An effective sensor for tool wear monitoring in face milling: Acoustic emission

Acoustic Emission (AE) has been widely used for monitoring manufacturing processes particularly those involving metal cutting. Monitoring the condition of the cutting tool in the machining process is very important since tool condition will affect the part size, quality and an unexpected tool failure may damage the tool, work-piece and sometimes the machine tool itself. AE can be effectively used for tool condition monitoring applications because the emissions from process changes like tool wear, chip formation i.e. plastic deformation, etc. can be directly related to the mechanics of the process. Also AE can very effectively respond to changes like tool fracture, tool chipping, etc. when compared to cutting force and since the frequency range is much higher than that of machine vibrations and environmental noises, a relatively uncontaminated signal can be obtained. AE signal analysis was applied for sensing tool wear in face milling operations. Cutting tests were carried out on a vertical milling machine. Tests were carried out for a given cutting condition, using single insert, two inserts (adjacent and opposite) and three inserts in the cutter. AE signal parameters like ring down count and rms voltage were measured and were correlated with flank wear values (VB max). The results of this investigation indicate that AE can be effectively used for monitoring tool wear in face milling operations.     

Assessment of the effectiveness of a spindle power signal for tool condition monitoring in machining processes

Less expensive and ‘readily available’ process monitoring techniques are needed to be effective in industrial machining processes. Spindle motors on modern computer numerical control machine tools allow easy access to the monitoring of spindle power. Whilst a spindle power signal fulfils the requirements for simple process monitoring, such a signal can trigger ‘machine alarms’ when process malfunctions occur. Little analysis has been done to assess the sensitivity of a spindle power signal relative to interrupted/continuous cutting processes. This paper aims to assess the effectiveness of a spindle power signal for tool condition monitoring in three machining processes: milling, drilling and turning. Based on cutting force/torque, the cutting power was calculated and a comparison between the theoretical cutting power and the spindle power signal was performed. Tool condition monitoring using spindle power could be successful in continuous machining processes (turning and drilling), while for discontinuous machining operations (milling), the spindle power signal showed reduced sensitivity to detect small uneven events such as chipping of one tooth. The results were used to define the sensitivity limitations when using a spindle power signal for tool condition monitoring on different computer numerical control machining centres where continuous and discontinuous machining operations are performed.     

Design of Vibration Monitoring System of CNC Machine

CNC machine have a fast development and is widely used in China. Generally, CNC machine tool, includs CNC lathes and CNC milling machine. CNC machine tool is a necessary tool for machining. It plays an important role in the mechanical design and machining fields. CNC machine tool is mainly composed of two parts of the machine body and the computer control system. Mechanical equipment failures usually related information such as vibration, sound, pressure, temperature performance. CNC machine tool vibration monitoring system with piezoelectric accelerometer, the eddy current displacement sensor, signal amplifier, signal conditioning modules. We can take an advantage of the CNC machine tool vibration monitoring system for vibration monitoring and fault diagnosis of CNC machine tools.     

基于变分模态分解的关联维数及相关向量机的刀具磨损状态监测

针对刀具磨损过程中产生的非平稳性信号,提出了基于变分模态分解的关联维数及相关向量机的刀具磨损状态监测方法。首先,利用变分模态分解对采集的声发射信号进行分解,获得一系列分量;其中部分分量跟磨损状态相关,部分分量是干扰噪声。为此根据分解后分量与原信号的互信息值提取出敏感分量;利用刀具信号特点确定关联维数的时延参数和嵌入维数,计算敏感分量的关联维数并组成特征向量;最后,将刀具不同状态的特征向量输入相关向量机进行训练与测试,从而实现对刀具磨损状态的监测。实验结果表明,该方法能够有效地识别出刀具磨损过程中不同的工作状态,且分类准确率较经验模态分解好。     

