隐马尔可夫树模型在带钢表面缺陷在线检测中的应用

通过图像分割算法寻找由缺陷组成的可疑区域是热轧带钢表面缺陷在线检测与识别的关键。将热轧带钢表面图像分为“背景”和“缺陷”两大类,采用隐马尔可夫树(Hidden Markov tree,HMT)模型分别建模并实现多尺度缺陷分割。将不同类别的缺陷用同一个“缺陷模型”来表示,可以降低算法复杂度。HMT模型对带钢表面常见缺陷的分割正确率达到94.4%,分割错误率为18.8%。针对HMT模型得到的细尺度分割结果中分割错误率较高问题,引入基于环境的多尺度融合方法(Context-adaptive hidden Markov tree, CAHMT),将不同尺度的分割结果融合,大幅降低细尺度分割的分割错误率,达到3.7%。     

带钢表面缺陷检测及分割技术研究

对带钢表面缺陷检测与分割技术进行了深入的研究,探讨了针对带钢表面缺陷图象特点所应:采取的策略.首先通过对传统差影图法进行改进,提出了一种通过实时更改标准图的缺陷检测方法,并通过;比较四种常用的分割算法,选择出适合带钢表面缺陷分割算法-迭代阈值法.     

影响热轧带钢氧化铁皮酸洗质量和速度的因素

用SEM、表面粗糙度仪对SPHC热轧带钢氧化铁皮的表面形貌、厚度、界面粗糙度、显微结构等因素对其酸洗质量和速度的影响进行了分析,探讨了酸洗工艺的调整对改善氧化铁皮酸洗效果的影响.结果表明:使氧化铁皮表面产生裂纹、厚度减薄均有利于提高酸洗速度;提高氧化铁皮的厚度均匀性、降低表面粗糙度,可减少带钢的酸洗色泽灰暗等缺陷;开卷状态下快速冷却的氧化铁皮具有双层结构,酸洗速度较快,卷曲状态下缓慢冷却的氧化铁皮酸洗速度较慢;用6%HCI溶液酸洗时,合适的带钢预热温度是60℃左右,可缩短酸洗时间;用18%HCI溶液酸洗时,合适的酸液温度为75～85℃,可显著缩短酸洗时间.     

基于Tetrolet变换的热轧钢板表面缺陷识别方法

通过Tetrolet变换将热轧钢板表面图像分解成不同尺度和方向的子带,提取子带的Tetrolet高通系数矩阵特征,得到一个高维的特征矢量。利用核保局投影算法对高维特征矢量进行降维,将降维后的低维特征矢量输入支持向量机,从而实现热轧钢板表面缺陷的分类识别。对现场采集到的热轧钢板表面图像样本进行试验,包括横向裂纹、纵向裂纹、横向划伤、纵向划伤、结疤、麻点、网纹、压痕等8类常见热轧钢板表面缺陷,以及氧化铁皮和无缺陷等样本。试验结果表明基于Tetrolet变换方法对样本图像的识别率可达97.38%,比基于Curvelet变换、Contourlet变换等方法得到的识别率提高1%左右。     

冷轧带钢表面相似线性缺陷检测

针对现有冷轧带钢表面的相似线状缺陷检测精度与识别率差的问题，提出一种局部二制模式LBP直方图特征与支持向量机SVM相结合的检测算法。通过对采集的大量划伤与夹杂的带钢表面缺陷图进行预处理，获得感兴趣区域，再进一步利用LBP等价模式获得目标区域的LBP直方图信息，结果显示可以很好地分辨缺陷与非缺陷，并描述的各种缺陷具有可分辨性。采用核函数为径向基函数核的SVM分类器训练识别，结果表明：该方法对划伤和夹杂的缺陷检测准确率达98%。     

一种改进YOLOv4-tiny的带钢表面缺陷实时检测方法

带钢表面缺陷检测是生产过程智能检测的重要任务。针对目前带钢表面缺陷检测算法效率低、实时性差的问题,本文提出了基于卷积神经网络的轻量级目标检测器。该方法以YOLOv4-tiny模型为框架,针对带钢表面缺陷检测任务的特殊性,结合了多尺度检测与空间注意力机制的优化策略,在保证检测效率的同时提高了轻量级目标检测器的精度。实验证明,所提出的改进的YOLOv4-tiny模型能够精确地检测带钢表面缺陷,平均均值精度mAP(mean Average precision)为73.29%,并且每秒帧数FPS (Frames per second)达到163,满足实际工业落地的实时性要求。     

