基于声信号小波分析的刀具破损监测

提出了基于切削声信号的刀具破损监测方法。通过对破损声信号进行小波分析,提取出了与刀具破损具有相应关系的特征频带,去除了冲击声信号、刀具切入声信号等与刀具破损具有相似特征的声信号干扰,通过设定合适的阈值,能够较好地监测刀具的破损。这种监测方法为刀具的破损监测提供了一种新的途径。     

基于人工神经网络的铣刀破损监测

在对众多反映刀具信息的信号选取中,选择了振动信号作为研究对象.根据试验数据,对切削过程中产生的振动信号进行了分析与处理,提出了能够反映刀具破损的特征量.讨论了一种适合于变切削参数铣削加工中刀具破损的监控方法,建立了基于人工神经网络的铣刀破损振动监控仿真系统.仿真实验表明:BP网络能够有效地用于铣刀破损监控系统中.建立的刀具破损监控系统能够达到预期效果,有很好的使用价值.     

铣刀破损的声发射检测技术

用声发射技术检测铣刀破损是一项新技术。文章叙述了应用信号处理和计算机技术对铣削加工中刀具破损的声发射信号进行时频分析,进而提出在频率要350～500kHz之间检测刀具破损的方法,并介绍了由此建立的铣刀破损检测系统。图5幅。     

基于HPSO优化BP神经网络的刀具磨损状态识别

针对BP神经网络容易陷入局部极值导致识别精度低的问题,文章提出了一种基于混合粒子群算法(HPSO)的BP神经网络优化算法。在刀具磨损监测实验过程中,采集刀具切削的声发射(AE)信号,利用小波包分解算法对AE信号进行滤波,并进行特征提取。将频带能量特征和切削参数分别作为主特征和辅助特征,并对其对归一化处理。采用混合粒子群优化算法(HPSO)对BP神经网络预测模型进行优化,利用优化后的模型对测试样本进行模式识别,结果表明,优化后的HPSO-BP模型能够有效地降低神经网络陷入局部极值的情况,提高刀具磨损识别精度。     

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。     

声发射信号特征分析中的小波变换应用方法

对声发射信号进行分析与处理是目前获取声发射源信息的唯一有效途径,也是声发射技术发展的难点和瓶颈。针对声发射信号的特点,对小波变换用于声发射信号的特征分析问题进行了研究,总结出了适用于声发射信号的小波变换信号特征提取方法,并对未来小波变换在声发射领域的应用与研究方向进行了探讨。     

基于小波包分解的刀具磨损特征分析

为了高效准确地在线监测加工高温合金过程中的刀具磨损,有效地提取刀具磨损相关特征显得尤为重要。文章提出了基于小波包分解的刀具磨损特征提取方法,将刀具切削过程中的切削力信号在时频域下分解重构,分析了各频段重构信号能量值与刀具磨损的相关性,提取了信号分解重构后小波包系数能量值中与刀具磨损相关的两个频段信号作为刀具磨损监测的特征参数,最后通过试验结果表明,采用小波包分解方法在切削力信号中提取的切削力特征和切削振动特征可作为刀具磨损特征,从而为后续研究刀具磨损在线监测提供有效输入。     

基于S变换时频图纹理特征的刀具磨损状态识别

针对刀具磨损状态监测问题,将图像纹理特征提取技术引入到刀具磨损故障诊断中,提出一种基于S变换时频图纹理特征的刀具磨损状态识别方法。首先采用S变换对刀具切削过程中采集的声发射信号进行时频分析,将时频图像转换为等高线灰度图,通过灰度共生矩阵算法提取图像纹理特征;然后采用散布矩阵算法对提取的特征向量进行敏感度分析,构建敏感特征向量;最后采用敏感特征向量训练离散隐马尔科夫模型,建立分类器,从而实现刀具磨损状态的识别。实验结果表明:该方法可以有效地识别刀具磨损状态,识别率为96.67%。     

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。     

基于切削力的小波神经网络刀具磨损状态监测

为了有效地进行刀具状态监测,采用小波神经网络对刀具进行故障诊断.通过小波变换提取刀具磨损切削力信号的特征,利用小波包分解技术对信号进行分析,得到有效的特征量作为BP神经网络的输入样本,并对网络进行学习训练,完成对刀具磨损状态的有效识别.仿真结果表明该方法是有效的.     

Development of a tool failure detection system using multi-sensors

Tool monitoring and machine diagnosis in real machining have been crucial to the realization of fully automated machining. Also, the on-line detection technique of the tool breakage in machining should be supported. The effect of tool breakage is usually revealed from an abrupt change in the processed measurements, which is in excess of a threshold value. Although these techniques are generally effective for a specific cutting condition, they are often not sufficiently reliable for use in production due to the inability of single measurement to reflect tool breakage under various cutting conditions. In order to enhance the reliability of tool breakage signatures obtained from a single sensor, an integrated approach based on measurements from several sensors has been put forward. In this study, the tool breakage detection method using multi-sensors is proposed and the sensor fusion algorithm is developed to integrate and make decisions from data measured through the multisensors. Also, the performances of this scheme are compared and evaluated with real cutting process.     