Acoustic emission analysis for tool wear monitoring in face milling

Monitoring the condition of the cutting tool in any machining operation is very important since it will affect the workpiece quality and an unexpected tool failure may damage the tool, workpiece and sometimes the machine tool itself. Advanced manufacturing demands an optimal machining process. Many problems that affect optimization are related to the diminished machine performance caused by worn out tools. One of the most promising tool monitoring techniques is based on the analysis of Acoustic Emission (AE) signals. The generation of the AE signals directly in the cutting zone makes them very sensitive to changes in the cutting process. Various approaches have been taken to monitor progressive tool wear, tool breakage, failure and chip segmentation while supervising these AE signals. In this paper, AE analysis is applied for tool wear monitoring in face milling operations. Experiments have been conducted on En-8 steel using uncoated carbide inserts in the cutter. The studies have been carried out with one, two and three inserts in the cutter under given cutting conditions. The AE signal analysis was carried out by considering signal parameters such as ring down count and RMS voltage. The results show that AE can be effectively used to monitor tool wear in face milling operation.     

Identification of feature set for effective tool condition monitoring by acoustic emission sensing

In tool condition monitoring systems, various features from suitably processed acoustic emission signals are utilized by researchers. However, not all of these features are equally informative in a specific monitoring system: certain features may correspond to noise, not information; others may be correlated or not relevant for the task to be realized. This study comprehensively takes all these known signal features and aims to identify the most effective set that can give robust and reliable identification of tool condition. In this paper, the aim is investigated through feature selection, in which automatic relevance determination (ARD) under a Bayesian framework and support vector machine (SVM) are coupled together to perform this task. In tool condition monitoring, this proposed method is able to identify the worst features according to their corresponding ARD parameters and delete them. Then the effectiveness of this pruning may be evaluated by a model validation. Finally, the effective feature set in the developed tool wear recognition system is obtained. The experimental results show that the AE feature set selected through this method is more effective and efficient to recognize tool status over various cutting conditions.     

An investigation into the possibility of using surface profiles for machine tool surveillance

Surfaces generated by machine tools are the fingerprint of the machine and tool combination. Any change in the condition of either should be reflected in the component produced, especially in the nature of the component surface generated and its dimensions. This paper investigates the possibility of using this approach to monitor the condition of the machine tool in order to predict failure or deterioration in performance.     

Improved performance evaluation of tool condition identification by manufacturing loss consideration

When neural networks are used to identify tool states in machining processes, the main interest is often the recognition ability. It is usually believed that a higher classification rate from pattern recognition can improve the accuracy and reliability of tool condition monitoring, thereby reducing the manufacturing loss. Nevertheless, the two objectives are not identical in most practical manufacturing systems. The aim is to address this issue and propose a new performance evaluation function so that the recognition ability of tool condition monitoring can be evaluated more reasonably. On this basis, two kinds of manufacturing loss due to misclassification are analysed: the over-prediction caused by misclassifying the worn tool condition; and the under-prediction caused by misclassifying the fresh tool condition. By using both to calculate corresponding weights in the performance evaluation function, the potential manufacturing loss is introduced to evaluate the recognition performance of tool condition monitoring. Based on this performance evaluation function, a modified support vector machine approach with two regularization parameters is employed to learn the information of every tool state. In this support vector machine design, the effective feature set extracted from acoustic emission signals is used as inputs, and a five-fold cross-validation is used to tune the parameters. The experimental results show that the proposed method can reliably identify tool flank wear and reduce the overdue prediction of worn tool conditions and its relative loss. Experimental results show that this approach may effectively identify tool state over a range of cutting conditions and reduce the manufacturing loss in the practical industry process.     

数控机床整机动态特性评价方法

动态特性是衡量机床性能的一项重要指标,但目前并没有较好的数控机床整机动态特性评价方法。利用真实的动态切削力对数控机床进行激励,能够快速获取机床在切削力作用下的动态特性。鉴于切削参数会影响各频率成分对应的切削力幅值,基于不同工件材料和切削参数下的动态切削力,建立动态激振力模型,通过分频段激励来检验数控机床在不同频段下的动态特性。通过有限元仿真分析,判断数控机床在各个频段下的动态特性;对振动信号进行快速傅里叶变换,得到机床振动时的主要频率成分,为优化机床动态特性提供指导;对比各种动态切削力激振下不同机床的动刚度,评价不同机床动态特性的优劣。最后,通过激振试验验证了仿真结果的准确性。结果表明上述方法简单实用,能快速评价数控机床的动态特性,具有一定的实用价值。     

