Multi-category micro-milling tool wear monitoring with continuous hidden Markov models

In-process monitoring of tool conditions is important in micro-machining due to the high precision requirement and high tool wear rate. Tool condition monitoring in micro-machining poses new challenges compared to conventional machining. In this paper, a multi-category classification approach is proposed for tool flank wear state identification in micro-milling. Continuous Hidden Markov models (HMMs) are adapted for modeling of the tool wear process in micro-milling, and estimation of the tool wear state given the cutting force features. For a noise-robust approach, the HMM outputs are connected via a medium filter to minimize the tool state before entry into the next state due to high noise level. A detailed study on the selection of HMM structures for tool condition monitoring (TCM) is presented. Case studies on the tool state estimation in the micro-milling of pure copper and steel demonstrate the effectiveness and potential of these methods.     

深孔加工刀具状态监测的研究

通过应变式传感器和振动传感器采集力与水平振动信号 ,提取了切削力信号的四阶中心矩和水平振动信号的特征频率谱峰 ,并将模式识别技术应用于刀具状态监测 ,利用感知器算法得到刀具状态的分类函数进行刀具状态识别 ;试验结果表明 ,该方法具有较高的识别精度和较强的抗干扰能力     

A statistical filtering method for denoising of micro-force measurements

Precise measurement of mechanical forces is crucial to efficient micro-manufacturing. The quality of such measurements depends heavily on the properties of the noise inevitably accompanying every measurement process. In the micro-range, the signal-to-noise ratio tends to be very low, and the noise dynamic varies for different frequencies. In result, common denoising methods that assume white noise perform poorly in this setting. In this paper, a novel, easily implementable denoising method based on a local statistic of the measured data’s spectrum is proposed. By testing it on a representative dataset, it is shown that the proposed method is robust and stable. Particularly, it allows for an efficient retrieval of the force signal encountered in micro-milling processes.     

CHMM for tool condition monitoring and remaining useful life prediction

To solve the problems of tool condition monitoring and prediction of remaining useful life, a method based on the Continuous Hidden Markov Model (CHMM) is presented. With milling as the research object, cutting force is taken as the monitoring signal, analyzed by wavelet packet theory to reduce noise and extract the energy feature of the signal as a basis for diagnosis. Then, CHMM is used to diagnose tool wear state. Finally, a Gaussian regression model is proposed to predict the milling tool’s remaining useful life after the test sample data are verified to be consistent with the Gaussian distribution based on a reliable identification of the milling tool wear state. The probability models of tool remaining useful life prediction could be established for tools with different initial states. For example, when an unknown state of milling force signal is delivered to the milling tool online diagnostic system, the state and the existing time of this state could be predicted by the established prediction model, and then, the average remaining useful life from the present state to the tool failure state could be obtained by analyzing the transfer time between each state in the CHMM. Compared to the traditional probabilistic model, which requires a large amount of test samples, the experimental cost is effectively reduced by applying the proposed method. The results from the experiment indicate that CHMM for tool condition monitoring has high sensitivity, requires less training samples and time, and produces results quickly. The method using the Gaussian process to accurately predict remaining life has ample potential for application to real situations.     

Detection of signal transients using independent component analysis and its application in gearbox condition monitoring

This paper addresses feature extraction of the higher-order statistics, which can effectively characterize the transients, using independent component analysis (ICA) for the one-dimensional measured vibration signal, and then proposes a novel automatic technique for detecting the transients in vibration signals with the low signal-to-noise ratio by ICA feature extraction. The basic principle of the ICA-based transient detection method is that the independent components (ICs) coefficients of the transients and the noise can be effectively distinguished by their different sparseness properties. Specifically, the proposed method mainly includes three steps: training the ICA basis features from the signal segments, denoising the sparse ICs coefficients using the shrinkage function deduced by the maximum a posteriori (MAP) estimation, and reconstructing the transient segments by the shrunken coefficients through the ICA basis functions. Experimental results through the simulated signal analysis and the vibration signal analysis show that the ICA-based method is very effective for transient detection outperforming the traditional methods and is valuable for gearbox condition monitoring and fault diagnosis.     

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.     

