基于小波包系数与隐马尔科夫模型的刀具磨损监测

在机械自动化加工中,为了防止刀具损坏,刀具磨损过程的监测是非常重要的。然而,由于加工过程的复杂性,对刀具磨损状态的监测十分困难。提出了一个基于小波包系数与隐马尔科夫模型的刀具磨损监测方法。将加工信号在不同频带上小波包系数的均方根值作为特征观测向量,即为隐马尔科夫模型的输入,并用隐马尔科夫模型模式识别方法识别刀具磨损状态。实验结果显示,提出的方法对刀具磨损状态具有很高的识别率。     

基于小波神经网络的刀具状态监测

建立了一种小波基函数神经网络的切削刀具磨损状态监测系统。通过提取反映刀具磨损状态的特征参数：声发射，主功率，进给电流为输入信号，利用Morlet解析小波神经网络的非线性模型，获得表示刀具磨损状态的特征量，来实现刀具磨损状态在线智能监测。它可以有效地提高系统识别的精确度和可靠性。     

基于声发射信号的振动钻削刀具磨损状态监测试验研究

针对钻削加工时难以直接观察刀具磨损状态的问题,基于声发射采集系统设计了超声轴向振动钻削刀具磨损状态监测装置,并在7075铝板上进行超声振动钻削试验。分析刀具磨损状态对声发射信号RMS值的影响,并通过小波分解技术对比分析刀具在不同磨损状态下的声发射信号变化规律;根据声发射信号对刀具磨损状态进行实时监测。试验结果表明:声发射信号的RMS值与刀具的磨损程度呈正相关;通过小波分解可知,随着刀具磨损的增加,信号的能量逐渐由低频段向高频段转移,可以通过监测声发射信号RMS值与能量的变化实现刀具磨损状态的有效识别。     

基于声信号HMM的刀具磨损程度分级识别

为有效地实时在线监测刀具的磨损状态，提出了基于声音识别技术的刀具磨损监测方法，进行了基于切削声信号HMM的刀具磨损程度的分级识别，监测系统能够对刀具的五级磨损划分进行准确识别，这为刀具的磨损监测提供了一条切实可行的途径。     

加工过程中刀具切削力的监测（上）

自动化加工的不断发展,要求在切削过程中有一个刀具自动监测系统,以便使切削加工不依赖操作者而自动进行。这个系统应能及时探测到刀具的损坏,并能迅速给控制机构发出信号,以避免损坏机床与工件。类似的用于监视刀具耐用度的系统,应能探测出刀具是否磨损到预先给定的极限值,从而最大限度地减少换刀次数,防止刀具过度磨损带来的诸如尺寸超差、光洁度变差、刀具易损坏等一系列问题.文章讨论了一项利用进给力和径向分力信号监测刀具破损和磨损的研究成果。全文分三期刊载,第—部分主要介绍了刀具耐用度极限的监测,讨论了监测决策、测点选择以及以微机为基础监测设备的结构和功能;第二部分介绍了刀具破损的快速识别;第三部分讨论了压电传感器的结构、功能及安装.全文图16幅。     

五轴铣削加工刀具磨损状态监测研究

随着加工零件的日益复杂,加工要求的不断提高,实际加工时的刀具状况已经成为限制加工质量进一步提高的重要因素.在五轴铣削加工时为了更好的监测刀具的磨损状况,文章对目前的刀具监测方法进行了分析,并建立了五轴铣削加工时平头立铣刀磨损状态监测系统.最后通过实验提出了用刀具的径向力与切向力比值作为监测刀具磨损状态的方法.     

基于变频器输入电流的刀具磨损状态监测系统设计与实现

为了使电流信号监测刀具磨损状态的可靠性提高。首先研究了变频器输入电流与刀具磨损状态的相关性,并根据电流有效值定义提出一种计算变频器输入侧线电流的方法。结合该方法分析软件和硬件的需求后,采用工业控制计算机主板、USB-4711A采集卡以及霍尔电流传感器搭建硬件平台,以Qt作为软件开发框架,设计研发了一套在线刀具磨损状态实时监测系统。该系统可应用于多种数控机床设备。经实验验证,该系统能够反映刀具磨损状态,及时发出更换刀具提醒。     

无先验知识下基于CHMM的刀具磨损监测技术

切削刀具的状态直接影响工件加工质量、生产率和产品成本,因此在切削加工过程中监测刀具的状态显得尤为重要。针对实际监测系统通常无法获取刀具各磨损退化状态先验知识的情况,以切削力与切削振动为监测信号,提出无先验知识下基于小波包分析与连续隐马尔可夫模型的刀具磨损监测技术。应用小波包分析技术提取信号特征信息,采用S函数实现特征值归一化处理。利用监测过程中的刀具正常状态下归一化特征信息建立基于连续隐马尔可夫模型的监测模型;根据刀具未知状态特性向量与监测模型间的对数似然度获取刀具性能指标PV,实现刀具磨损状态评价。采用铣刀磨损全寿命数据来验证该方法的有效性,实验结果表明:该方法能在无先验知识的情况下对刀具的健康状态进行较为准确的评估,且所需样本数较少,训练速度快。该技术对实现无先验知识下的刀具智能化在线状态监测具有重要意义。     