Evaluation method of dynamic characteristics of whole NC machine tool

The dynamic characteristics is an important index to measure the performance of machine tools.However, there is no better method to evaluate the dynamic characteristics of whole NC (numerical control) machine tool. Through the excitation of real dynamic cutting force to the NC machine tool, the dynamic characteristics of the machine tool under the action of cutting force can be quickly obtained. In view of the fact that the cutting parameters would affect the amplitude of cutting force corresponding to each frequency component, a dynamic excitation force model was established based on the dynamic cutting forces under different sample materials and cutting parameters.The dynamic characteristics of the NC machine tool in different frequency bands could be tested by frequency band excitation. Through the finite element simulation analysis, the dynamic characteristics of NC machine tool in each frequency band was judged. The main frequency components in the vibration of machine tool were obtained by fast Fourier transform of vibration signal, which could provide guidance for optimizing the dynamic characteristics of machine tool. The dynamic stiffness of different machine tools under excitation of various dynamic cutting forces was compared to distinguish which machine tool had better dynamic characteristics. Finally, the simulation results were verified by the excitation test. The results indicate that the above method is simple and practical, and can quickly evaluate the dynamic characteristics of NC machine tool, which has certain practical value.     

微细铣削振动信号特征参数的主成分分析

铣削振动是描述微细铣削加工状态的重要特征参数. 利用微小型车铣加工中心、压电加速度计和多通道电荷放大器建立了微细铣削振动测试系统,分别提取了不同铣削方式和铣削转速条件下微细铣削振动信号的时域特征参数和频域特征参数. 针对特征参数数量繁多且变化趋势不一致的特点,引入主成分分析方法,利用主成分分别对时域和频域特征参数进行替换,定量描述出振动信号的能量和差异,以及主频带位置和能量分散程度之间的关系. 分析结果表明,通过时域与频域特征参数主成分的综合运用,应用较少的参数即可描述微细铣削振动信号的主要特征,显著降低了原始数据维数; 主成分分析结果可用于铣削方式和铣削转速等微细铣削加工参数的优化.     

EMD趋势分析方法及其应用研究

趋势分析是一种重要的设备状态监测与故障诊断方法,对分析较长时间范围内设备运行状态的变化具有重要意义。研究了一种基于经验模式分解（Empirical Mode Decomposition,EMD）的设备运行状态趋势分析方法。研究表明,与传统方法（如最小二乘法、低通滤波法）相比,经验模式分解能够更准确地提取信号趋势信息。应用于某炼油厂透平烟机故障诊断,表明这种基于经验模式分解的趋势分析方法能够有效提取设备运行趋势信息,消除采样中随机因素的影响,为准确评估设备运行状态、诊断故障提供可靠依据,具有重要的现场实用价值。     

基于奇异值分解和灰靶决策的车刀磨损状态判别

针对随机噪声干扰车刀磨损振动信号时域特征提取,车刀磨损判别精度不高的问题,提出一种通过小波包变换和相关系数法提取车刀振动信号的磨损时域特征,采用奇异值分解对磨损时域特征进行去噪处理,去噪处理后获取磨损时域特征。选取与车刀磨损最相关的磨损特征作为参考特征序列,计算参考特征序列与其余磨损特征序列之间的相似关联度,对相似关联度归一化处理得到各磨损时域特征的权值,使用灰靶决策计算各磨损时域特征的综合测度,确定车刀磨损状态。实验结果表明:该方法可以有效地滤除随机噪声干扰。     

Experimental Study of the Tool Wear During the Electrochemical Discharge Machining

Electrochemical discharge machining is a nonconventional machining method which can be used to machine nonconductive materials such as glass and ceramics. However, machining of the refractory materials such as ceramics requires high voltages to produce the required thermal energy. In this condition, the tool wear would be increased significantly. This paper reports the study of the wear of the different tool materials. The selected tool materials have different melting/boiling temperatures responding to the high voltages in different ways. The possibility of using different tool materials in high voltages along with estimation of tool surface temperature is discussed in this paper.     

