GNOCIS-an on-line NOx emissions and plant performance optimizer for fossil fuel-fired power plants

摘要

The Generic NO{sub}x Control Intelligent System (GNOCIS) is an on-line enhancement to existing digital control systems (DCS) designed to reduce NO{sub}x emissions from fossil fuel-fired boilers while meeting other operational constraints on theunit (principally beat rate and other regulated emissions). Using artificial intelligence techniques, GNOCIS utilizes a model of the combustion characteristics of the boiler that includes NO{sub}x emissions and boiler efficiency. The software applies anoptimizing procedure to identify the best set points for the plant, which can be implemented automatically without operator intervention in a closed-loop mode, or at the plant's discretion, conveyed to the plant operators for implementation in anopen-loop mode. GNOCIS can be viewed as a low-cost long-term means to maintain short-term optimized plant performance.Development of GNOCIS was funded by a consortium consisting of the Electric Power Research Institute, PowerGen, Radian International, Southern Company, U.K. Department of Trade and Industry, and U.S. Department of Energy. The first commercial installation of GNOCIS was at Georgia Power's Hammond Unit 4, a 500 MW opposed wall-fired boiler. Hammond Unit 4 serves as the host site of a U.S. Department of Energy Clean Coal Technology (CCT) Program project, wherein a stepwise long-term evaluation of threetechnologies to reduce NO{sub}x emissions was conducted: (1) Advanced Overfire Air (AOFA), (2) Low NO{sub}x Burners (LNB), and (3) LNB + AOFA. A general overview of the CCT project and GNOCIS technology will be presented along with performance resultsfrom Plant Hammond. Preliminary GNOCIS data from Hammond Unit 4 show an efficiency gain of 0.5 percent, a reduction in fly ash loss-on-ignition of 1-3 percentage points, and NO{sub}x reduction of 10-15 percent at full load.