NOX EMISSION MODELING USING THE ITERATIVELY REWEIGHTED LEAST-SQUARE PROCEDURES

NOx emission dispatching is a method to reduce the amount of oxide of nitrogen produced by thermal generating units to meet given power dema nds. This requires adequate models relating NOx emissions to the activ e power generation of the unit. Least-squares estimation procedures wo rk best when measurement errors are Gaussian. For the non-Gaussian err ors and Gaussian errors, the iteratively reweighted least-squares (IRW LS) procedure with optimized weight functions and their associated wei ght constants can be used to estimate, refine and fine tune parameters of identified models. The form of the emissions model is restricted t o those with monotonically increasing derivatives due to subsequent mi nimization process requirements. We explore the application of some tr ansformations to the form of model chosen. Moreover, emission models a le developed using the IRWLS procedure. The results obtained using the iteratively reweighted least-square procedures are compared with the least squares.