BENEFIT ANALYSIS OF COMBUSTIONOPTIMIZATION WITH A NEURALNETWORK FOR VATTENFALLS6×500 MW JAENSCHWALDE PLANT

摘要

Vattenfall operates 6 units at Jaenschwalde, each unit running one turbine of 500 Mwel fedrnby 2 boilers. The units burn lignite coal. The boilers were modernized in the mid 90ies inrnorder to meet the then actual requirements on a low emission plant. Today besides therndominant task of low generation costs additional expectations exist regarding environmentalrnfriendliness.rnThe combustion efficiency is of significant effect for the compliance with these requirements.rnImprovements in the combustion process enable lower lignite consumption and thus reducedrnCO2 emissions and fuel cost.rnIn order to assess the potential of improvement of neural networks on the combustionrnefficiency, a test was carried out on one of the 815 t/h steam generators in the Jaenschwaldernpower plant over several weeks by installing a NMPC (non-linear model based predictiverncontrol). The boiler is equipped with new sensor equipment developed at the TechnicalrnUniversity Zittau showing the furnace temperature distribution across the boiler located rightrnunderneath the over fire air nozzles. The relationship of regular process variables to thisrntemperature distribution was examined.rnThe analysis aimed for:rn? centering and smoothing of the fire positionrn? emissions reductionrn? lowering excess airrn? reduction of reheat spray flowrnThis paper shows the method of plant testing within the plant constraints and the benefit-analysisrnresults. Further optimization benefits are shown in other references.rnFinally the presentation shows the regular procedure of a NMPC installation for a combustionrnoptimization project.