一种铣刀磨损在机立体视觉测量系统

实现刀具磨损在机测量是解决自动化制造中确定最佳换刀时间的一个重要问题。介绍了铣床刀具磨损的在机三维测量方法,并结合铣床的实际情况,设计制造了一种灵巧的双目相机夹持与调节机构,搭建了一套铣刀磨损在机立体视觉测量系统。实验结果表明:该系统能够获得较为清晰的铣刀磨损区图像对,为进一步实现刀具磨损的在机三维测量奠定了基础。     

刀具磨损便携式视觉在位检测技术研究

简要分析了目前常用刀具的磨损测量方法,提出一种便携式在位测量方法。该方法将小型光学镜组直接夹持在手机上,与手机摄像头一起组成便携式视觉检测系统,对安装在机床上的刀具磨损区域进行拍摄取样,然后将图像传输到电脑中,经图像处理后可获得刀具后刀面磨损量。试验表明,该测量方法操作简单,测量精度符合工程要求;可实现刀具磨损的在位检测,为刀具磨损的过程监测提供新途径。     

可调式检验芯轴

针对机床上孔径检测过程中芯轴外径的磨损,提出了一种可以根据磨损情况随时调节外径的芯轴结构.     

联机刀具磨损的测定

由Kennametal公司的研究报告可知,如果在机床上配备联机刀具磨损测量系统,机加成本可降低40％。为此,联机的刀具磨损测定装置的开发受到了广泛的重视。测定装置的核心是传感系统,现在各种传感系统已相继出现。 1.间接磨损测定法在通过测试切削阻力检测刀具磨损方面,Sandvik公司开发了测试进给方向阻力的     

基于机器视觉的立铣刀磨损检测方法研究

针对传统立铣刀视觉检测流程中图像定位及利用圆弧拟合边缘不精确的问题,提出一种垂直分布的双镜头视觉检测方法,开发了一套加工中心立铣刀机器视觉检测系统。在自适应阈值分割及边缘检测算法的基础上,通过筛选及合并共线轮廓,拟合直线获取端面刀刃偏转角度,驱动电动机精确定位后采集铣刀侧面图像。基于立铣刀投影几何模型复原侧面轮廓,在侧面摄像头所获取的图像上拟合原轮廓曲线,结合区域求差算法计算出磨损参数及位置信息。实验表明,此检测方法可以精确拟合圆周刃轮廓,提取磨损缺陷区域,检测精度达到0.01 mm,实现了加工中心立铣刀在位检测。     

刀具磨损的机器视觉监测研究

为提高铣削加工时的刀具利用率、降低刀具成本,提出采用机器视觉技术在机监测铣刀磨损状态,及时更换刀具。建立刀具磨损监测系统,由电荷耦合器件(Charge coupled device,CCD)相机获取刀具磨损图像,通过图像预处理、阈值分割、基于Canny算子和亚像素的边缘检测方法建立刀具磨损边界,提取刀具磨损量。开展GH4169镍基高温合金铣削实验,将监测系统检测的磨损量与超景深显微镜的测量结果进行比对,结果表明:该系统具有较高的检测精度,可实现铣削加工时刀具磨损状态的在机监测。     

微型铣刀在位检测方法及系统设计

针对现有计算机视觉测量设备在刀具检测领域的应用现状和不足,结合微型铣刀的磨损特点和微型机床的结构,提出了一种基于计算机视觉的微型铣刀在位检测方法。通过机械手夹持光学成像系统的方法对微型铣刀的刀尖高度、刀具直径、副后刀面面积、前角和后角进行在位检测,特别强调了使用线性激光投影变换的方法测量前角、后角,最后介绍了系统软件、硬件设计并通过实验验证了系统检测效果。     

刀具磨损状况的检测方法研究综述

刀具磨损状况的有效检测不仅能提高刀具本身的利用率,还能提高工件的加工精度,延长机床的使用年限。刀具磨损状况的准确检测是当前智能加工技术的主要发展方向,通过回顾近年来刀具磨损状况的检测方法,着重分析了检测信号的获取、特征提取及模式识别等关键技术,并由此提出了一种可操作性强、不影响机床加工的刀具磨损状况智能检测新方法。最后,针对刀具磨损状况的检测应用现状和存在不足进行了探讨,并对未来的智能检测方法发展方向进行了展望,以期得到更好的刀具磨损状况智能检测方法,促进刀具磨损状况检测技术在智能装备中的应用与推广。     