加工过程中的刀具破损报警装置

在机床或自动线上 ,刀具损坏或磨损的检测报警 ,通常是在加工后或机床开始加工前 ,通过测量装置对刀具进行比较 ,发出信号 ,判别刀具是否正常、损坏或磨损 ;但在加工过程中 ,对于回转刀具 ,要及时发现刀具损坏、磨损 ,通常采用电机过载来判断 ,这种报警方式极不准确 ,当过载参数设置较大时 ,刀具可能已损坏或磨损 ,报警装置却不报警 ;过载参数设置较小时 ,刀具可能没有损坏、磨损 ,由于工件材质硬度或其它因素变化 ,如刀具磨钝 ,切削功率增大 ,达到设定值 ,而产生误报 ,使机床报警处于不可靠状态。上述报警方法不能满足需要。现我们为南阳红…     

基于迁移学习与残差网络的刀具磨损状态监测

针对现有基于深度学习的刀具磨损状态监测方法训练样本少、识别精度低的问题，建立基于迁移学习（TL）与深度残差网络(ResNet)的铣刀磨损状态监测模型。将刀具加工过程中的振动监测信号通过连续小波变换转换成能量时频图，作为网络模型的输入；将在ImageNet数据集上训练的ResNet50模型作为预训练模型，通过迁移学习的方法，应用到刀具磨损状态监测领域当中。实例验证表明:TL-ResNet模型的平均识别准确率达到98.52%，实现了刀具不同磨损状态下的智能识别，有效提高了刀具磨损状态监测的准确性和稳定性。     

Application of statistical filtering for optical detection of tool wear

The application of automated tool condition monitoring systems is very important for unmanned machining systems. Tool wear monitoring is a key factor for optimization of the cutting processes. Basically, tool wear monitoring systems can be subdivided into two classes: direct and indirect. Currently direct tool wear monitoring systems are most frequently based on machine vision by camera. Several approaches have been studied for tool wear detection by means of tool images, and an innovative statistical filter proved to be very efficient for worn area detection. A new approach has been implemented and tested in order to develop an automatic system for tool wear measurement. This new approach is described in this paper and the main topics related to tool wear monitoring using wear images have been discussed.     

机床线性轴与导轨局部和非局部磨损产生的根本原因分析

机床线性轴需要使用在线检测方法,提供系统运行实时反馈的相关参数信息,从而了解和预测机床的性能,所以惯性测量单元(IMU)线上状态监测具有相当高的研究价值。提出基于空间滤波器的方法,通过IMU测量的运动误差来确定直线导轨的磨损情况,从而解决导轨磨损引起的平移和角度误差的变化问题,精度可以达到1.5μm和3.0μrad。主要阐述两种运动轨迹误差的跟踪方法:第一种是确定导致运动误差的导轨位置;第二是确定每条导轨非局部损坏的根本原因。这些方法有利于智能机床的优化开发,为实现机床精密控制提供可靠的理论依据。     

An overview of approaches to end milling tool monitoring

The increase in awareness regarding the need to optimise manufacturing process efficiency has led to a great deal of research aimed at machine tool condition monitoring. This paper considers the application of condition monitoring techniques to the detection of cutting tool wear and breakage during the milling process. Established approaches to the problem are considered and their application to the next generation of monitoring systems is discussed. Two approaches are identified as being key to the industrial application of operational tool monitoring systems.Multiple sensor systems, which use a wide range of sensors with an increasing level of intelligence, are seen as providing long-term benefits, particularly in the field of tool wear monitoring. Such systems are being developed by a number of researchers in this area. The second approach integrates the control signals used by the machine controller into a process monitoring system which is capable of detecting tool breakage. Initial findings mainly under laboratory conditions, indicate that both these approaches can be of major benefit. It is finally argued that a combination of these approaches will ultimately lead to robust systems which can operate in an industrial environment.     

An approach based on current and sound signals for in-process tool wear monitoring

This paper presents a tool condition monitoring system (TCMS) for on-line tool wear monitoring in turning. The proposed TCMS was developed taking into account the necessary trade-off between cost and performance to be applicable in practice, in addition to a high success rate. The monitoring signals were the feed motor current and the sound signal. The former was used to estimate the feed cutting force using the least squares version of support vector machines (LS-SVM). Singular spectrum analysis (SSA) was used to extract information correlated with tool wear from the sound signal. The estimated feed cutting force and the SSA decomposition of the sound signal alone with the cutting conditions constitute the input data to the TCMS. Again LS-SVM was used to estimate tool condition and its reliability for on-line implementation was validated by experiments using AISI 1040 steel. The results showed that the proposed TCMS is fast and reliable for tool condition monitoring.     

