An intelligent emissions controller for fuel lean gas reburn in coal-firedpower plants

The application of artificial intelligence techniques for performance optim ization of the fuel lean gas reburn (FLGR) system is investigated. A multil ayer, feedforward artificial neural network is applied to model static nonl inear relationships between the distribution of injected natural gas into t he upper region of the furnace of a coal-fired boiler and the corresponding oxides of nitrogen (NOx) emissions exiting the furnace. Based on this mode l, optimal distributions of injected gas are determined such that the large st NOx reduction is achieved for each value of total injected gas. This opt imization is accomplished through the development of a new optimization met hod based on neural networks. This new optimal control algorithm, which can be used as an alternative generic tool for solving multidimensional nonlin ear constrained optimization problems, is described and its results are suc cessfully validated against an off-the-shelf tool for solving mathematical programming problems. Encouraging results obtained using plant data from on e of Commonwealth Edison's coal-fired electric power plants demonstrate the feasibility of the overall approach. Preliminary results show that the use of this intelligent controller will a lso enable the determination of the most east-effective operating condition s of the FLGR system by considering, along with the optimal distribution of the injected gas, the cost differential between natural gas and coal and t he open-market price of NOx emission credits. Further study, however, is ne cessary, including the construction of a more comprehensive database, neede d to develop high-fidelity process models and to add carbon monoxide (CO) e missions to the model of the gas reburn system.