断刀检测及刀具磨损自动补偿技术研究

数控(CNC)机床加工过程中会出现断刀和刀具磨损的情况,严重影响产品生产效率和质量。传统切削是通过操作者来判断刀具是否断刀和磨损,既影响生产效率又浪费人力。而在自动化普及的今天,传统切削远远不能满足机床加工对效率和质量的要求,须通过自动检测来实现断刀检测和刀具磨损的自动补偿。     

刀具磨损状态检测方法的分析与验证

为监测机床刀具磨损程度,提出了一种基于小波包理论(WPD)、经验模态分解(EMD)以及支持向量机(SVM)等相结合的刀具故障诊断方法。通过小波包理论工具消除刀具的高频噪声信号,并对去噪后的信号进行模态分解、合成,计算出模态函数(IMF)和EMD分解信号的相关参数。将计算出的信号时域上的特征参数作为支持向量机(SVM)的输入特征向量,完成对刀具故障的检测。实验结果分析表明,该方法可以有效地判断刀具磨损程度,验证了方法的可行性。     

On-machine tool prediction of flank wear from machined surface images using texture analyses and support vector regression

In this paper, a method for on-machine tool condition monitoring by processing the turned surface images has been proposed. Progressive monitoring of cutting tool condition is inevitable to maintain product quality. Thus, image texture analyses using gray level co-occurrence matrix, Voronoi tessellation and discrete wavelet transform based methods have been applied on turned surface images for extracting eight useful features to describe progressive tool flank wear. Prediction of cutting tool flank wear has also been performed using these eight features as predictors by utilizing linear support vector machine based regression technique with a maximum 4.9% prediction error.     

Tool condition classification in turning process using hidden Markov model based on texture analysis of machined surface images

Tool condition monitoring has found its importance to meet the requirement of production quality in industries. Machined surface texture is directly affected by the extent of tool wear. Hence, by analyzing the machined surface images, the information about the cutting tool condition can be obtained. This paper presents a novel technique for tool wear classification using hidden Markov model (HMM) technique applied on the features extracted from the gray level co-occurrence matrix (GLCM) of machined surface images. The tool conditions are classified into sharp, semi-dull and dull tool states. The proposed method is found to be cost effective and reliable for on-machine tool classification of cutting tool wear with an average of 95% accuracy.     

Optimal design of electrode cooling system for resistance spot welding with the response surface method

In the last decade, the progress of surface metrology has led to improved 3D characterisation of surfaces, offering the possibility of monitoring manufacturing operations and providing highly detailed information regarding the machine tool condition. This paper presents a case study where areal surface characterisation is used to monitor tool wear in peripheral milling. Due to the fact that tool wear has a direct effect on the machined workpiece surface, the machined surface topography contains much information concerning the machining conditions, including the tool wear state. By analysing the often subtle changes in the surface topography, one can highlight the tool wear state. This paper utilises areal surface characterization, areal auto-correlation function (AACF) and pattern analysis to illustrate the effect of tool wear on the workpiece surface. The result shows the following: (1) tool wear, previously difficult to detect, will influence almost all of the areal surface parameters; (2) the pattern features of AACF spectrum can reflect the subtle surface texture variation with increasing tool wear. The authors consider that, combined analysis of the surface roughness and its AACF spectrum are a good choice for monitoring the tool wear state especially with the latest developments in on-machine surface metrology.     

Knife-edge interferometry for cutting tool wear monitoring

This paper presents a novel technique for more easily measuring cutting tool wear using knife-edge interferometry (KEI). Unlike an amplitude splitting interferometry, such as Michelson interferometry, the proposed KEI utilizes interference of a transmitted wave and a diffracted wave at the cutting tool edge. In this study, a laser beam was incident on the cutting tool edge, and the photodetector was used to determine the interference fringes by scanning a cutting tool edge along the cutting direction. The relationship between the cutting tool wear and interferometric fringes generated by edge diffraction phenomena was established by using the cross-correlation of KEI fringes of two different cutting tool-edge conditions. The cutting tool wear produced the phase shift (attrition wear) and the decay of oscillation (abrasive wear) in the interferometric fringe. The wear characteristics of the cutting tool with a radius of curvature of 6 mm were investigated by measuring the interferometric fringes of the tool while cutting an aluminum work piece in a lathe. As a result, the attrition and abrasive wear of cutting tool showed a linear relationship of 5.62 lag/wear (μm) and 1.14E-3/wear (μm), respectively. This measurement technique can be used for directly inspecting the cutting tool wear in on-machine process at low-cost.     

