Iterative prediction of chaotic time series using a recurrent neural network. Quarterly progress report, January 1, 1995--March 31, 1995
Chaotic systems are known for their unpredictability due to their sensitive dependence on initial conditions. When only time series measurements from such systems are available, neural network based models are preferred due to their simplicity, availability, and robustness. However, the type of neural network used should be capable of modeling the highly non-linear behavior and the multi- attractor nature of such systems. In this paper we use a special type of recurrent neural network called the ``Dynamic System Imitator (DSI)``, that has been proven to be capable of modeling very complex dynamic behaviors. The DSI is a fully recurrent neural network that is specially designed to model a wide variety of dynamic systems. The prediction method presented in this paper is based upon predicting one step ahead in the time series, and using that predicted value to iteratively predict the following steps. This method was applied to chaotic time series generated from the logistic, Henon, and the cubic equations, in addition to experimental pressure drop time series measured from a Fluidized Bed Reactor (FBR), which is known to exhibit chaotic behavior. The time behavior and state space attractor of the actual and network synthetic chaotic time series were analyzed and compared. The correlation dimension and the Kolmogorov entropy for both the original and network synthetic data were computed. They were found to resemble each other, confirming the success of the DSI based chaotic system modeling.
- Research Organization:
- Tennessee State Univ., Nashville, TN (United States). School of Engineering and Technology
- Sponsoring Organization:
- USDOE, Washington, DC (United States)
- DOE Contract Number:
- FG22-94MT94015
- OSTI ID:
- 283610
- Report Number(s):
- DOE/MT/94015-T4; ON: DE96050227
- Resource Relation:
- Other Information: PBD: 31 Mar 1996
- Country of Publication:
- United States
- Language:
- English
Similar Records
Neural network-based monitoring and control of fluidized bed. Quarterly progress report, October 1, 1995--December 31, 1995
Chaotic behavior control in fluidized bed systems using artificial neural network. Quarterly progress report, October 1, 1996--December 31, 1996