热轧变形区润滑条件与板带钢表面质量关系试验研究

为研究热轧变形区润滑条件与轧后板带钢表面质量关系,对热轧变形区润滑机理进行计算分析,设计一种可移动式热轧工艺润滑装置,用于板带钢热轧工艺润滑试验。研究不同热轧变形区润滑条件对轧后板带钢表面粗糙度、氧化膜断面厚度、钢板酸洗后形貌的影响。结果表明:在热轧变形区内,当轧制速度大于2m/s时,热轧油油滴在变形区的停留时间在0.07s以内,远小于油滴着火延迟时间与油滴燃烧需要的时间之和,油水混合液来不及燃烧便已通过变形区,仍为传统的液态润滑形式;采用工艺润滑与无润滑相比,表面粗糙度降低40%左右,氧化膜厚度减少50%以上。通过3D显微镜进一步对酸洗后钢板表面进行观察分析,可以发现热轧变形区润滑能够明显减少钢板表面缺陷,使板带钢轧后表面轧制纹络清晰,表面质量得到显著改善。     

FPGA图像处理在带钢表面缺陷视觉检测中的应用

为有效解决冷轧带钢表面缺陷在线视觉检测系统中图像处理的瓶颈问题,本文提出了一种新型冷轧带钢表面缺陷检测与识别算法流程。首先介绍了阀值中值滤波算法及迭代阀值分割算法;接着对这两种算法的计算流程进行了分析;最后采用Xilinx公司的System Generator模块在Simulink中完成缺陷图像的中值滤波变换及迭代阀值分割任务。实验结果表明:Slice Flip Flops使用率28%,4 Input LUTs使用率10%,Occupied Slices使用率34%,FPGA图像处理技术可以解决图像信息实时处理这一关键问题。FPGA图像处理技术基本满足在线检测的稳定可靠、精度高、抗干扰能力强等要求,且能较好的满足实际生产线上的处理速度要求。     

实时带钢表面质量检测算法研究与应用

针对现有带钢表面质量检测技术在检测精度、数据实时吞吐量等方面存在的问题,提出了一种基于纹理特征编码的带钢表面缺陷检测方法。首先,利用高斯滤波器的差分响应模拟人类视觉的纹理感知模型,在原始图像空间内进行缺陷可疑点检测;然后对疑似缺陷位置进行纹理特征的提取与编码,在纹理特征编码空间内完成缺陷的精密定位。实验结果表明,该方法可以对带钢表面常见的氧化、孔洞、边裂、麻点等十几种不同类型缺陷进行精确地检测,降低了系统的误检率,同时提高了缺陷检测的识别率和算法的计算效率。     

基于谱残差视觉显著性的带钢表面缺陷检测

针对带钢表面缺陷检测实时性要求高,采集的图像易受光照环境影响且缺陷特征弱等因素影响,提出一种基于谱残差视觉注意模型的带钢表面缺陷在线检测算法。首先,提出改进同态滤波方法对图像预处理,去除光照不均匀的影响,改善后续的分割结果。然后,构建谱残差视觉注意模型,通过对数频谱曲线差分得到缺陷显著图像。最后,提出加权马氏距离方法对显著图像阈值化增强,并利用连通区域标记法,标记出原带钢图像的缺陷位置。对提出的算法进行了实验验证,结果显示:该算法检测速度快,单幅图像平均检测耗时仅37.6ms,满足带钢在线实时检测要求。在同一缺陷数据库与灰度投影法,多尺度Gabor边缘检测法和隐马尔可夫树模型法进行了性能对比,结果表明:本文算法对带钢常见8类缺陷类型,平均检测率达到了95.3%,且漏检率和误检率较低,有效性高于对比算法。     

基于激光线光源的钢轨表面缺陷三维检测方法

将结构光三维检测方法应用于钢轨生产过程中的表面缺陷三维检测,通过在钢轨四周安装4台激光线光源和8台面阵CCD摄像机实现钢轨四个面的检测。对摄像机采集到的激光光带图像进行光带中心提取、光带中心线矫正、光带中心线与基准线的差值等步骤,得到钢轨表面深度的变化值,并将沿钢轨长度方向和高度方向的深度变化值用深度分布图表示,通过两维图像识别的方法检测缺陷所在的区域,从而实现钢轨表面缺陷的自动检测。该方法已经实现在线应用,可以达到的最大检测速度为1.5m/s,深度检测分辨力为0.2mm。     