On-machine precision preparation and dressing of ball-headed diamond wheel for the grinding of fused silica

In the grinding of high quality fused silica parts with complex surface or structure using ball-headed metal bonded diamond wheel with small diameter,the existing dressing methods are not suitable to dress the ball-headed diamond wheel precisely due to that they are either on-line in process dressing which may causes collision problem or without consideration for the effects of the tool setting error and electrode wear.An on-machine precision preparation and dressing method is proposed for ball-headed diamond wheel based on electrical discharge machining.By using this method the cylindrical diamond wheel with small diameter is manufactured to hemispherical-headed form.The obtained ball-headed diamond wheel is dressed after several grinding passes to recover geometrical accuracy and sharpness which is lost due to the wheel wear.A tool setting method based on high precision optical system is presented to reduce the wheel center setting error and dimension error.The effect of electrode tool wear is investigated by electrical dressing experiments,and the electrode tool wear compensation model is established based on the experimental results which show that the value of wear ratio coefficient K’ tends to be constant with the increasing of the feed length of electrode and the mean value of K’ is 0.156.Grinding experiments of fused silica are carried out on a test bench to evaluate the performance of the preparation and dressing method.The experimental results show that the surface roughness of the finished workpiece is 0.03 μm.The effect of the grinding parameter and dressing frequency on the surface roughness is investigated based on the measurement results of the surface roughness.This research provides an on-machine preparation and dressing method for ball-headed metal bonded diamond wheel used in the grinding of fused silica,which provides a solution to the tool setting method and the effect of electrode tool wear.     

恒定加工条件及定期补偿下的刀具渐变可靠性灵敏度分析方法

据统计,由刀具失效导致的停机时间超过机床被迫停机时间的1/3,故开展刀具渐变可靠性及其灵敏度分析的研究对提高机床的运行可靠性具有重要意义。采用连续时间、连续状态、具有非减独立增量的非平稳Gamma过程描述刀具磨损量的变化过程。根据加工偏差不大于机床给定加工精度的原则,构建刀具制造及磨损量检测有无误差两种情形下、恒定加工条件及定期补偿的刀具渐变状态函数,由此推导出相应的渐变可靠度模型。在此基础上给出渐变可靠度模型对各个参数的灵敏度计算方程。通过数值实例分析,阐述了通过提出的渐变可靠性模型及灵敏度分析方法提高刀具运行可靠性的应用过程。这一工作为提高恒定加工条件及定期补偿下刀具的运行可靠性提供切实可行的理论和方法基础。     

Image edge detection based tool condition monitoring with morphological component analysis

The measurement and monitoring of tool condition are keys to the product precision in the automated manufacturing. To meet the need, this study proposes a novel tool wear monitoring approach based on the monitored image edge detection. Image edge detection has been a fundamental tool to obtain features of images. This approach extracts the tool edge with morphological component analysis. Through the decomposition of original tool wear image, the approach reduces the influence of texture and noise for edge measurement. Based on the target image sparse representation and edge detection, the approach could accurately extract the tool wear edge with continuous and complete contour, and is convenient in charactering tool conditions. Compared to the celebrated algorithms developed in the literature, this approach improves the integrity and connectivity of edges, and the results have shown that it achieves better geometry accuracy and lower error rate in the estimation of tool conditions.     

Hybrid Learning for Tool Wear Monitoring

In automated manufacturing systems such as flexible manufacturing systems (FMSs), one of the most important issues is the detection of tool wear during the cutting process. This paper presents a hybrid learning method to map the relationship between the features of cutting vibration and the tool wear condition. The experimental results show that it can be used effectively to monitor the tool wear in drilling. First, a neural network model with fuzzy logic (FNN), responding to learning algorithms, is presented. It has many advantageous features, compared to a backpropagation neural network, such as less computation. Secondly, the experimental results show that the frequency distribution of vibration changes as the tool wears, so the r.m.s. of the different frequency bands measured indicates the tool wear condition. Finally, FNN is used to describe the relationship between the characteristics of vibration and the tool wear condition. The experimental results demonstrate the feasibility of using vibration signals to monitor the drill wear condition.     

Characterization of Tool Wear Measurement with Relation to the Surface Roughness in Turning

In turning, an accurate gauging of tool wear condition is an essential part of process control due to adverse effects on dimensional tolerance and surface finish quality. When the surface roughness is the primary concern, the conventional measure of tool wear is found to be imprecise because it provides very little information on the wear patterns in tool nose and flank. A tool wear model, developed in this study, represents the wear condition more comprehensively and accurately with relation to the surface roughness. Experimental results validate the model, showing 92% accuracy between the predicted surface roughness and the actual measurements.