Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Application of neural networks for control of chaotic systems

Conference ·
OSTI ID:81603
 [1];  [2]
  1. Visual Solutions, Inc., Westford, MA (United States)
  2. Univ. of Massachusetts, Lowell, MA (United States)

This paper investigates the feasibility of alternative and more general ways to control nonlinear and chaotic systems, based on Artificial Neural Networks (ANN). A chaotic system model is considered and a neural network is trained to serve as an intelligent controller for the system. During the training phase, a conventional controller is used as the teacher. The neural controller is placed in the closed loop after the training phase. Simulation results indicate that the neural net controller performs satisfactorily, compared to conventional closed-loop controllers.

Research Organization:
USDOE Pittsburgh Energy Technology Center, PA (United States); Oregon State Univ., Corvallis, OR (United States). Dept. of Computer Science; Naval Research Lab., Washington, DC (United States); Electric Power Research Inst., Palo Alto, CA (United States); Bureau of Mines, Washington, DC (United States)
OSTI ID:
81603
Report Number(s):
CONF-9410335--; ON: DE95011702
Country of Publication:
United States
Language:
English

Similar Records

A neural-network-based identifier/controller for modern HVAC control
Conference · Sat Dec 30 23:00:00 EST 1995 · OSTI ID:211785

Application of neural networks to seismic active control
Conference · Sat Jul 01 00:00:00 EDT 1995 · OSTI ID:88660

Seismic active control by neural networks.
Journal Article · Wed Dec 31 23:00:00 EST 1997 · Int. J. Smart Eng. Syst. Des. · OSTI ID:937822