US EPA

1678050 

Journal Article 

Neural network-based combustion optimization reduces NOx emissions while improving performance 

Booth, RC; Roland, WB 

1998 

667-672 

WOS:000074129000124 

The NeuSIGHT neural network based system has been applied to units with tangential-, cell-, single wall-, and opposed wall-burner arrangements that have ranged in capacity from 146 to 800 MW in an advisory mode. Several sites have employed the neural network-based system for closed-loop supervisory combustion control. Boiler combustion profiles change continuously due to coal quality, boiler loading, changes in slag/soot deposits, ambient conditions, and the condition of plant equipment. Through on-line retraining, the neural network-based system optimizes the boiler operation by accommodating equipment performance changes due to wear and maintenance activities, adjusting to fluctuations in fuel quality, and improving operating flexibility. The system dynamically adjusts combustion setpoints and bias settings in closed-loop supervisory control to reduce NOx emissions and improve heat rate simultaneously. This paper presents the benefits of applying an on-line, real-time neural network to several commercially operating bituminous coal fired utility boilers. The system helps reduce NOx emissions up to 60%, meeting compliance while it improves heat rate up to 2% overall (5% at low load) and reduces LOI as much as 30% through combustion optimization alone. The system can avoid or postpone large capital expenditures for low NOx burners, overfire air boiler modifications, SCRs, and SNCRs.