基于背景减除的彩色铁谱图像自动分割

提出一种基于背景减除和标记分水岭算法的彩色铁谱图像自动分割方法.其分割流程为:基于颜色分量比对彩色铁谱图像的背景进行减除,实现磨粒与背景的分离;通过对分离后的图像进行形态学处理使其成为后续分水岭分割的基础图像;结合形态学复合开闭重建和阈值极小值提取技术得到磨粒前景标记图像,对磨粒测地影响区骨架进行提取得到图像背景标记;利用形态学极小值强加技术修改基础图像,并利用分水岭算法实现其自动分割.     

基于图像增强的OLVF反射光磨粒图像分割算法

针对反射光磨粒图像中亮度过高和过暗部分难以识别的问题,提出一种基于图像增强的OLVF(On-Line Visual Ferrograph)反射光磨粒图像分割算法.对原始图像进行背景减操作,大致区分出磨粒部分;利用形态黑帽操作增强反射光磨粒图像,使图像总体亮度均衡.对增强后的图像应用Canny边缘检测操作分割出磨粒,利用Otsu算法获取H-minima校正图像的阈值以消除局部极值干扰.最后,运用膨胀腐蚀开闭操作填充孔洞,实现了OLVF反射光磨粒图像分割,获得了准确、连续的磨粒图像.与其他同类算法相比,该算法有效抑制了反射光影响,更好地保留磨粒图像信息.     

自动阈值法在铁谱图像磨粒分割中的应用

铁谱图像处理、分析的目的就是要通过对图像中磨粒信息的研究来判断机械磨损形式及故障原因,而磨粒信息的获取依赖于铁谱图像磨粒的分割和磨粒特征的提取。本文将数学形态学中的自动阈值算法引入铁谱磨粒图像的分割中,利用MATLAB程序成功地完成了磨粒图像的分割,有助于实现铁谱磨粒的自动识别。     

自动阈值法在铁谱图像磨粒分割中的应用

铁谱图像处理、分析的目的就是要通过对图像中磨粒信息的研究来判断机械磨损形式及故障原因，而磨粒信息的获取依赖于铁谱图像磨粒的分割和磨粒特征的提取。本文将数学形态学中的自动阈值算法引入铁谱磨粒图像的分割中，利用MATLAB程序成功地完成了磨粒图像的分割，有助于实现铁谱磨粒的自动识别。     

一种彩色铁谱图像自动分割方法

铁谱图像有效分割是实现铁谱图像自动化分析的基础,但彩色磨粒图像背景颜色相对单一,磨粒区域同时包含亮区域和暗区域且与背景色差较大,且部分磨粒存在黏连的情况,因此铁谱图像的有效分割难以实现。根据彩色铁谱图像特点,提出基于两次K-means颜色聚类分离磨粒区域与背景区域后,再对磨粒区域采用改进的分水岭算法分割黏连磨粒的图像分割方法。该方法解决了铁谱图像中亮暗磨粒同时存在的情况下磨粒提取不完全的问题,并实现了黏连磨粒的分割。实验结果验证了该方法的有效性。     

气泡高干扰在线铁谱视频图像的磨粒快速分割算法研究

针对在线铁谱视频图像气泡高干扰所面临的磨粒分割困难问题,提出一种气泡高干扰在线铁谱视频图像的磨粒快速分割算法。首先运用运动检测的方法确定视频中气泡的位置,并用相邻帧相同位置的图像信息对气泡区域进行处理,再使用双边滤波对处理后的图像进行平滑去噪,实现气泡干扰的初步抑制;最后基于抑制气泡图像的灰度直方图,对每一帧图像选取其自适应的阈值,实现在线铁谱视频图像中磨粒的快速分割。该研究为在线铁谱的磨粒分割与后续对磨粒特征的智能提取和分析奠定了基础。     

基于yolov5在线可视铁谱图像磨粒多目标识别方法研究

鉴于在线图像可视铁谱获取的磨粒谱片图像分辨率低,磨粒种类复杂多变,磨粒图像背景复杂等问题,使得磨粒在线智能识别面临挑战。为了实现在线可视铁谱图像磨粒多目标实时检测与识别,提出基于yolov5在线可视铁谱图像磨粒多目标识别方法。以正常磨损磨粒、疲劳磨损磨粒、滑动磨损磨粒、球形磨粒、氧化磨损磨粒、切削磨损磨粒6种磨粒作为研究对象,基于yolov5深度神经网络模型对复杂油液环境下的异常磨损磨粒进行分割与识别。结果表明：基于yolov5算法的磨粒智能识别模型能够实现复杂环境下多目标、多类型磨粒在线实时识别,其识别速度和准确率基本满足油液在线监测需求,为装备在线图像可视铁谱技术工业化应用提供了技术支撑。     

