Advertisement

Estimation of Some Crucial Variables in Erythromycin Fermentation Process Based on ANN Left-Inversion

  • Xianzhong Dai
  • Wancheng Wang
  • Yuhan Ding
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3973)

Abstract

For the on-line estimation of some directly immeasurable crucial variables in erythromycin fermentation process, this paper presents an Artificial Neural Network (ANN) left-inversion based on the “assumed inherent sensor” and its left-inversion concepts. The ANN left-inversion is composed of two relatively independent parts ( a static ANN used to approximate the complex nonlinear function and several differentiators used to represent its dynamic behaviors, so that the ANN left-inversion is a special kind of dynamic ANN in essence. Different from common dynamic ANNs, such a separate structure makes the ANN left-inversion easier to use, hence facilitating its application. The ANN left-inversion has been used to estimate such immeasurable variables as mycelia concentration, sugar concentration and chemical potency in erythromycin fermentation process. The experimental results show its validity.

Keywords

Artificial Neural Network Back Propagation Neural Network Hopfield Neural Network Crucial Variable Penicillin Production 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Shi, D., Zhang, H., Yang, L.: Time-Delay Neural Network for the Prediction of Carbonation Tower’s Temperature. IEEE Trans. Instrumentation and Measurement 52(4), 1125–1128 (2003)CrossRefMathSciNetGoogle Scholar
  2. 2.
    Wang, W., Ren, M.: Soft-Sensing Method for Wastewater Treatment Based on BP Neural Network. In: Xi, Y., Cao, X., Guo, L. (eds.) Proceedings of the World Congress on Intelli-gent Control and Automation, Shanghai, P.R. China, vol. 3, pp. 2330–2332 (2002)Google Scholar
  3. 3.
    Su, H., Fan, L., Schlup, J.R.: Monitoring the Process of Curing of Epoxy/Graphite Fiber Composites with a Recurrent Neural Network as a Soft Sensor. Engineering Applications of Artificial Intelligence 11(2), 293–306 (1998)CrossRefGoogle Scholar
  4. 4.
    Paul, G.C., Syddall, M.T., Kent, C.A., Thomas, C.R.: A Structured Model for Penicillin Production on Mixed Substrates. Biochemical Engineering Journal 2(1), 11–21 (1998)CrossRefGoogle Scholar
  5. 5.
    Birol, G., Undey, C., Cinar, A.: A Modular Simulation Package for Fed-Batch Fermentation: Penicillin Production. Computers and Chemical Engineering 26(11), 1553–1565 (2002)CrossRefGoogle Scholar
  6. 6.
    Singh, S.N.: A Modified Algorithm for Invertibility in Nonlinear Systems. IEEE Trans. Automatic Control 26(2), 595–598 (1981)MATHCrossRefGoogle Scholar
  7. 7.
    Dai, X., He, D., Zhang, X.: MIMO System Invertibility and Decoupling Control Strategies Based on ANN th-Order Inversion. IEE Proceedings-Control Theory and Applications 148(2), 125–136 (2001)CrossRefGoogle Scholar
  8. 8.
    Benedetto, M.D.D., Glumineau, A., Moog, C.H.: The Nonlinear Interactor and Its Applica-tion to Input-Output Decoupling. IEEE Trans. Automatic Control 39(6), 1246–1250 (1994)MATHCrossRefGoogle Scholar
  9. 9.
    Dai, X., Liu, J., Feng, C., He, D.: Neural Networkth Order Inverse System Method for the Control of Nonlinear Continuous Systems. IEE Proceedings-Control Theory and Applications 145(6), 519–522 (1998)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Xianzhong Dai
    • 1
  • Wancheng Wang
    • 1
  • Yuhan Ding
    • 1
  1. 1.Department of AutomationSoutheast UniversityNanjingChina

Personalised recommendations