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...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.展开更多
In the present paper, two models based on artificial neural networks and genetic programming for predicting split tensile strength and percentage of water absorption of concretes containing ZrO2 nanoparticles have bee...In the present paper, two models based on artificial neural networks and genetic programming for predicting split tensile strength and percentage of water absorption of concretes containing ZrO2 nanoparticles have been developed at different ages of curing. For building these models, training and testing using experimental results for 144 specimens produced with 16 different mixture proportions were conducted. The data used in the multilayer feed forward neural networks models and input variables of genetic programming models were arranged in a format of eight input parameters that cover the cement content, nanoparticle content, aggregate type, water content, the amount of superplasticizer, the type of curing medium, age of curing and number of testing try. According to these input parameters, in the neural networks and genetic programming models, the split tensile strength and percentage of water absorption values of concretes containing ZrO2 nanoparticles were predicted. The training and testing results in the neural network and genetic programming models have shown that two models have strong potential for predicting the split tensile strength and percentage of water absorption values of concretes containing ZrO2 nanoparticles. It has been found that neural network （NN） and gene expression programming （GEP） models will be valid within the ranges of variables. In neural networks model, as the training and testing ended when minimum error norm of network gained, the best results were obtained and in genetic programming model, when 4 genes were selected to construct the model, the best results were acquired. Although neural network have predicted better results, genetic programming is able to predict reasonable values with a simpler method rather than neural network.展开更多
基金The financial support of National Natural Science Foundation of China （under project No.59836210） is acknowledged.
文摘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.
文摘In the present paper, two models based on artificial neural networks and genetic programming for predicting split tensile strength and percentage of water absorption of concretes containing ZrO2 nanoparticles have been developed at different ages of curing. For building these models, training and testing using experimental results for 144 specimens produced with 16 different mixture proportions were conducted. The data used in the multilayer feed forward neural networks models and input variables of genetic programming models were arranged in a format of eight input parameters that cover the cement content, nanoparticle content, aggregate type, water content, the amount of superplasticizer, the type of curing medium, age of curing and number of testing try. According to these input parameters, in the neural networks and genetic programming models, the split tensile strength and percentage of water absorption values of concretes containing ZrO2 nanoparticles were predicted. The training and testing results in the neural network and genetic programming models have shown that two models have strong potential for predicting the split tensile strength and percentage of water absorption values of concretes containing ZrO2 nanoparticles. It has been found that neural network （NN） and gene expression programming （GEP） models will be valid within the ranges of variables. In neural networks model, as the training and testing ended when minimum error norm of network gained, the best results were obtained and in genetic programming model, when 4 genes were selected to construct the model, the best results were acquired. Although neural network have predicted better results, genetic programming is able to predict reasonable values with a simpler method rather than neural network.
