Neural network-based combustion optimization reduces NO{sub}x emissions while improving performance

摘要

This paper presents the benefits of applying an on-line, real4ime neural network to several 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, over-fire air boiler modifications, SCRS, and SNCRs.The neural network-based system has been applied on 11 electric utility boilers that represent a wide range of furnace and burner types including units with tangential-, cell-, single wall-, and opposed wall-burner arrangements that have ranged incapacity 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 boileroperation 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 set-points and bias settings inclosed-loop supervisory control to reduce NOx emissions and improve heat rate simultaneously.