Prediction of CO/NOx emissions and the smoldering characteristic of sewage sludge based on back propagation neural network

Abstract

Smoldering can achieve effective disposal of sewage sludge (SS) with high moisture content at low energy input, providing social and economic benefits. However, smoldering is accompanied by the emission of high concentrations of CO/NOx, and thus, it requires sufficient attention. This study comprehensively investigates the effects of SS characteristics and experimental parameters on CO/NOx emissions and smoldering characteristics. Results showed that when the moisture content of SS increases from 35% to 50%, CO concentration increases while NOx formation is simultaneously inhibited. After airflow rate exceeds 5 cm/s, the concentrations of CO and NOx begin to decrease. When SS concentration is increased to 20%, the emission concentration of gas pollutants is directly increased. However, high temperatures inhibit the formation of NOx. When the particle size range is 180–270 μm, the formation of CO/NOx is promoted. Finally, a back propagation (BP) neural network model is constructed with SS characteristics and experimental parameters as input conditions, and CO/NOx emission concentration, smoldering velocity, and smoldering temperature as output parameters. The BP neural network model can effectively predict the emission concentration of CO/NOx and smoldering characteristics, providing support for intelligent control scenarios related to SS smoldering, it will help to further explore the great potential of smoldering treatment.