论文

利用DSC、XRD,结合热焓分析对硅钢级氧化镁和二氧化硅的固相反应行为进行了研究。比较了不同二氧化硅原料及混合方法对硅钢级氧化镁反应性的影响,找到了一种更为有效的硅钢级氧化镁反应性的评估方法,克服了传统柠檬酸活性法在比较不同厂家生产的氧化镁的反应性上的局限性。进一步研究了Na₂B₄O₇添加剂、TiO₂添加剂对氧化镁和二氧化硅反应行为的影响,结果表明,Na₂B₄O₇添加剂含量的增加对反应有利,而TiO₂添加剂对反应有阻碍作用。 The solid-state reaction behavior between silicon-steel grade MgO and SiO₂ was investigated by DSC and XRD combined with enthalpimetric analysis.The influence of different kinds of SiO₂ and different preparation methods were studied and a specifical measurement that is more reliable was proposed to evaluate reactivity of silicon steel grade MgO.It overcomes the limitation of the traditional citric acid activity（CAA） method,which can not be used to evaluate the reactivity of... 

针对宝钢硅钢常化退火过程中产生的退火炉辊印缺陷问题,通过实际生产的大数据与产品质量问题相结合,将数据挖掘、数据分析方法应用到实际,一定程度上解决了现场实际生产中的痛点,为现场生产提供决策支撑,避免了以前通过人工识别判定存在疏漏和无法定量判断的问题,形成了一套具有鲁棒性和可操作性的钢铁生产过程数据分析方法。通过智慧决策系统平台获取实际生产和表检仪数据,基于Pearson相关系数算法进行变量挑选和特征工程,并应用随机森林算法对数据建立分类预测模型,实现了质量问题的溯源和监控,通过数据量化预测了炉辊印缺陷是否可通过轧制消除的质量问题,识别准确率达到96.43%。 In views of the normalizing annealing furnace roll marks problem occurred in the process of normalizing annealing of silicon steel in Baosteel,by combining big data from actual production with product quality problems,data mining and data analysis methods were applied to actual production to solve the pain points and provide decision support,a robust and practical data analysis method for the steel production process has been developed,which avoided the previous problems of omission and non-quan...