SO2 Emission Characteristics and BP Neural Networks Prediction in MSW/Coal Co-Fired Fluidized Beds

The SO_2 emission characteristics of typical MSW components and their mixtures have been investigated in aΦ150mm fluidized bed.Some influencing factors of SO_2 emission in MSW fluidized bed incinerator were foundout in this study.The SO2 emission is increasing with the growth of the bed temperature,and it is rising with theincreasing oxygen concentration at furnace exit.When the weight percentage of auxiliary coal is being raised,theconversion rate of S to SO_2 is largely going up.The SO_2 emission decreases if the desulfurizing agent (CaCO_3) isadded during the incineration process,but the desulfurizing efficiency is weakened with the enhancement of thebed temperature.The fuel moisture content has a slight effect on the SO_2 emission. Based on these experimentalresults, a 12×6×1 three-layer 13P neural networks prediction model of SOR emission in MSW/coal co-firedfluidized bed incinerator was built.The prediction results of this model give good agreement with theexperimental results,which indicates that the model has relatively high accuracy and good generalization ability.It was found that BP neural network is an effectual method used to predict the SO_2 emission of MSW/coalco-fired fluidized bed incinerator.

The SO2 emission characteristics of typical Msw components and their mixtures have been investigated in a φ150mm fluidized bed. Some influencing factors of SO2 emission in MSW fluidized bed incinerator were found out in this study. The SO2 emission is increasing with the growth of the bed temperature, and it is rising with the increasing oxygen concentration at furnace exit. When the weight percentage of auxiliary coal is being raised, the conversion rate of S to SO2 is largely going up. The SO2 emission decreases if the desulfurizing agent （CaCO3） is added during the incineration process, but the desulfurizing efficiency is weakened with the enhancement of the bed temperature. The fuel moisture content has a slight effect on the SO2 emission. Based on these experimental results, a 12 × 6 × 1 three-layer BP neural networks prediction model of SO2 emission in MSW/coal co-fired fluidized bed incinerator was built. The prediction results of this model give good agreement with the experimental results, which indicates that the model has relatively high accuracy and good generalization ability. It was found that BP neural network is an effectual method used to predict the SO2 emission of MSW/coal co-fired fluidized bed incinerator.