基于模态分量优化重构和稀疏表达的 静电信号联合降噪方法

航空发动机静电监测技术表现出了较高的故障预警能力,但原始静电信号常包含较多噪声,为提高故障信息提取的准确性,必须对静电信号进行降噪处理。本研究首先介绍了静电监测技术的原理,分析了信号的噪声的来源和主要构成;针对静电信号耦合噪声滤除问题,引入了信号稀疏表达和经验模态分解理论,研究了模态分量的筛选依据和相关准则,并提出了一种基于模态分量优化重构和稀疏表达的联合降噪算法和具体流程;利用所提方法对涡扇发动机试车实验中采集的实际静电信号进行了降噪效果验证,并与其它方法进行了对比。结果表明本文方法在滤除随机噪声以及工频干扰的同时能更高程度的保留有用异常颗粒信号,稀疏迭代次数在设置为20～50时均能够较好提取异常信号。     

Acoustic emission method for tool condition monitoring based on wavelet analysis

It is believed that the acoustic emission (AE) signals contain potentially valuable information for tool wear and breakage monitoring and detection. However, AE stress waves produced in the cutting zone are distorted by the transmission path and the measurement systems and it is difficult to obtain an effective result by these raw acoustic emission data. In this article, a technique based on AE signal wavelet analysis is proposed for tool condition monitoring. The local characterize of frequency band, which contains the main energy of AE signals, is depicted by the wavelet multi-resolution analysis, and the singularity of the signal is represented by wavelet resolution coefficient norm. The feasibility for tool condition monitoring is demonstrated by the various cutting conditions in turning experiments.     

Empirical mode decomposition of pressure signal for health condition monitoring in waterjet cutting

Waterjet/abrasive waterjet cutting is a flexible technology that can be exploited for different operations on a wide range of materials. Due to challenging pressure conditions, cyclic pressure loadings, and aggressiveness of abrasives, most of the components of the ultra-high pressure (UHP) pump and the cutting head are subject to wear and faults that are difficult to predict. Therefore, the continuous monitoring of machine health conditions is of great industrial interest, as it allows implementing condition-based maintenance strategies, and providing an automatic reaction to critical faults, as far as unattended processes are concerned. Most of the literature in this frame is focused on indirect workpiece quality monitoring and on fault detection for critical cutting head components (e.g., orifices and mixing tubes). A very limited attention has been devoted to the condition monitoring of critical UHP pump components, including cylinders and valves. The paper investigates the suitability of the water pressure signal as a source of information to detect different kinds of fault that may affect both the cutting head and the UHP pump components. We propose a condition monitoring approach that couples empirical mode decomposition (EMD) with principal component analysis to detect any pattern deviation with respect to a reference model, based on training data. The EMD technique is used to separate high-frequency transient patterns from low-frequency pressure ripples, and the computation of combined mode functions is applied to cope with the mode-mixing effect. Real industrial data, acquired under normal working conditions and in the presence of actual faults, are used to demonstrate the performances provided by the proposed approach.     

Applying the self-organization feature map (SOM) algorithm to AE-based tool wear monitoring in micro-cutting

This study applies a self-organization feature map (SOM) neural network to acoustic emission (AE) signal-based tool wear monitoring for a micro-milling process. An experiment was set up to collect the signal during cutting for the system development and performance analysis. The AE signal generated on the workpiece was first transformed to the frequency domain by Fast Fourier transformation (FFT), followed by feature extraction processing using the SOM algorithm. The performance verification in this study adopts a learning vector quantification (LVQ) network to evaluate the effects of the SOM algorithm on the classification performance for tool wear monitoring. To investigate the improvement achieved by the SOM algorithms, this study also investigates cases applying only the LVQ classifier and based on the class mean scatter feature selection (CMSFS) criterion and LVQ. Results show that accurate classification of the tool wear can be obtained by properly selecting features closely related to the tool wear based on the CMSFS and frequency resolution of spectral features. However, the SOM algorithms provide a more reliable methodology of reducing the effect on the system performance contributed by noise or variations in the cutting system.     

