基于快速C均值聚类算法的烧结断面图像分割

利用图像分割技术,采用基于快速C均值聚类（FFCM）算法,实现了烧结图像背景、红火区和气孔区的自动分割。该算法在Visual C＋＋2008软件开发平台上编程实现并与其他算法作了比较。实验表明该算法对于具有多峰直方图的烧结断面图像有良好的实时性和分割效果,为烧结断面图像特征提取和识别工作奠定了良好基础。     

用模糊聚类Fuzzy C-Means算法实现图像分割

本文描述了一种有效的FuzzyC-Means(FCM)聚类算法的数学原理及其在图像分割中的应用,该算法的主要特点是提供了一种非监督的模糊聚类方式。为了减少计算量,文章引入了塔型数据结构PDS(PyramidDataStructure),并对FCM算法的初始模糊矩阵的选取和实验结果进行了讨论。     

模糊聚类算法综述

模糊聚类算法是近年来图像分割技术领域的研究热点之一。本文在对模糊C均值聚类算法分析的基础上,结合目前在图像分割中的应用研究,对模糊C均值聚类算法的有效性进行了比较分析。从隶属度、聚类数和其它方面,评述改进的模糊c均值聚类算法。最后讨论模糊c均值聚类算法目前存在的问题和发展方向。     

微细铣削技术研究综述

微细铣削可以加工三维自由曲面及复杂零件,其应用前景日益广阔。然而由于刀具尺寸及加工参数的急剧减小,微细铣削表现出显著不同于传统铣削的切削特性,因此近年来研究人员对微细铣削技术进行了广泛研究。微细铣削的加工过程复杂,涉及到许多方面,综述国内外在微细铣削方面的研究,总结了微细铣削加工过程中最小切削厚度、切削力、表面粗糙度、刀具磨损及其他方面研究的最新进展。探讨了微细铣削所研究的各方面的发展趋势,并对其应用前景进行了初步讨论。     

Improved analytical chip thickness model for milling

In this paper an analytic expression for chip thickness in milling was formulated while considering the cycloidal motion of the teeth, runout, and uneven teeth spacing. In order to generalize the equation, the cutting parameters associated with milling (linear feed, tool rotational speed, and radius) were combined into a single, non-dimensional parameter. The new parameter allowed abstraction of the milling process and enabled selection of the maximum possible chip thickness in milling. Equations for entry and exit angles of a cut were also developed. The chip thickness values given by the new model were compared to prior models and showed lower error levels.     

选择高速钢刀具材料的专家模糊聚类算法

在加工中心数控系统内开发的选刀专家系统中应用模糊聚类分析法，结合选刀专家系统，提出了一套新的用于选择高速钢刀具材料牌号的模糊聚类分析模型和算法。实践证明，这种方法适用面广，易于扩充，简单、有效，具有一定的理论意义和较高的实用价值，为选刀专家系统的进一步开发打下了坚实的基础。     

Multi-objective optimization using Taguchi based grey relational analysis for micro-milling of Al 7075 material with ball nose end mill

This study was carried out to understand micro-milling of aluminum material with ball nose end mill and consisted of four stages: experimental work, modelling, mono and multi objective optimization. In the first stage (experimental work), micro-milling experiments were carried out using Taguchi method. The effects of spindle speed, feed per tooth and depth of cut on tool wear, force and surface roughness were investigated. Cutting tools and workpiece surfaces were also inspected via scanning electron microscope. Adhesion and abrasion wear mechanisms during micro-milling of aluminum were observed. Workpiece surfaces had the accumulations of plastically deformed workpiece material due to the high ductility of aluminum. In the second stage (modelling), all data gathered in the experimental works were utilized to formulate first-order models with interaction. These first-order models with interaction could be used to predict responses in micro-milling of aluminum with a minor error. In the third stage (mono-objective optimization), responses were used alone in optimization study as an objective function. To minimize all responses, Taguchi’s signal to noise ratio was used. The effect of control factors on responses was determined by analysis of variance. In the fourth stage (multi objective optimization), responses were optimized simultaneously using grey relational analysis.     

基于小波分析和模糊控制理论的铣刀磨损监控方法

研制了一种铣刀磨损的监控方法.在该系统中信号采集采用声发射传感器,信号的特征提取采用小波分析的方法,将变换后的尺度系数和各个频段的小波系数作为特征,采用自行设计的Sugeno模糊控制系统进行状态识别,模糊控制系统的输出是刀具磨损的具体值.     

混沌差分优化数据聚类及在故障诊断中的应用

以某往复式天然气压缩机三类典型故障下的振动数据为例,进行数据聚类性能仿真和故障诊断应用实验,仿真实验结果表明改进的FCM数据聚类算法聚类性能效果有较大提高,故障类别分类诊断中能提高故障判断准确率15％以上,在工程实践中具有很好应用前景.     

基于多特征量的刀具磨损模糊判决研究

利用信号处理技术分析AE、Ac及切削力信号特征参数随刀具磨损的变化规律,并将这些特征参数组成反映刀具磨损状态的特征矢量。论文提出基于模糊理论的刀具磨损状态识别方法。试验证明,该方法能有效地判断刀具状态,比常用的利用神经网络进行磨损状态分析的方法更具有理论直观性与操作的时效性。     

Predicting Visible Image Degradation by Colour Image Difference Formulae

It carried out a CRT monitor based psychophysical experiment to investigate the quality of three colour image difference metrics, the CIEAE ab equation, the iCAM and the S-CIELAB metrics. Six original images were reproduced through six gamut mapping algorithms for the observer experiment. The result indicates that the colour image difference calculated by each metric does not directly relate to perceived image difference.     

