针对1JC厚板表面质量在线检测,提出了 一种2D/3D复合成像的表面检测系统.应用2D和3D成像系统分别实现厚板上下表面无深度变化及有深度变化缺陷的检测和识别,系统均采用深度学习算法进行分类模型的训练和应用.该技术已在宝钢厚板1JC精整线得到成功验证,现场一年多的应用表明,该技术可以有效实现精整线厚板表面缺陷的在线检测和识别.

缺陷检测模型一般需要大量样本来学习缺陷的特征,但实际场景中一些重要缺陷的样本难以收集,如何用少量样本来学习罕见缺陷的特征成为一个具有挑战性的问题.为了促进少样本缺陷检测的研究,构建了一个新的工业表面缺陷数据集,包括缺陷样本和无缺陷样本.同时提出了一个两阶段缺陷增强网络以提升少样本场景下的缺陷检测性能,它利用了无缺陷样本,并将整个训练过程分为两个阶段.第一阶段的训练需要大量缺陷样本,而第二阶段的训练只需要少量缺陷样本和无缺陷样本.此外,还提出了一个缺陷突显模块,可以更好地利用无缺陷样本来增强缺陷区域的特征.在新数据集上的实验表明,该缺陷检测模型的性能优于其他的少样本目标检测模型,在工业表面缺陷检测中具有更好的应用前景.

针对热态无缝钢管表面质量在线检测,提出了一种分体式表面质量在线检测系统的架构,应用输送辊道参数,建立了成像系统的自动对中对焦模型,实现了各规格钢管表面的清晰成像.该技术已在宝钢无缝钢管厂得到成功应用,现场两年多时间的应用表明,该技术可以有效实现热态无缝钢管表面缺陷的在线检测.

针对变厚度板材的表面成像问题,根据建立的数学模型进行光源照度的调节和相机位置的自动调整,实现不同规格厚板的自动对焦成像,获取厚板表面清晰图像;并通过多相机组合测宽技术,完成厚板外形尺寸的测量.现场通过对冷态厚板进行测量测试,外形尺寸宽度精度误差小于2‰,长度精度误差小于1‰,说明该技术可有效实现厚板外形尺寸的测量.更多还原

在我国社会经济飞速发展带动下，混凝土施工技术在交通工程中的应用也得到了进一步推广，而道路桥梁作为交通工程的关键组成部分，加强混凝土施工技术在其桥梁工程中的应用研究，不仅能够从整体上提高工程施工质量，对推动我国交通事业的进一步发展也有着重要意义，应给予足够重视。

振动是影响视觉检测系统成像效果的最重要因素之一,被测对象及检测系统本身的振动对成像质量有着重要影响.在基于机器视觉的表面检测系统中,选择合适成像位置或增加稳定辊,并通过专用机械结构支撑检测系统,将检测系统与生产机组进行隔离,有效避免了生产过程中的振动对成像的影响.表面检测系统防振设计方法已在宝钢多套表面检测系统中得到应用,为表面检测系统在现场的稳定运行起到了非常重要的作用.

针对镀锡带钢表面差厚打印线在表面检测系统中的识别和剔除,以机组生产信息进行差厚打印线信息解析,结合图像处理功能有效地将差厚打印线与表面缺陷进行区分和识别.首先,生产系统将含有打印线模式的相关信息通过L3传送给带钢表面检测系统;然后,检测系统解析打印线模式,并综合图像处理结果进行打印线过滤.该技术已在宝钢镀锡带钢表面检测系统中得到成功应用,现场3年多时间的应用表明,该技术可以有效实现差厚打印线在表面检测系统中的检测.

介绍了数学形态学的原理和应用,针对中厚板表面图像存在的低对比度、背景复杂和氧化皮干扰等问题,分析表面裂纹的形态特性,提出了基于多重形态滤波和图像块累积直方图分析的表面裂纹在线检测方法.通过与其他形态学方法的对比试验,表明该方法不仅能有效地消除噪音干扰、更为准确地检测裂纹,而且能够满足实际生产的实时性需求.

For high-speed, high-resolution images of steel strip surface online inspection, a machine vision system based on TDI (Time Delayed Integration) imaging technology was researched and developed. TDI CCD sensor was used and cooperated with adaptive illumination LED light in this system. The acquired images of steel strip were sent to the image splitter through the fiber and then real-time processed by the Image Processing Units (IPU). Surface defects on tin strip were detected in this system. Application and results show effectiveness for tin strip surface defect inspection of the system (SIS) based on TDI (Time Delayed Integration) imaging technology.

A defect detection and measurement method was proposed for detecting dots and cracks on the surface of strip steel.The method includes the following steps: first,the digital image of the sample is filtered,binarized,thinned and deburred;then dot detection is conducted to the binary image and crack detection to the skeleton image;finally,after computation is made within the defect area,the number and area of dots and the number,length and direction of cracks are obtained.Test results proved the effectiveness of this method in detecting and measuring strip steel defects.

