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

Neural networks for control of NO{sub x} emissions in fossil plants

Conference ·
OSTI ID:469066
We discuss the use of two classes of artificial neural networks, multilayer feedforward networks and fully-recurrent networks, in the development of a closed-loop controller for discrete-time dynamical systems. We apply the neural system to the control of oxides of nitrogen (NO{sub x}) emissions for a simplified representation of a furnace of a coal-fired fossil plant. Plant data from one of Commonwealth Edison`s fossil power plants were used to build a recurrent neural model of NO{sub x} formation which is then used in the training of the feedforward neural controller. Preliminary simulation results demonstrate the feasibility of the approach and additional tests with increasingly realistic models should be pursued.
Research Organization:
Argonne National Lab., IL (United States)
Sponsoring Organization:
USDOE Office of Energy Research, Washington, DC (United States)
DOE Contract Number:
W-31109-ENG-38
OSTI ID:
469066
Report Number(s):
ANL/RA/CP--91404; CONF-970430--8; ON: DE97004688
Country of Publication:
United States
Language:
English

Similar Records

Recurrent neural networks for NO{sub x} prediction in fossil plants
Conference · Sun Mar 31 23:00:00 EST 1996 · OSTI ID:219304

Intelligent emissions controller for substance injection in the post-primary combustion zone of fossil-fired boilers
Patent · Tue Dec 31 23:00:00 EST 2002 · OSTI ID:874994

Nonlinear identification of process dynamics using neural networks
Journal Article · Tue Dec 31 23:00:00 EST 1991 · Nuclear Technology; (United States) · OSTI ID:5776510