The purpose of this tutorial is to simulate a realistic industrial pulverized-coal furnace and compare the results with the measured data. Prerequisites This tutorial assumes that you are familiar with the FLUENT interface and have a good understanding of the basic setup and solution procedures. Some steps will not be shown explicitly. This tutorial uses the mixture fraction/PDF model with the k-epsilon turbulence model and P-1 radiation model. If you have not used these models before, it would be helpful to refer to the FLUENT 6.2 Tutorial Guide.
2022-01-06 11:21:49 440KB Fluent pulverized-coal
1
在高炉炼铁过程中,对铁水中硅含量的预测是最重要但也是最困难的一项。提出了一种基于经验模态分解(EMD)和动态神经网络(DNN)的组合算法,用于预测高炉中铁水的硅含量。为了消除原始历史数据的不同频率分量的相互干扰,EMD算法将原始历史数据分解为一系列不同的频率和固定本征函数(IMF)和一个残差。然后将每个IMF和残差近似于其非线性自回归模型(NARM)并通过DNN进行预测,最后,通过将每个IMF和残差的预测相加,可以得出硅含量的预测。最后,通过对中国某钢铁厂采集的一些硅含量的样本数据进行实验以验证我们的算法,结果表明,我们提出的组合算法比没有EMD的单一算法具有更好的性能,这表明该算法的有效性。提出的算法。
2021-10-15 21:44:12 518KB blast furnace; silicon content
1