: Bioprocess Engineering – Basic Principles. Prentice Hall PTR, New Jersey (1992)Google Scholar
  8. 8.
    Pouliot, K., Thibault, J., Garnier, A., Acuña Leiva, G.: K La Evaluation During the Course of Fermentation Using Data Reconciliation Techniques. Bioprocess Biosystems. Engineering. 23, 565–573 (2000)Google Scholar
  9. 9.
    Patel, N., Thibault, J.: Evaluation of Oxygen Mass Transfer in Aspergillus Niger Fermentation Using Data Reconciliation. Biotechnol. Prog. 20, 239–247 (2004)CrossRefGoogle Scholar
  10. 10.
    Brown, D.E.: Bioprocess Measurements and Control. Chemistry & Industry, 678–681 (September 16, 1991)Google Scholar
  11. 11.
    Hodouin, D., Bazin, C., Makni, S.: On-line Reconciliation of Mineral Processing Data. In: Proc. of the AIME/SME Symposium – Emerging Computer Techniques for the Mineral Industry, Reno, Nevada, pp. 101–110 (1993)Google Scholar
  12. 12.
    Cruz, A.J.G., Silva, A.S., Araujo, M.L.G.C., Giordano, R.C., Hokka, C.O.: Estimation of the Volumetric Oxygen Transfer Coefficient (K La) From the Gas Balance and Using a Neural Network Technique. Braz. J. Chem. Eng. 16, 179–183 (1999)CrossRefGoogle Scholar
  13. 13.
    Rao, A.R., Kumar, B.: Predicting Re-aeration Rates Using Artificial Neural Networks in Surface Aerators. Int. J. Appl. Environ. Sci. 2, 155–166 (2007)Google Scholar
  14. 14.
    Djebbar, Y., Narbaitz, R.M.: Neural Network Prediction of Air Stripping K La. J. Environ. Eng. 128, 451–460 (2002)CrossRefGoogle Scholar
  15. 15.
    Yamane, T., Shimizu, S.: Fed-batch Techniques in Microbial Processes. Adv. Biochem. Eng./Biotechnol. 30, 147–194 (1984)Google Scholar
  16. 16.
    Copella, S.J., Dhurjati, P.: A Detailed Analysis of Saccharomyces cerevisiae Growth Kinetics in Batch, Fed-batch, and Hollow-fiber Bioreactors. Chem. Eng. J. 41, B27–B35 (1989)CrossRefGoogle Scholar
  17. 17.
    Wang, H.Y., Cooney, C.L., Wang, D.I.C.: Computer-Aided Baker’s Yeast Fermentations. Biotechnol. Bioeng. 19, 69–86 (1977)CrossRefGoogle Scholar
  18. 18.
    Atkinson, B., Mavituna, F.: Biochemical Engineering and Biotechnology Handbook, 2nd edn. Stockton Press, New York (1991)Google Scholar
  19. 19.
    Gagnon, H., Lounes, M., Thibault, J.: Power Consumption and Mass Transfer in Agitation Gas-Liquid Columns: A Comparative Study. Can. J. Chem. Eng. 76, 379–389 (1998)CrossRefGoogle Scholar
  20. 20.
    Heinzle, E.: Present and Potential Applications of Mass Spectrometry for Bioprocess Research and Control. J. Biotechnol. 25, 81–114 (1992)CrossRefGoogle Scholar
  21. 21.
    Crowe, C.M.: Observability and Redundancy of Process Data for Steady State Reconciliation. Chem. Eng. Sci. 44, 2909–2917 (1989)CrossRefGoogle Scholar
  22. 22.
    Hodouin, D., Everell, M.D.: A Hierarchical Procedure for Adjustment and Material Balancing of Mineral Process Data. Int. J. Miner. Process. 7, 91–116 (1980)CrossRefGoogle Scholar
  23. 23.
    Liebman, M.J., Edgar, T.F., Lasdon, L.S.: Efficient Data Reconciliation and Estimation for Dynamic Processes Using Nonlinear Programming Techniques. Comput. Chem. Eng. 16, 963–986 (1992)CrossRefGoogle Scholar
  24. 24.
    Mah, R.S.H.: Chemical Process Structures and Information Flows. Batterworths, Boston (1990)Google Scholar
  25. 25.
    Makni, S., Hodouin, D., Bazin, C.: A Recursive Node Imbalance Method Incorporating a Model of Flowrate Dynamics for On-Line Material Balance of Complex Flowsheets. Miner. Eng. 8, 753–766 (1995)CrossRefGoogle Scholar
  26. 26.
    Lippmann, R.P.: An Introduction to Computing With Neural Nets. IEEE ASSP Magazine 4(2), 4–22 (1987)CrossRefGoogle Scholar
  27. 27.
    Thibault, J., Van Breusegem, V., Chéruy, A.: On-line Prediction of Fermentation Variables Using Neural Networks. Biotechnol. Bioeng. 36, 1041–1048 (1990)CrossRefGoogle Scholar
  28. 28.
    Koprinkova-Hristova, P., Patarinska, T.: Neural Network Software Sensors Design for Lysine Fermentation Process. Applied Artificial Intelligence 22, 235–253 (2008)CrossRefGoogle Scholar
  29. 29.
    Mangesh, M.G., Jana, A.K.: A comparison of Three Sets of DSP Algorithms for Monitoring the Production of Ethanol in Fed-Batch Baker’s Yeast Fermenter. Measurement 41, 970–985 (2008)CrossRefGoogle Scholar
  30. 30.
    Lawrynczuk, M.: Modelling and nonlinear predictive control of a yeast Fermentation biochemical reactor using neural networks. Chem. Eng. J. 145, 290–307 (2008)CrossRefGoogle Scholar
  31. 31.
    Powell, M.J.D.: Some Global Convergence Properties of a Variable Metric Algorithm for Minimization without Exact Line Searches. In: ASM/SIAM Symp. on Non-linear Programming, New York (1975)Google Scholar
  32. 32.
    Alves, R.M.B., Nascimento, C.A.O.: Analysis and Detection of Outliers and Systematic Errors in Process Plant Data. Chem. Eng. Comm. 194, 382–397 (2007)CrossRefGoogle Scholar
  33. 33.
    Ruchti, G., Dunn, I.J., Bourne, J.R.: Comparison of Dynamic Oxygen Electrode Methods for the Measurement of K La. Biotechnol. Bioeng. 23, 277–290 (1981)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Nilesh Patel
    • 1
  • Jules Thibault
    • 1
  1. 1.Department of Chemical and Biological EngineeringUniversity of OttawaOttawa (Ontario)Canada

Personalised recommendations