Modelling Chaos with Neural Networks
In this work, a comparison between alternative neural approaches to model chaotic systems is reported. In particular, two different approaches have been presented. The first, is a Locally Recurrent Neural Network that, keeping the feedforward architecture of the MLP, replaces the classical synapses with Finite Impulse Response and Infinite Impulse Response filters. The second, is a novel dynamic neural network obtained by making recurrent the neurons in the output layer. The performances of the proposed approaches have been tested on the problem of modeling the dynamics of a non-isothermal, continuously stirred tank reactor when two consecutive first order reactions lead to a chaotic behavior. Moreover, the obtained dynamic neural networks have been used to develop a Generic Model Control controller.
KeywordsNeural Network Hide Layer Finite Impulse Response Model Predictive Control Recurrent Neural Network
Unable to display preview. Download preview PDF.
- Back D., Tsoi A.C. (1991) FIR and IIR synapses, a new neural network architecture for time series modelling. Neural Computation, 3, 375–385, Massachusetts Institute of TechnologyGoogle Scholar
- Wan E.A. (1990) Temporal backpropagation for FIR neural networks, Proceedings of International Joint Conference on Neural Networks, San Diego, June 1990, 575–580Google Scholar
- Khotanzad R., Lu Afkhami-Rohani T., Abaye A., Davis M., Maratukulam D.J. (1997) ANNSTLF- A neural-network-based electric load forecasting system. IEEE Trans, on Neural Networks, 8Google Scholar
- Celli G., Marchesi M., Mocci F., Pilo F. (1997) Applications of neural networks in power distribution systems diagnosis and control. Proc. 32nd Universities Power Engineering Conference UPEC ’97, Manchester (UK), 10–12 Sept. 1997, 523–526Google Scholar
- Celli G., Pilo F., Sannais R., Tosi M. (1998) Voltage quality improvement by Custom Power devices: applications of Solid-State Breakers and Neural Controllers. Proc. of SPEEDAM 98 Conference, Sorrento (ITALY), 3–5 June 1998Google Scholar
- Baratti R., Servida A. (1999) DMC control strategy for a CSTR based on dynamic neural model. Proc. of Ichea P-4, Forth Italian Conference on Chemical Eng., Florence, Italy, May 2–5 1999, 179–182Google Scholar
- Werbos P. (1990) Backpropagation through time: what it does and how to do it. Proc. IEEE, Special Issue on Neural Networks, 2, 1550–1560Google Scholar
- Ogunnaike B.A., Ray W.H. (1994) Process Dynamics, Modeling, and Control. Oxford University Press, OxfordGoogle Scholar
- Glover F. (1989) Tabu search — part. I. ORSA Journal on Computing, 1, 190–206Google Scholar
- Glover F. (1990) Tabu search — part. II. ORSA Journal on Computing, 2, 4–32Google Scholar
- Henon M. (1982) On the Numerical Computation of Poincaré Maps. Physica 5D, 412–414Google Scholar