Fuzzy Days 1997: Computational Intelligence Theory and Applications pp 478-483 | Cite as
Identification of Waste Water Treatment Plant using Neural Networks
Conference paper
First Online:
Abstract
Identification of non-linear processes has always been a problem, as long as the mathematical model structure hardly can be known in advance. In the present paper, conventional Recursive Least Squares estimation is compared with Neural Network identification. Being more flexible and undependable on the model structure, this approach can approximate large variety of relationships. Both strategies are compared identifying a Waste Water Treatment Plant, which posses very strong non-linear properties.
Keywords
Biochemical Oxygen Demand Aeration Tank Neuron Layer Waste Water Treatment Plant Network Error
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.
References
- 1.Grag D. P., Boziuk III J. S., (1972) Parameter estimation of non-linear dynamical systems, Int. J. Control, vol. 15, No. 6, 1121–1127 Google Scholar
- 2.McCabe S., Davies P., Siedel D., (1991) On the use of nonlinear autoregressive moving average models for simulation and system identification, ACC, v.1, BostonGoogle Scholar
- 3.Sundstorm W. D., Klei H. E., (1979) Wastewater treatment, Prentice-Hall, Inc.Google Scholar
- 4.Horan J. N., (1990) Biological wastewater treatment systems. Theory and Operation, John Wiley & SonsGoogle Scholar
- 5.Demuth H., Beale M., The Math Works, (1992), Neural Network Toolbox User's Guide, The Math Works.Google Scholar
- 6.Klimasauskas C., Guiver J., Pelton Garrett, (1989), Neural Computing, NeuralWare, Inc.Google Scholar
- 7.Warwick K., (1992), Neural networks for systems and control, Peter Peregrinus Ltd.Google Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 1997