基于卷积型小波包变换的切削力信号消噪

为了消除切削力信号中的随机噪声干扰,本文提出了一种基于卷积型小波包变换的消噪算法,给出了算法的详细步骤。对两个切削力信号的消噪实例结果表明:随机噪声已完全被去除,获得了准确的力信号。     

基于自适应稀疏表示的宽带噪声去除算法

为了有效地去除信号中的宽带噪声,提出了一种基于自适应稀疏表示的宽带噪声去除算法.根据噪声成分与信号特征成分之间的不相关或弱相关特点,自适应地确定稀疏分解的终止条件,实现信号的稀疏表示.降噪过程中使用染噪信号构造学习样本,由信号的自适应稀疏表示和原子库的更新迭代实现原子库的训练.染噪信号在训练后的原子库上进行自适应稀疏表示,实现信号的噪声去除.仿真信号和齿轮振动信号的降噪试验表明:该方法具有比小波阈值降噪、匹配追踪降噪方法更好的降噪性能,能够有效地去除信号中的宽带噪声.     

Tool condition monitoring in an end-milling operation based on the vibration signal collected through a microcontroller-based data acquisition system

Machine condition plays an important role in machining performance. A machine condition monitoring system will provide significant economic benefits when applied to machine tools and machining processes. Development of such a system requires reliable machining data that can reflect machining processes. This study demonstrates a tool condition monitoring approach in an end-milling operation based on the vibration signal collected through a low-cost, microcontroller-based data acquisition system. A data acquisition system has been built through interfacing a microcontroller with a signal transducer for collecting cutting vibration. The examination tests of this developed system have been carried out on a CNC milling machine. Experimental studies and data analysis have been performed to validate the proposed system. The onsite tests show the developed system can perform properly as proposed.     

Development of a tool wear observer model for online tool condition monitoring and control in machining nickel-based alloys

Online monitoring and in-process control improves machining quality and efficiency in the drive towards intelligent machining. It is particularly significant in machining difficult-to-machine materials like super alloys. This paper attempts to develop a tool wear observer model for flank wear monitoring in machining nickel-based alloys. The model can be implemented in an online tool wear monitoring system which predicts the actual state of tool wear in real time by measuring the cutting force variations. The correlation between the cutting force components and the flank wear width has been established through experimental studies. It was used in an observer model, which uses control theory to reconstruct the flank wear development from the cutting force signal obtained through online measurements. The monitoring method can be implemented as an outer feedback control loop in an adaptive machining system.     

Vibration condition monitoring of planetary gearbox under varying external load

The paper shows that for condition monitoring of planetary gearboxes it is important to identify the external varying load condition. In the paper, systematic consideration has been taken of the influence of many factors on the vibration signals generated by a system in which a planetary gearbox is included. These considerations give the basis for vibration signal interpretation, development of the means of condition monitoring, and for the scenario of the degradation of the planetary gearbox. Real measured vibration signals obtained in the industrial environment are processed. The signals are recorded during normal operation of the diagnosed objects, namely planetary gearboxes, which are a part of the driving system used in a bucket wheel excavator, used in lignite mines. It is found that a planetary gearbox in bad condition is more susceptible to load than a gearbox in good condition. The estimated load time traces obtained by a demodulation process of the vibration acceleration signal for a planetary gearbox in good and bad conditions are given. It has been found that the most important factor of the proper planetary gearbox condition is connected with perturbation of arm rotation, where an arm rotation gives rise to a specific vibration signal whose properties are depicted by a short-time Fourier transform (STFT) and Wigner-Ville distribution presented as a time–frequency map. The paper gives evidence that there are two dominant low-frequency causes that influence vibration signal modulation, i.e. the varying load, which comes from the nature of the bucket wheel digging process, and the arm/carrier rotation. These two causes determine the condition of the planetary gearboxes considered. Typical local faults such as cracking or breakage of a gear tooth, or local faults in rolling element bearings, have not been found in the cases considered. In real practice, local faults of planetary gearboxes have not occurred, but heavy destruction of planetary gearboxes have been noticed, which are caused by a prolonged run of a planetary gearbox at the condition of the arm run perturbation. It may be stated that the paper gives a new approach to the condition monitoring of planetary gearboxes. It has been shown that only a root cause analysis based on factors having an influence on the vibration solves the problem of planetary gearbox condition monitoring.     