图像可视在线铁谱传感器的图像数字化处理技术

为实现图像可视在线铁谱传感器的磨粒图像自动辨识,建立数字图像获取系统,探讨铁谱图像数字化处理方法。研究了铁谱图像的预处理方法,对比在RGB和YUV颜色空间对铁谱图像的灰度化处理效果,采用不同的微分模板对平滑后图像进行锐化处理;探讨减背景法和自动阈值法在铁谱图像磨粒分割中的应用效果;给出适用于在线铁谱图像的定量描述方法。研究表明,采用YUV颜色空间的明视度分量可以得到平滑的灰度图像,合理的模板选择可以使微分法在锐化磨粒边缘的同时保持整体图像的平滑;铁谱图像的磨粒分割结果表明,减背景法由于采用人工选取门限值而难以适用于在线铁谱图像的处理,而自动阈值法可以根据铁谱图像自动选取合适的阈值以达到良好的分割效果;采用磨粒百分覆盖面积作为定量指标可反应良好分割的铁谱图像中的磨粒统计质量分数。     

一种改进的基于最大类间方差的图像分割方法

在分析最大类间方差阈值图像分割算法原理的基础上,根据实际图像直方图中目标与背景的像素分布特点,提出了一种改进的最大类间方差图像分割算法.该算法充分考虑了图像直方图中目标与背景存在交叉的情况,通过与传统阈值分割算法的实验比较,证明该算法具有分割精度高、效果好、速度快的特点.     

基于萤火虫算法的二维熵多阈值快速图像分割

提出了基于萤火虫算法的二维熵多阈值快速图像分割方法以改善分割复杂图像和多目标图像时存在计算量大、计算时间长的问题。首先,分析了二维熵阈值分割原理,将二维熵单阈值分割扩展到二维熵多阈值分割。然后,引入萤火虫算法的思想,研究了萤火虫算法的仿生原理和寻优过程;提出了基于萤火虫算法的二维熵多阈值快速图像分割方法。最后,使用该方法对典型图像进行阈值分割实验,并与二维熵穷举分割法、粒子群算法(PSO)二维熵多阈值分割法进行比较。实验结果表明:该方法在单阈值分割、双阈值分割和三阈值分割时分别比二维熵穷举分割法快3.91倍,1040.32倍和8128.85倍;另外,在阈值选取的准确性和计算时间方面均优于PSO二维熵多阈值分割法。结果显示,基于萤火虫算法的二维熵多阈值快速图像分割方法能快速有效地解决复杂图像和多目标图像的分割问题。     

基于Mask R-CNN的铁谱磨粒智能分割与识别

针对铁谱图像因背景复杂、尺寸分布广、颗粒重叠等导致难以精确分割与识别的问题,以相似度高的疲劳剥块、严重滑动磨粒、层状磨粒共3种异常磨粒作为研究对象,提出基于深度神经网络模型Mask R-CNN的对多目标铁谱磨粒进行智能分割与识别的方法,并对特征提取层分别选用深度不同的残差网络ResNet50和ResNet101进行对比试验。实验结果表明,基于迁移学习方法的Mask R-CNN+ResNet101模型能够在复杂背景下对多目标、多类型、多尺寸的相似磨粒进行有效分割与识别,测试集的平均精度高达76.2%,模型具有较好的泛化能力。     

基于粗糙集和神经网络的润滑油中磨损磨粒的识别

为了更有效地对润滑油中的磨损磨粒进行识别,探讨了基于粗糙集和神经网络的磨粒识别。它首先利用粗糙集理论对磨粒特征参数进行约简,这样能够大大减少了神经网络的输入维数。然后介绍了一种径向基神经网络,并利用它对磨粒进行分类。对20个磨粒进行识别,磨粒分类分对14个,分错6个,识别率达到70.0%。     