Diamond plate is one kind of steel products. It has a complex surface topography,resulting in an increase in the difficulty of applying surface quality detection system. In this paper,it attempts to analyse one of the most common defect on the surface of diamond plate-surface water marks,then gives a method of defect detection based on the texture background,to provide effective support for the deployment of the strip surface quality online detection system on the diamond plate. It presents a novel method to remove the diamond plate surface's water mark that combined with image's gray color parameter,gradient parameter and the relationship between the upper two. The method provides a good performance to make water marks excluded from the true defects.

针对宝钢某热轧产线在线检测需求及机组现场条件,自主研发了热轧带钢表面质量在线检测系统.该系统以机器视觉技术为基础,采用大功率高亮度LED光源配合高速线扫描CCD相机获取带钢表面图像,解决了高温环境下远距离清晰成像的问题.在空间尺寸受限的情况下,通过改变LED排布保证系统清晰成像所需的有效照明效果.系统中采用了高效的图像处理和目标识别算法,保证了高速图像处理及缺陷识别.现场应用证明:宝钢热轧带钢表面质量在线检测系统具有较高的实时性、可靠性和缺陷检出及识别率.

Burrs removing is a classic problem in image processing,and is also the key point of accurate calculation of strip steel crack length.A given length threshold is needed in traditional burrs removing algorithms need,however it is not feasible for crack measurement of strip steel as both long and short cracks may exist in one image.We apply the idea of Local Binary Pattern to identify each skeleton point as nodes,ends or ordinary points.Firstly most burrs are removed according to the relationship of burrs,nodes and ends.Then the shortest branches of remaining nodes would be removed and a skeleton image without burrs is obtained.The experimental result proves that it is an effective burrs removing algorithm which can make the skeleton express the object's geometric structure accurately without fixed length threshold.

When steel plates are inspected for surface defects,it is necessary to control and lower the surface temperature of the detection equipment so as to ensure normal operation of the surface defect detection system at high temperature.This paper studied the thermal protection of the surface defect detection system at high temperature,and analyzed the factors influencing the temperature variation of the detection system,such as the distance between the protective box and the plate,the area,shape and blackness of the protective box,and the ambient air temperature.For all the above influencing factors,measures to lower and control the temperature were proposed.

The harsh environment such as oil stain,dust,mosquito,high temperature and striking sound,affects strongly the normal work of on-line surface defect inspection systems for strip steel.In order to ensure the image resolution and equipment performance,the equipment should be protected effectively.The implementation of protective measures should not only satisfy the requirement of detective system for protection,but also full consider the limitation of site environment.The influence factor of site environment where the equipment is located is analyzed.Combining with its use in different production lines,the protective measures and status in-use of on-line detective apparatus of strip surface defect are introduced.

As an important part of the inspection system,a light source in normal condition is the basic guarantee of the system.In a high temperature environment,if the light is too close to the strip steel,the light will be damaged by the radiation and convection,and if the light is far from the strip steel,the illumination will be unable to satisfy the requirements.Therefore,how to control the light surface temperature and make the light in a reasonable distance range in a high temperature environment will be the key in the light source design.In this paper,the relationship between the light source distance,thermal radiation received by the light source and the illumination was analyzed.The light source which is suitable to the hot strip surface inspection has been designed.The application of the light source at the worksite has proved that the design method is correct.

When CCD is used as the image sensor to detect steel strip's surface defects, it is very often that no satisfactory image can be obtained for the field restriction and the error of the material's surface smoothness. When the linear CCD was applied to the detection of the strip surface defects, because the size of the sensor was comparatively larger and the distance between the sensor and the steel strip was limited, the image got by the sensor would be brighter in the middle and darker at both sides. For these images, a method using least-square principle fitting quadric curve was adopted and some curve parameters were obtained. In this way, the pixel grey scale was compensated and the experimental results were satisfactory.

During the quality inspection of steel strip surface,some low contrast defect images cannot be found when the inspection system employs the grad operator to segment images.It would result in some undetected errors.In order to improve the segmentation result of low contrast defects,a method based on the threshold of the scan lines was proposed.Defects like unknit and dot scratches can be segmented effectively by this method.It is also useful for the segmentation of other defects.

This paper proposes a design of internal model control systems for process with delay by using support vector regression（SVR）.The proposed system fully uses the excellent nonlinear estimation performance of SVR with the structural risk minimization principle.Closed-system stability and steady error are analyzed for the existence of modeling errors.The simulations show that the proposed control systems have the better control performance than that by neural networks in the cases of the training samples with small size and noises.

Defect segmentation results affect the precision of classification in the automatic strip surface defect detection system.In order to obtain a better result,the mean shift algorithm is presented to segment the defects in strip images.The mean shift algorithm is used to smooth the region of interest in the image and detect the defect's edge,and its effectiveness is compared with that of the median filter.Test results show that it can smooth strip images effectively and can detect the edges of defect objects accurately.The mean shift algorithm can work effectively in strip image segmentation.