钢厂
硅钢常化退火炉辊印缺陷预测分类预警方法研究
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...
提高硅钢卷材下料利用率的几种方法
阐述了影响硅钢卷材下料利用率的因素,并结合具体事例利用计算机排样系统进行了详细分析,对提高硅钢卷材的利用率具有一定的指导作用。 It describes the factors influenceing the the utilization ratio of the roll of Silicon steel,and analyzes it in detail combined with concrete examples by a computer arrangement system,which can give a guide for increasing the utilization ratio of the roll of Silicon steel.
电工钢边缘降控制研究
以马鞍山钢铁集团公司电工钢板形优化控制研究项目为背景,系统地研究了热轧、冷连轧和单机架轧机在电工钢生产过程中的边缘降控制问题。通过现场数据采集、工况数值模拟计算和工业化大生产试验,设计出适用、合理的电工钢板形控制的辊型优化曲线,满足了不同工序、不同机型的板形控制策略要求,解决了电工钢板形质量问题,取得了显著的经济效益。 Based on the project of electric steel strip shape optimization control,problem of edge drop control was systematically studied in production of electric steel of hot-rolling mill,cold-rolling mill and single stand mill.Roll optimization contour was designed out in point and reasonable by collection of work condition data,numerical simulation and test of industrial production.The shape control system can meet with the different working steps and difference mills,and quality problem of electric s...
融入结构张量和活动轮廓的硅钢表面缺陷分割
为了解决在纹理背景下冷轧硅钢表面缺陷的分割问题,提出了基于局部信息结构张量和活动轮廓模型的硅钢表面缺陷分割方法。将图像的局部信息引入到结构张量中;在结构张量提取的特征空间中,以KL距离作为区域的概率密度相似性度量建立分割图像的活动轮廓模型;采用Split-Bregman数值解法对模型进行求解。运用提出的分割方法对硅钢表面的一些常见缺陷如纵向划伤、横向划伤、异物和孔洞等进行分割实验。实验结果表明,该方法可以准确地分割出硅钢表面缺陷区域,验证了该方法的有效性。 In order to address the segmentation problem for cold rolled silicon steel surface defect based on the texture background,a novel method based on structure tensor and active contour model is proposed.Image local information is introduced to the structure tensor.In the extracted feature space of structure tensor,KL distance is treated as a regional similarity measure of the probability density to establish active contour model for image segmentation.The numerical solution of Split-Bregman is used...
辉光放电发射光谱法测定硅钢薄板中微量硼元素
通过对辉光放电发射光谱参数的优化,以铁元素为内标来消除基体效应,建立了测定硅钢薄板中微量硼元素的方法。优化的实验参数为:放电电压1200 V,放电电流50 mA,预溅射时间40 s,积分时间10 s。校准曲线硼元素含量范围0.0001%~0.022%,相关系数大于0.999,测量结果与认定值一致,相对标准偏差小于10%。完全能够满足日常分析测试的要求。 A glow discharge optical emission spectrometry(GD-OES) method for determining trace boron element in silicon steel sheets were established through optimization of instrumental parameters and using Fe element as an internal standard to eliminate the matrix effect.The optimized instrumental parameters included discharge voltage,discharge current,pre-sputtering time and integration time,which are 1200 V,50 mA,40 s,and 10 s,respectively.The content of boron element that can be determined from the ca...
冷轧无取向硅钢产品标准浅析
聚焦无取向硅钢产品标准,从电磁性能、表面性能、机械性能以及尺寸公差与边部质量等维度对国际标准IEC、EN、JIS、ASTM以及国标GB进行了分析研究。分析得出,各类标准在电磁性能方面要求基本一致;ASTM标准的机械性能要求有别于其他几个标准。 In this paper,non-oriented silicon steel standards of EN,JIS,GB and ASTM were compared and analyzed. It is showed that,all types of standards in electromagnetic performance requirements are basically the same. Surface properties in ASTM standard are expressed in the most detailed. The mechanical properties requirements of the standards,except for ASTM,are basically the same.
