In the present work, the gas flow pressure drop and gas–solid heat transfer characteristics in sinter bed layer of vertical tank were studied experimentally on the basis of the homemade experimental setup. The gas fl...In the present work, the gas flow pressure drop and gas–solid heat transfer characteristics in sinter bed layer of vertical tank were studied experimentally on the basis of the homemade experimental setup. The gas flow pressure drop through the sinter bed layer was measured with different gas velocity and particle diameters, as well as the sinter and air temperatures. The influences of gas superficial velocity and particle diameter on the gas flow pressure drop and gas solid heat transfer in sinter bed layer were analyzed in detail. The revised Ergun's correlation and gas solid heat transfer correlation were obtained according to the regression analysis of experimental data. It is found that, the pressure drop of unit bed layer height gradually increases as a quadratic relationship with increasing the gas superficial velocity, and decreases as an exponential relationship with the increase of sinter particle diameter. For a given sinter temperature, the heat transfer coefficient in sinter bed layer increases with increasing the gas superficial velocity, and increases with decreasing the sinter particle diameter. In addition, the heat transfer coefficient also gradually increases with increasing the sinter temperature at the same gas superficial velocity and sinter particle diameter. The mean deviations between the experimental data obtained from this work and the values calculated by the revised Ergun's correlation and the experimental heat transfer correlation are 7.22% and 4.22% respectively, showing good prediction.展开更多
氧化亚铁(FeO)含量是衡量烧结矿强度和还原性的重要指标,烧结过程FeO含量的实时准确预测对于提升烧结质量、优化烧结工艺具有重要意义.然而烧结过程热状态参数缺失、过程参数波动频繁给FeO含量的高精度预测带来巨大的挑战,为此,提出一...氧化亚铁(FeO)含量是衡量烧结矿强度和还原性的重要指标,烧结过程FeO含量的实时准确预测对于提升烧结质量、优化烧结工艺具有重要意义.然而烧结过程热状态参数缺失、过程参数波动频繁给FeO含量的高精度预测带来巨大的挑战,为此,提出一种基于知识与变权重回声状态网络融合(Fusion of data-knowledge and adaptive weight echo state network, DK-AWESN)的烧结过程FeO含量预测方法.首先,针对烧结过程热状态参数缺失的问题,建立烧结料层最高温度分布模型,实现基于料层温度分布特征的FeO含量等级划分;其次,针对烧结过程参数波动频繁的问题,提出基于核函数高维映射的多尺度数据配准方法,有效抑制离群点的影响,提升建模数据的质量;最后,针对烧结过程数据驱动模型缺乏机理认知致使模型预测精度不高的问题,将过程数据中提取得到的FeO含量等级知识与AW-ESN (Adaptive weight echo state network)结合,建立DK-AWESN模型,有效提升复杂工况下FeO含量的预测精度.现场工业数据试验表明,所提方法能实时准确地预测烧结过程FeO含量,为烧结过程的智能化调控提供实时有效的FeO含量反馈信息.展开更多
基金Project(51274065)supported by the National Natural Science Foundation of ChinaProject(2015020074)supported by the Science and Technology Planning Project of Liaoning Province,China
文摘In the present work, the gas flow pressure drop and gas–solid heat transfer characteristics in sinter bed layer of vertical tank were studied experimentally on the basis of the homemade experimental setup. The gas flow pressure drop through the sinter bed layer was measured with different gas velocity and particle diameters, as well as the sinter and air temperatures. The influences of gas superficial velocity and particle diameter on the gas flow pressure drop and gas solid heat transfer in sinter bed layer were analyzed in detail. The revised Ergun's correlation and gas solid heat transfer correlation were obtained according to the regression analysis of experimental data. It is found that, the pressure drop of unit bed layer height gradually increases as a quadratic relationship with increasing the gas superficial velocity, and decreases as an exponential relationship with the increase of sinter particle diameter. For a given sinter temperature, the heat transfer coefficient in sinter bed layer increases with increasing the gas superficial velocity, and increases with decreasing the sinter particle diameter. In addition, the heat transfer coefficient also gradually increases with increasing the sinter temperature at the same gas superficial velocity and sinter particle diameter. The mean deviations between the experimental data obtained from this work and the values calculated by the revised Ergun's correlation and the experimental heat transfer correlation are 7.22% and 4.22% respectively, showing good prediction.
文摘氧化亚铁(FeO)含量是衡量烧结矿强度和还原性的重要指标,烧结过程FeO含量的实时准确预测对于提升烧结质量、优化烧结工艺具有重要意义.然而烧结过程热状态参数缺失、过程参数波动频繁给FeO含量的高精度预测带来巨大的挑战,为此,提出一种基于知识与变权重回声状态网络融合(Fusion of data-knowledge and adaptive weight echo state network, DK-AWESN)的烧结过程FeO含量预测方法.首先,针对烧结过程热状态参数缺失的问题,建立烧结料层最高温度分布模型,实现基于料层温度分布特征的FeO含量等级划分;其次,针对烧结过程参数波动频繁的问题,提出基于核函数高维映射的多尺度数据配准方法,有效抑制离群点的影响,提升建模数据的质量;最后,针对烧结过程数据驱动模型缺乏机理认知致使模型预测精度不高的问题,将过程数据中提取得到的FeO含量等级知识与AW-ESN (Adaptive weight echo state network)结合,建立DK-AWESN模型,有效提升复杂工况下FeO含量的预测精度.现场工业数据试验表明,所提方法能实时准确地预测烧结过程FeO含量,为烧结过程的智能化调控提供实时有效的FeO含量反馈信息.
