Prediction of Pollution State of Heating Surface in Coal-Fired Utility Boilers

This paper presents a method to predict the cleaning state of the boiler heating surface. In this method, firstly, the historical fouling rate data is decomposed into two parts: fitting curve data and the difference between original data and the fitting curve. Then, combined with the real-time fouling rate data, the prediction model is established. Finally, the method is verified by the actual operation data of a 300 MW coal-fired power station boiler. The method does not need additional special instruments or a complex calculation system but can use the existing monitoring data to realize the dirt monitoring and soot blowing optimization of the economizer, which has a certain guiding role for the soot blowing operation of the coal-fired power plant.