Recurrent neural networks for NO{sub x} prediction in fossil plants

Conference · Mon Apr 01 00:00:00 EST 1996

OSTI ID:219304

Reifman, J; Vitela, J E; Feldman, E E; Wei, T Y.C.

The authors discuss the application of recurrent (dynamic) neural networks for time-dependent modeling of NO{sub x} emissions in coal-fired fossil plants. They use plant data from one of ComEd`s plants to train and test the network model. Additional tests, parametric studies, and sensitivity analyses are performed to determine if the dynamic behavior of the model matches the expected behavior of the physical system. The results are also compared with feedforward (static) neural network models trained to represent temporal information.

• Research Organization: Argonne National Lab. (ANL), Argonne, IL (United States)
• Sponsoring Organization: USDOE, Washington, DC (United States)
• DOE Contract Number: W-31109-ENG-38
• OSTI ID: 219304
• Report Number(s): ANL/RA/CP-88854; CONF-960482-4; ON: DE96008447; TRN: AHC29609%%35
• Resource Relation: Conference: Society of Computer Simulation (SCS) multiconference: high performance computing, New Orleans, LA (United States), 8-11 Apr 1996; Other Information: PBD: [1996]
• Country of Publication: United States
• Language: English

Related Subjects

01 COAL, LIGNITE, AND PEAT
20 FOSSIL-FUELED POWER PLANTS
99 MATHEMATICS
COMPUTERS
INFORMATION SCIENCE
MANAGEMENT
LAW
MISCELLANEOUS
FOSSIL-FUEL POWER PLANTS
AIR POLLUTION
NITROGEN OXIDES
FORECASTING
NEURAL NETWORKS
PERFORMANCE
COAL
COMBUSTION
TRAINING
MATHEMATICAL MODELS
TIME DEPENDENCE
PARAMETRIC ANALYSIS
FUEL-AIR RATIO