数控机床加工曲面时刀具破损的小波分析

介绍小波变换思想及特点，根据傅里叶变换原理，结合刀具破损信号，分析了快速小波变换－Mallat算法。实验表明多分辨分析的方法，对于刀具破损突变信号具有精确时－频定位和易于监测的优点，能够有效处理刀具破损监控的信号。     

Detection of tool breakage in milling operations—II. The neural network approach

On-line monitoring of tool cutting conditions and tool breakage is very important for automated factories of the future. In this paper, the time series based tooth period modeling technique (TPMT) is proposed for detecting tool breakage by monitoring a cutting force or torque signal in any direction. TPMT uses the fast a posteriori error sequential technique (FAEST) for on-line modeling of cutting force or torque signals. Tool breakage is detected by evaluating variations of the characteristics of the monitored signal in each tooth period. TPMT was tested on simulated and experimental end milling data. The proposed technique detected tool breakage in all of the test cases without giving any false alarms in the transition cases.     

End milling tool breakage detection using lifting scheme and Mahalanobis distance

In this paper, a novel method based on lifting scheme and Mahalanobis distance (MD) is proposed for detection of tool breakage via acoustic emission (AE) signals generated in end milling process. The method consists of three stages. First, by investigating the specialty of AE signals, a biorthogonal wavelet with impact property is constructed using lifting scheme, and wavelet transform is carried out to separate AE components from the original signals. Second, Hilbert transform is adopted to demodulate signal envelope on wavelet coefficients and salient features indicating the tool state (i.e., normal conditions, slight breakage, and serious breakage) are extracted. Finally, tool conditions are identified directly through the recognition of these features by means of MD. Practical application results on a CNC vertical milling machine tool show that the proposed method is accurate for feature extraction and efficient for condition monitoring of cutting tools in end milling process.     

数控切削过程中的刀具破损在线监控

提出了一种数控加工过程中的刀具破损在线监控系统，并详细介绍了加工过程中用电机电流信号监测刀具破损的原理以及具体的实验方案。探讨了中断型宏指令功能在刀具破损在线监控系统中的应用。经实践证明，利用该监控系统和中断型宏指令，能够实时的识别加工过程刀具的破损，并能及时报警、自动换刀等.机床的故障停机时间大大地减少，利用率得到了很大地提高。     

Complexity measure of motor current signals for tool flute breakage detection in end milling

Automated tool condition monitoring is an important issue in the advanced machining process. Permutation entropy of a time series is a simple, robust and extremely fast complexity measure method for distinguishing the different conditions of a physical system. In this study, the permutation entropy of feed-motor current signals in end milling was applied to detect tool breakage. The detection method is composed of the estimation of permutation entropy and wavelet-based de-noising. To confirm the effectiveness and robustness of the method, typical experiments have been performed from the cutter runout and entry/exit cuts to cutting parameters variation. Results showed that the new method could successfully extract significant signature from the feed-motor current signals to effectively detect tool flute breakage during end milling. Whilst, this detection method was based on current sensors, so it possesses excellent potential for practical and real-time application at a low cost by comparison with the alternative sensors.     

Flute breakage detection during end milling using Hilbert–Huang transform and smoothed nonlinear energy operator

Real time tool condition monitoring has great significance in modern manufacturing processes. In order to prevent possible damages to the workpiece or the machine tool, reliable monitoring techniques are required to provide fast response to the unexpected tool failure. Milling is one of the most fundamental machining operations. During the milling process, the current of feed motor is weakly related to the cutter condition, the change of power consumption is not significant to identify tool condition. Thus, current of motor-based tool condition still requires some new approaches to sort out significant pattern that could be employed to indicate tool condition. In this paper, a new approach is proposed to detect end mill flute breakage via the feed-motor current signals, which implements Hilbert–Huang transform (HHT) analysis and a smoothed nonlinear energy operator (SNEO) to extract the crucial characteristics from the measured signals to indicate tool breakage. Experiments on a CNC Vertical Machining Centre are presented to show the algorithm performance. The results show that this method is feasible and can accurately and efficiently monitor the conditions of the end mill under varying cutting conditions.     

Discrete wavelet transform for tool breakage monitoring

Detection of tool breakage is of vital importance in automated manufacturing. Various methods have been attempted, and it is considered that the use of discrete wavelet transform (DWT), which is much more efficient and just as accurate wavelet analysis, may provide a realistic solution to the detection of tool breakage in operation. The DWT uses an analyzing wavelet function which is localized in both time and frequency to detect a small change in the input signals. In addition, it requires less computation than Fast Fourier Transformation (FFT). This paper discusses a tool breakage monitoring system based on DWT of an acoustic emission (AE) and an electric feed current signal using an effective algorithm. The experiment results show overall 98.5% reliability and the good real-time monitoring capability of the proposed methodology for detecting tool breakage during drilling.     

数控镗刀磨损与破损的声发射监测法

通过分析声发射传感器采集的刀具磨损状态信号,提取出反映刀具磨损状态的特征向量MFCC系数及差分系数,然后利用隐马尔可夫模型进行信号处理,建立了检测镗刀刀具状态的监测系统。实验结果表明:在刀具的正常磨损阶段,该监测系统可以实现刀具大致磨损量的预报;在刀具破损或损坏情况下,能够及时监测和预报刀具损坏状态。这种监测方法可用于实时在线监测,为刀具的磨损监测提供了一条切实可行的途径。