GPIB激光自动测径系统及逻辑分析仪的应用

激光测径仪可以对被测的直径进行精确地测量，但被测物所处的环境条件如灰尘、蒸汽等都会影响测量的精确性。本文介绍了一种基于GHB接口的激光测径自动测试系统，用于采集激光测径仪在各种干扰条件下的测量信号，并利用计算机对获得的数据进行处理，从而消除环境对测量结果精确性的影响，另外重点介绍了系统中逻辑分析仪的使用。     

高速激光切割机床数控加工态势识别系统

当前方法设计的系统对机床数控加工态势进行识别时,没有对噪声进行回放,对切割平面度、切割定位精度、机床平稳性进行识别时,识别结果不准确,存在识别准确率低的问题。该文提出高速激光切割机床数控加工态势识别系统设计方法,首先,通过运动控制卡,伺服控制模块及加工态势识别模块构成高速激光切割机床数控加工态势识别系统的架构;其次,在加工态势识别模块中设计系统初始化、态势识别、自动诊断报警、运动控制、图形转码和G代码编译等子模块,在此基础上,通过噪音采集、噪音回放和信号分析等方法提高加工态势识别的准确率;最后,采用HMM算法构建高速激光切割机床数控加工态势识别模型,实现加工态势识别。实验结果表明,加工态势设计方法设计的系统可有效识别机床的切割平面度、切割定位精度和机床平稳性,识别准确率较高。     

Life Prediction Model of Machine Tool based on Deep Learning

In view of the shortage of traditional life prediction methods for machine tools, such as low accuracy of life prediction and few samples basis attributes, a life prediction model of machine tools combined with machine tool attributes is proposed. The life prediction model of machine tool adopts KL dispersion distribution theory, uses modal superposition method to carry out machine tool life analysis, calculates the theoretical life of machine tool, and then carries on the simulation, obtains the machine tool life prediction value. Compared with the traditional method of machine tool life prediction, the model is based on the application life fatigue damage model, which superimposes the service times and maintenance cycle of the machine tool, derives the influence factor of machine tool life, and obtains the linear relationship between the influence factor of machine tool life and the life of machine tool. The influence factor of machine tool life is introduced as the life prediction parameter of machine tool. The data transformation relationship of HT300 parts is constructed. The original part data is enhanced. The effective training set is obtained. The life prediction model of machine tool based on deep learning is completed. The quantitative analysis of machine tool life is carried out. The experiment of machine tool life prediction using training data set proves the validity of the model. Regression test was carried out on the training data set to reflect the robustness of the model. The prediction accuracy of the model is further verified by Weibull test.     

基于似然比检验原理的机床切削颤振早期监测

根据似然比检验原理提出了一种新的机床切削颤振监测统计量，能识别切削过程中产生的信噪比为０．１５的微弱振动成份。文章还就颤振监测工作特性、颤振监测门限值设置等有关问题进行了分析讨论。颤振监测考证试验在一台数控车床上进行。     

基于增量分析法的机床薄弱模块识别方法及应用

串联式机床整机的刚度受到刚度最小的薄弱模块的制约.为了提高机床整机的刚度,提出了一种新的机床薄弱模块识别方法.首先,利用模块化设计方法对机床进行模块划分.然后,将包含主轴的最小模块作为基础模块,逐一添加同一串联结构中的模块,通过分析添加某个模块后结构变形量的增量来确定机床的薄弱模块.最后,对识别出的薄弱模块进行结构改进...     

精密机床主轴轴承的预紧力控制

 以FL-1000型精密磨床主轴系统为对象,设计了一种精密机床主轴轴承预紧力实时控制系统.根据实际工况,确定该机床的最佳预紧力,对其控制原理和控制算法的设计进行了分析,并以FL-1000型精密磨床主轴系统为例验证了预紧力实时控制的可行性.