Simultaneous boiler optimization of efficiency, emission, and reliability utilizing neural network modeling
Abstract
Boiler performance optimization includes the preservation of efficiency, emission, capacity, and reliability. Competitive pressures require cost reduction and environmental compliance. It is a challenge for utility personnel to balance these requirements and to achieve specific company goals. Unfortunately, these requirements often demand tradeoffs. The Clean Air Act Amendment requires Utilities to reduce NO{sub x} emission. NO{sub x} emission reduction has often been accomplished by installation of new low NO{sub x} burners. Boiler tuning for NO{sub x} control can be used as an alternative to low NO{sub x} burner installation. A PC-based computer software program was developed to assist the tuning process. This software, System Optimization Analysis Program (SOAP), is a neural network based code which uses the self-adaptation learning process, with an adaptive filter added for data noise control. SOAP can use historical data as the knowledge base and it provides a fast optimal solution to adaptive control problems. SOAP was tested at several fossil plants. The tests were primarily for NO{sub x} reduction, but the performance parameters were optimized simultaneously.
- Authors:
- Publication Date:
- Research Org.:
- Electric Power Research Inst. (EPRI), Palo Alto, CA (United States); Baltimore Gas and Electric Co., MD (United States)
- OSTI Identifier:
- 401957
- Report Number(s):
- EPRI-TR-106753; CONF-960719-
TRN: 96:005874-0041
- Resource Type:
- Technical Report
- Resource Relation:
- Conference: Fossil plant maintenance conference, Baltimore, MD (United States), 29 Jul - 1 Aug 1996; Other Information: PBD: Jul 1996; Related Information: Is Part Of Proceedings: 1996 EPRI fossil plant maintenance conference; PB: 677 p.
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 20 FOSSIL-FUELED POWER PLANTS; FOSSIL-FUEL POWER PLANTS; BOILERS; MAINTENANCE; PERFORMANCE; NEURAL NETWORKS; USES; OPTIMIZATION; RELIABILITY; NITROGEN OXIDES; AIR POLLUTION CONTROL; COMPUTERIZED SIMULATION
Citation Formats
Chang, P S, and Poston, J. Simultaneous boiler optimization of efficiency, emission, and reliability utilizing neural network modeling. United States: N. p., 1996.
Web.
Chang, P S, & Poston, J. Simultaneous boiler optimization of efficiency, emission, and reliability utilizing neural network modeling. United States.
Chang, P S, and Poston, J. 1996.
"Simultaneous boiler optimization of efficiency, emission, and reliability utilizing neural network modeling". United States.
@article{osti_401957,
title = {Simultaneous boiler optimization of efficiency, emission, and reliability utilizing neural network modeling},
author = {Chang, P S and Poston, J},
abstractNote = {Boiler performance optimization includes the preservation of efficiency, emission, capacity, and reliability. Competitive pressures require cost reduction and environmental compliance. It is a challenge for utility personnel to balance these requirements and to achieve specific company goals. Unfortunately, these requirements often demand tradeoffs. The Clean Air Act Amendment requires Utilities to reduce NO{sub x} emission. NO{sub x} emission reduction has often been accomplished by installation of new low NO{sub x} burners. Boiler tuning for NO{sub x} control can be used as an alternative to low NO{sub x} burner installation. A PC-based computer software program was developed to assist the tuning process. This software, System Optimization Analysis Program (SOAP), is a neural network based code which uses the self-adaptation learning process, with an adaptive filter added for data noise control. SOAP can use historical data as the knowledge base and it provides a fast optimal solution to adaptive control problems. SOAP was tested at several fossil plants. The tests were primarily for NO{sub x} reduction, but the performance parameters were optimized simultaneously.},
doi = {},
url = {https://www.osti.gov/biblio/401957},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Mon Jul 01 00:00:00 EDT 1996},
month = {Mon Jul 01 00:00:00 EDT 1996}
}