逆向工程中基于模糊聚类的点云数据分区

点云数据分区是逆向工程中重要而又难以解决的问题。首次将模糊聚类方法应用于逆向工程中的点云数据分区,用点的位置矢量、法矢量、高斯曲率和平均曲率8维向量作为特征向量,加权距离替代欧氏距离。在实现分区的同时,可以识别区域内部点和边界附近点,便于后续曲面特征参数精确提取。实验结果证明此算法具有较强的抗噪性,并具有较高的分区效率。     

基于动态树理论的刀具磨损监测技术

提出了基于动态树理论的刀具磨损监测方法,通过相关系数法提取传感器信号与刀具磨损最相关的几组特征,并采用具有局部记忆的B样条模糊神经网络建立刀具磨损量与声发射信号、切削力信号和振动信号特征之间的非线性映射关系,构造了任意加工条件下的刀具磨损监测系统,刀具磨损的识别结果由集成神经网络输出。试验结果表明,基于此方法构建的刀具磨损监测系统具有精度高、可靠度强、增殖性好和在线识别速度快等优点,值得工业推广。     

基于时序分析与模糊聚类的铣削刀具磨损状态识别

对XKA714数控铣床采集的刀具运行状态振动信号进行计算、检验、分析样本自相关函数和样本偏相关函数的截尾性、拖尾性和周期性以及模型参数估计等时间序列相关分析,可判断动态数据序列适于AR(p)(autoregression)模型.以阶数p取12的模型参数作为特征向量提取,并采用模糊聚类分析方法确定刀具运行状态特征向量样本的亲疏关系,实现对铣削刀具的初期磨损阶段、正常磨损阶段和剧烈磨损阶段运行状态的识别.研究结果表明,基于时间序列分析与模糊聚类分析相结合的识别方法可以用于刀具磨损运行状态识别.     

Assessment and visualisation of machine tool wear using computer vision

Tool wear monitoring is an integral part of modern CNC machine control. Cutting tools must be periodically checked for possible or actual premature failures, and it is necessary to record the cutting history for a tool’s full life of utilisation. This means that an on-line monitoring system would be of great benefit to overall process control in manufacturing systems. Computer vision has already shown promise as a candidate technology for this task. In this paper, we describe the use of digital image processing techniques in the analysis of images of worn cutting tools in order to assess their degree of wear and thus remaining useful life. It is shown that a processing strategy using a variety of image texture measures allows for effective visualisation and assessment of tool wear, and indicates good correlation with the expected wear characteristics.     

When,what and how image transformation techniques should be used to reduce error in Particle Image Velocimetry data?

Particle Image Velocimetry is commonly used to compute velocity fields in several areas including fluid mechanics, hydraulics and geophysics. However, acquired images often contain deformations caused either by camera lenses or placement. In this work the most popular digital transformation methods used to remove/reduce these deformations are benchmarked and suggestions tailoring specific transformations to different types of deformations are made. This article also shows the reduction of the error associated to the first and second order statistics, in the case of two-dimensional Particle Image Velocimetry, when the transformation techniques are applied to the computed velocity fields, and not the raw images, a common option in available commercial software.     

相位相关配准法及其在射线图像数字减影中的应用

介绍了一种基于相位相关法射线图像配准的方法。该方法利用傅立叶变换的平移特性对发生平移和旋转的两幅图像进行精确的配准。提出了将该方法用在数字减影中图像的配准 ,首先用相位相关配准法对发生平移和旋转的两幅图像进行配准 ,然后 ,对配准好的图像进行数字减影 ,正确地检测出了构件的内部状态。实验证明 ,该方法完全不受人工干预 ,具有较高的精度和较强的抗噪能力 ,匹配速度也有很大提高。同时 ,旋转校正算法简单 ,易于实现 ,能够满足系统的实时性要求     

基于彩色图像的运动目标分割方法

针对彩色图像Hue-saturation-intensity颜色模型各分量所携带的颜色信息不同的特点,结合区域分割算法在彩色图像中提取区域颜色特征,并将区域颜色特征作为局部阈值分割方法的阈值特征,提出一种基于图像区域颜色特征的运动目标分割方法。分割试验显示了该运动目标分割方法的有效性和可行性。提出融合梯度算子和子区合并技术进行区域分割的方法,子区合并技术能够在一定程度上防止两个独立的区域被错误的合并成一个区域, 这种区域分割方法和常用的Region growing算法的对比分割试验显示该方法对灰度变化不均匀的区域进行分割的效果优于Region growing算法。     

Surface Texture Indicators of Tool Wear - A Machine Vision Approach

There has been much research on the automated monitoring of cutting tool wear. This research has tended to focus on three main areas that attempt to quantify the cutting tool condition: monitoring of specific machine tool parameters in order to infer tool condition, direct observations made on the cutting tool; and measurements taken from the chips produced by the tool. However, considerably less work has been performed on the development of surface texture sensors that provide information on the condition of the tool employed in machining the surface. A preliminary experimental study is presented for accomplishing this texture analysis using a machine vision-based sensor system. In particular, an investigation of the condition of a two-flute end mill used in a standard face milling operation is presented. The degree of tool wear is estimated by extracting three parameters from video camera images of the machined surface. The performance of three image-processing algorithms, in estimating the tool condition, is presented: analysis of the intensity histogram; image frequency domain content; and spatial domain surface texture.