Abstract
A recognition method modified from the classical Wiener-model is introduced, which recognizes the dynamic modes of an industrial process automatically on-line on the basis of the measurement information available. The dynamical linear part is based on Laguerre systems for all inputs. The values of the Laguerre system outputs contain information about the dynamic behaviour of the input signals in the near past. The static nonlinear mapping is realized with a MLP and a Kohonen's SOM, which map the “behaviour” to a unique binary code for each functional state i.e. dynamic mode. It is applied to the B. subtilis batch fermentation producing alpha-amylase to recognize the five functional states of the process.
Preview
Unable to display preview. Download preview PDF.
References
M. Schetzen: The Volterra and Wiener Theories of Nonlinear Systems, John Wiley & Sons, 1980. 531 p.
N. Wiener. Nonlinear problems in random theory. The Technology Press, MIT and John Wiley & Sons Inc. New York, 1958.
A. Back & A.C. Tsoi: Identification of nonlinear processes using Laguerre functions. Proceedings of EANN'95, Otaniemi, 21–23 August 1995, Finland.
G. Schram, M.G.H. Verhaegen & A.J. Krijgsman: System Identification with orthogonal basis functions and neural networks. Preprints of the 13th IFAC World Congress, San Fransisco, USA, 30th June–5th July 1996, Volume I pages 221–226
A. Visala & A. Halme: Qaulity Assurance in Bioprocesses by Model Based Fault Diagnosis and State Estimation. Preprints of the 13th IFAC World Congress, San Fransisco, USA, 30th June–5th July 1996, Volume N pages 425–430.
A. Halme: Generalized Polynomial Operators for Nonlinear Systems Analysis. Acta Polytechnica Scandinavica Ma 24, Helsinki, 1972.
T. Kohonen: Self-Organization and Associative Memory, Springer Verlag, 1984.
B. Wahlberg & P. M. Mákilä: On approximation of stable linear dynamical systems using Laguerre and Kautz functions, Automatica, Vol 32, No 5, 1995, pp 693–708.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Visala, A., Pitkänen, H., Halme, A. (1997). Wiener type SOM-and MLP-Classifiers for recognition of dynamic modes. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020295
Download citation
DOI: https://doi.org/10.1007/BFb0020295
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63631-1
Online ISBN: 978-3-540-69620-9
eBook Packages: Springer Book Archive