Intelligent identification of wear mechanism via on-line ferrograph images

Condition based maintenance（CBM） issues a new challenge of real-time monitoring for machine health maintenance. Wear state monitoring becomes the bottle-neck of CBM due to the lack of on-line information acquiring means. The wear mechanism judgment with characteristic wear debris has been widely adopted in off-line wear analysis; however, on-line wear mechanism characterization remains a big problem. In this paper, the wear mechanism identification via on-line ferrograph images is studied. To obtain isolated wear debris in an on-line ferrograph image, the deposition mechanism of wear debris in on-line ferrograph sensor is studied. The study result shows wear debris chain is the main morphology due to local magnetic field around the deposited wear debris. Accordingly, an improved sampling route for on-line wear debris deposition is designed with focus on the self-adjustment deposition time. As a result, isolated wear debris can be obtained in an on-line image, which facilitates the feature extraction of characteristic wear debris. By referring to the knowledge of analytical ferrograph, four dimensionless morphological features, including equivalent dimension, length-width ratio, shape factor, and contour fractal dimension of characteristic wear debris are extracted for distinguishing four typical wear mechanisms including normal, cutting, fatigue, and severe sliding wear. Furthermore, a feed-forward neural network is adopted to construct an automatic wear mechanism identification model. By training with the samples from analytical ferrograph, the model might identify some typical characteristic wear debris in an on-line ferrograph image. This paper performs a meaningful exploratory for on-line wear mechanism analysis, and the obtained results will provide a feasible way for on-line wear state monitoring.     

On the wear debris of polyetheretherketone: fractal dimensions in relation to wear mechanisms

It has been recognized that wear debris contains extensive information about wear and friction of materials. Investigation of wear debris is important for tribological research. In order to find out an effective way that is able to diagnose and predict the wear state of polymers, the authors investigated the relationship between the wear debris morphology and the wear behaviour of the bulk material. Polyetheretherketone (PEEK) was employed as the model material. Its sliding wear and friction properties were measured by means of a pin-on-disc apparatus. At a constant sliding velocity of 1 m s⁻¹, the specific wear rate was independent of load under lower loading conditions (1–4 MPa) but increased with a rise in load under higher loading conditions (4–8 MPa). The coefficient of friction was insensitive to the variation of contact pressure. The possible mechanisms involved were analysed on the basis of the wear debris morphology as well as the wear performance. Fractal geometry, which describes non-Euclidean objects, was applied to the quantitative analysis of the boundary texture of the wear debris due to the fact that the qualitative assessment of the wear debris morphology was not effective enough to reflect the geometrical variation of the fragmental shapes. The experimental results demonstrated that the wear debris were fractals, and could be characterized with the fractal dimensions which were determined by the slit island method. In addition, it was found that the fractal dimension of the wear debris was closely related to the wear behaviour of PEEK, and can be regarded as a measure of wear rate.     

Watershed-Based Morphological Separation of Wear Debris Chains for On-Line Ferrograph Analysis

Separation and characterization of wear debris from ferrograph images are demanded for on-line analysis. However, particle overlapping issue associated with wear debris chains has markedly limited this technique due to the difficulty in effectively segmenting individual particles from the chains. To solve this bottleneck problem, studies were conducted in this paper to establish a practical method for wear debris separation for on-line analysis. Two conventional watershed approaches were attempted. Accordingly, distance-based transformation had a problem with oversegmentation, which led to overcounting of wear debris. Another method, by integrating the ultimate corrosion and condition expansion (UCCE), introduced boundary-offset errors that unavoidably affected the boundary identification between particles, while varying the corrosion scales and adopting a low-pass filtering method improved the UCCE with satisfactory results. Finally, together with a termination criterion, an automatic identification process was applied with real on-line wear debris images sampled from a mineral scraper gearbox. With the satisfactory separation result, several parameters for characterization were extracted and some statistics were constructed to obtain an overall evaluation of existing particles. The proposed method shows a promising prospect in on-line wear monitoring with deep insight into wear mechanism.     

磨粒类型识别研究

提出了一种有效的磨粒类型识别方法，该方法除了选用传统的磨粒形态特征参数，将表面粗糙度和表面纹理指数也作为重要的磨粒识别参数，选用面积、长度、圆度、纤维比率、体态比、边界分形维数、表面粗糙度．Sa．Sq，和表面纹理指数（Stdi）等9个参数，采用人工神经网络来识别磨粒类型，应用示例表明效果良好，提高了磨粒类型识别的精确度。     

基于磨粒颜色特征的识别方法研究

磨粒监测是机械设备故障诊断的有效方法,其中磨粒的识别是目前研究的重点和难点,磨粒的颜色参数是识别磨粒的重要特征。基于对因子分析方法的介绍,将彩色磨粒图像提取的颜色变量减少为5个主要特征,简化了描述参数。结果表明,选择适合的HSV获得不同磨粒的空间分布,设置分割线,就可用于不同颜色的磨粒分类和识别。     

Wear and wear particles—some fundamentals

Each of the various processes by which material can be lost from a surface in service leaves its fingerprint both in the topography of the worn surface and in the size, shape and number of the particles which make up the wear debris. To use debris examination as a diagnostic aid in assessing the health of operating plant, which may contain many tribological contacts, requires not only careful and standardised procedures for debris extraction and observation but also an appreciation of the mechanisms by which wear occurs and the regimes in which each of the contacts of interest operates when displayed on an appropriate operational map.