The Effect of Graphite Particle Size on Properties of Low Carbon MgO-C Composite Materials

The effects of graphite granularity on the properties of low carbon MgO-C based materials have been investigated in the work. Large crystal fused magnesia, natural flake graphite with different particle sizes and anti-oxidant were adopted as raw material for preparation of specimens. However, the results show that the physical properties, oxidation resistance and thermal shock resistance of low carbon MgO-C materials with content of 4.0wt% graphite are improved obviously through the use of special and suitable size graphite. The excellent performance achieved was considered as a result of microstructure modification of MgO-C materials. Therefore, it is suggested that both fine and micro grade natural flake graphite used for production of low carbon MgO-C bricks.

BP神经网络和SARIMA模型在手足口病发病率预测中的比较

目的 探讨BP神经网络和季节差分自回归移动平均模型(SARIMA)模型在手足口病(HFMD)发病率预测中的应用,建立HFMD发病的预警系统,为其有效防控提供参考依据。方法 收集2012-2020年南昌市东湖区HFMD的发病数据,用BP神经网络和SARIMA进行模型拟合,预测2021年1-12月HFMD的发病情况,并用MSE、MAE、MAPE来评估2种模型的预测效果。结果 2012-2021年东湖区累计报告HFMD例2 923例,年平均发病率为52.56/10万,不同年度HFMD发病率有所不同(χ2=286.066,P<0.001)。对于2021年1-12月东湖区HFMD发病率的预测,BP神经网络模型的MSE、MAE、MAPE分别为2.87、1.37、0.82%,SARIMA模型MSE、MAE、MAPE分别为11.47、2.85、6.24%。结论 BP神经网络和SARIMA模型均适用于预测HFMD发病率,且BP神经网络模型的预测效果优于SARIMA模型。