Fuzzy algorithm for calculating roll speed variation based on roll separating force in hot rolling

Thickness control of hot-rolled strips has become an important issue in recent years because of the need for improving the quality of the hot-rolled strip. For this purpose, various thickness control systems such as finishing mill set-up (FSU), automatic gauge control (AGC), and looper control system, have been developed at steel works. Although these systems have greatly improved the quality of the strip thickness, there still exists a small amount of thickness deviation. It is difficult to adequately control by applying conventional thickness control techniques since hot rolling process is a highly nonlinear system in which many process parameters are coupled. In this study, a fuzzy algorithm to calculate the roll speed variations was developed in order to improve the thickness uniformity of hot-rolled strips. Since the strip thickness is mostly affected by the magnitude of roll separating force depending on the roll speed, the strip thickness deviation between the desired and actual thicknesses can be reduced by controlling roll speed. In order to carry out this investigation, slab analysis was carried out to determine the relation between roll separating force and roll speed for various process parameters such as roll speed, reduction ratio, strip entry thickness, and front and back tensions. From the production data, the effective stress-strain rate relations of the materials used in slab analyses were acquired. Based on the analytical results, the relation between roll separating force and roll speed was approximated by a log function. A fuzzy algorithm was developed to determine variations in roll speed according to variations of roll separating force, depending on various ranges of rolling temperature, reduction ratio, front and back tensions, and strip thickness. In addition, simulations to predict roll speed variations for a small amount of thickness deviation were carried out at continuous finishing mills consisting of seven stands and the calculated roll speed variations were found to be reasonable. Thus, the developed fuzzy algorithm might be useful in reducing the thickness deviation in the actual hot rolling mills.     

含钢骨架橡胶密封条的冲切加工

含钢骨架橡胶密封条的冲切加工不同于单独的橡胶或金属材料的加工。文中给出了适合的刀具参数和夹具设计，这些刀具和夹具被应用在某型家用汽车密封条生产线，使用情况良好。     

Mechanical and Tribological Properties of Shot-Peened SAE 1070 Steel

The effects of shot peening pressure on the mechanical and tribological properties of shot-peened SAE 1070 steel strips were systematically investigated. The surface hardness of the shot-peened steel strips significantly increased with increased shot peening pressure due to the promoted cold work-hardening effect. The tribological results showed that the increased surface roughness of the shot-peened steel strips associated with increased shot peening pressure resulted in their increased friction by enhancing mechanical interlocking between two rubbing surfaces. The wear of the shot-peened steel strips decreased with increased shot peening pressure via their increased surface hardness. However, the shot-peened steel strips at shot peening pressures less than 345 kPa did not exhibit better wear resistance than the as-received steel strip, indicating that a certain intensity of shot peening was required to improve the wear resistance of the shot-peened steel strips. It could be concluded that the mechanical and tribological properties of the shot-peened steel strips were significantly influenced by the shot peening pressure.     

热轧钢卷搬运设备的设计

以钢卷搬运概念入手,以某钢厂的一条热轧钢板生产线为案例,以其工艺时序图和设备速度图为依据,通过对钢卷搬运设备的分析对比,提出了钢卷搬运设备的选择方法和思路,指出了在计算能力时应考虑的因素,给出了设备能力的计算方法,为热轧钢板生产线的设计提供了经验。     

Economical preparation of 40X steel for cold upsetting of bolts

If hot-rolled 40X steel bar is prepared for cold upsetting by the energy-saving technology here proposed, the production costs of the resulting bolts will be reduced.     

Tribological behavior of low-carbon steel depending on treatment and structural state

The work presents the results of tribological study of low-carbon steel (up to 0.2 wt % carbon) in three states: initial (hot-rolled), heat-treated (refined), and refined and further subjected to severe plastic deformation by equal-channel angular pressing. After the various treatment types, the steel samples are found to be in different structural states with different hardness values and oxygen content in the surface layer. These factors exert a complex effect on the material’s tribological properties in contact with tool steel. The lowest adhesive strength, friction coefficient, and wear rate are shown by refined and plastically deformed steel.