基于移不变抗混叠轮廓波变换的混合统计模型图像降噪

针对抗混叠轮廓波变换缺乏平移不变性的缺陷,构造出具有近似移不变性的抗混叠轮廓波变换。在此基础上,在变换域提出一种混合统计模型图像降噪方法。该方法充分利用变换域信号系数层间层内相关性强、噪声系数无层内相关性且在小尺度下存在较强的假层间相关性的特点,采用混合统计模型对小尺度信号系数进行估计,从而避免了非高斯双变量模型放大噪声系数的风险。实验结果表明,提出的去噪法能克服轮廓波变换中的频谱混叠,避免重构图像出现"划痕"和边缘模糊现象,得到的峰值信噪比(PSNR)值分别比轮廓波硬阈值去噪、轮廓波变换域HMT去噪和抗混叠轮廓波变换域硬阈值去噪平均高2.87,1.32和1.36 dB,在有效去噪的同时,具有较好的图像边缘和细节保护能力。     

汽车覆盖件拼接模具硬态铣削过程的动态特性

针对汽车覆盖件拼接模具铣削过程铣削力及振动信号测试失真问题,运用经验模态分解(empirical mode decomposition,简称EMD)结合小波阈值降噪原理,对铣削力及振动信号进行降噪处理。对降噪后的振动信号进行时频域分析,研究了不同切削参数、切削进给方向对铣削拼接模具过程动态特性的影响,得到铣削方向由硬度大材料切向硬度小材料,走刀方向与拼接缝成30°夹角时铣削力突变值较小的结论。发现x,y,z方向的切削分力及振动幅值的突变值与轴向切深及进给速度呈现正相关,与切削速度是非线性关系的特性。该研究结果为汽车覆盖件拼接模具硬态铣削的工艺优化提供了理论支持。     

二维振动辅助微细铣削切削力建模与试验研究

基于力学解析法与斜角切削微元力模型,综合考虑刀具偏心、尺度效应与累积作用对瞬时切削厚度的影响,结合二维振动辅助微细铣削运动学特性,根据剪切区与犁耕区切削力大小不同的特点,建立了二维振动辅助微细铣削切削力模型。为实现振动辅助加工的目的,基于自行设计并优化的非谐振式二维柔顺振动平台,对铝合金Al6061进行了相应的二维振动辅助微细铣削试验研究,并利用MATLAB软件对铝合金Al6061的切削力曲线进行了仿真研究,通过对比分析验证所建立的二维振动辅助微细铣削切削力模型的正确性。最后,基于所建立的切削力模型,分别分析了振幅与振动频率对铣削力的影响规律。     

Tool wear monitoring in drilling using force signals

Utilization of force signals to achieve on-line drill wear monitoring is presented in this paper. A series of experiments were conducted to study the effects of tool wear as well as other cutting parameters on the cutting force signals and to establish the relationship between force signals and tool wear as well as other cutting parameters when drilling copper alloy. These experiments involve four independent variables; spindle rotational speed ranging from 600 to 2400 rev min⁻¹, feed rate ranging from 60 to 200 mm min⁻¹, drill diameter ranging from 5 to 10 mm, and average flank wear ranging from 0.1 to 0.9 mm. A statistical analysis provided good correlation between average thrust and drill flank wear. The relationship between cutting force signals and cutting parameters as well as tool wear is then established. The relationship can then be used for on-line drill flank wear monitoring. Feasibility studies show that the use of force signal for on-line drill flank wear monitoring is feasible.     

The design of a single-chip tool monitoring system for on-line turning operation

Tool condition monitoring systems play an important role in a FMS system. By changing the worn tool before or just at the time it fails, the loss caused by defect product can be reduced greatly and thus product quality and reliability is improved. To achieve this, an on-line tool condition monitoring system using a single-chip microcomputer for detecting tool breakage during cutting process is discussed in this paper. Conventionally, PC-based monitoring systems are used in most research works. The major shortcoming of PC-based monitoring systems is the incurred cost. To reduce costs, the tool condition monitoring system was built with an Intel 8051 single-chip microprocessor and the design is described in this paper. The 8051 tool monitoring system uses a strain gauge for measuring cutting force; according to the force feature, the tool monitoring system can easily recognize the breakage of the cutting tool with its tool breakage algorithm. The experimental results show that the low-cost 8051 tool monitoring board can detect tool breakage in three successive products successfully.