Calibrated method for ultrasonic on-line monitoring of gradual wear during turning operations

On-line tool condition monitoring is essential for modern machining systems, especially in the case of precision and unmanned machining. Knowledge of the condition and the expected life of the tool are very important inputs for determining the optimal machining parameters. Previous efforts have indicated that ultrasonic gaging methods can be used to directly measure in-process gradual tool wear during turning operations. Good correlation was shown between the level of gradual wear and the ultrasonic signals. However, the correlation was tool dependent. This was mainly attributed to variations in the tool materials and inconsistent coupling of the transducer to the tools. This paper describes a robust method for on-line gradual wear monitoring using normalized ultrasonic signals. A consistent calibration mark, cut in the lower comer of the tool nose, is used to generate a calibration echo. The calibration echo is affected by the same variations as that of the gradual wear and is used to normalize the nose and flank echoes. Experiments under various cutting conditions showed that the gradual wear measurements can be made tool independent by normalizing the measurements with the calibration mark. In addition, the variations in the signals which were previously reported are also eliminated.     

Evaluation of wear of turning carbide inserts using neural networks

Recent trends, being towards mostly unmanned automated machining systems and consistent system operations, need reliable on-line monitoring processes. A proper on-line cutting tool condition monitoring system is essential for deciding when to change the tool. Many methods have been attempted in this connection.Recently, artificial neural networks have been tried for this purpose because of its inherent simplicity and reasonably quick data-processing capability. The present work uses the back propagation algorithm for training the neural network of 5-3-1 structure. The technique shows close matching of estimation of average flank wear and directly measured wear value. Thus the system developed demonstrates the possibility of successful tool wear monitoring on-line.     

Real time implementation of on-line tool condition monitoring in turning

This paper describes a real-time tool condition monitoring system for turning operations. The system uses a combination of static and dynamic neural networks with off-line and on-line training and cutting force components are used as diagnostic signals. The system is capable of monitoring several wear components simultaneously. The wear estimation system has been implemented experimentally to evaluate its suitability for use in shop floor conditions. The tests were performed in real time with different cutting conditions. The experimental results showed that the system was successful in predicting three wear components in real time. However, the accuracy of the wear prediction was not the same for all three wear components. The crater wear predictions were less accurate partly because of the opposing effects of crater and flank wear components on cutting force components.     

Development of an on-line tool-life monitoring system using acoustic emission signals in gear shaping

Sensing techniques for monitoring machining processes have been one of the focuses of research on process automation. This paper presents the development of on-line tool-life monitoring system for gear shaping that uses acoustic emission (AE). Characteristics of the AE signals are related to the cutting condition, tool material and tool geometry in the cutting of metals. The relationship between AE signal and tool wear was investigated experimentally. Experiments were carried out on the gear shaping of SCM 420 material with a pinion cutter having 44 teeth. Root-mean-square (RMS) AE voltages increase regularly according to tool wear. It is suggested that the maximum value of RMS AE voltage is an effective parameter to monitor tool life. In this study, not only the acquisition method of AE signals for rotating objects but also the signal-processing technique were developed in order to realize the in-process monitoring system for gear shaping. The on-line tool-life monitoring system developed has been successfully applied to gear machining processes.     

Tool wear condition monitoring in drilling operations using hidden Markov models (HMMs)

Monitoring of tool wear condition for drilling is a very important economical consideration in automated manufacturing. Two techniques are proposed in this paper for the on-line identification of tool wear based on the measurement of cutting forces and power signals. These techniques use hidden Markov models (HMMs), commonly used in speech recognition. In the first method, bargraph monitoring of the HMM probabilities is used to track the progress of tool wear during the drilling operation. In the second method, sensor signals that correspond to various types of wear status, e.g., sharp, workable and dull, are classified using a multiple modeling method. Experimental results demonstrate the effectiveness of the proposed methods. Although this work focuses on on-line tool wear condition monitoring for drilling operations, the HMM monitoring techniques introduced in this paper can be applied to other cutting processes.     

An active method of monitoring tool wear states by impact diagnostic excitation

This paper presents an active method of monitoring tool wear states by using impact diagnostic excitation in the machining process. Because the dynamic characteristics of tool vibration in machining process will change with the tool wear development, the damping ratio, which is one of the important dynamic characteristics of tool vibration, will be used for monitoring the tool wear states in machining. In order to obtain the damping ratio, impact diagnostic excitation was applied to the tool in the feed direction and the signals of the tool vibration were measured for some flank wears under different cutting conditions. The signals were analyzed through FFT analyzer and computer, and then the damping ratio of the tool vibration in the feed direction was calculated. The experimental results have shown that the damping ratio measured by impact excitation increases linearly with tool wear development and the increment of the damping ratio is different for each cutting condition, but the damping ratio can be uniquely determined through the flank worn area. To explain the reason for increase with tool wear development, the damping mechanism on the flank worn land was also discussed. The results of the discussions and numerous cutting experiments have indicated that the presented active method could be used for effectively monitoring the tool wear states in machining.