Monitoring of hard turning using acoustic emission signal

Monitoring of tool wear during hard turning is essential. Many investigators have analyzed the acoustic emission (AE) signals generated during machining to understand the metal cutting process and for monitoring tool wear and failure. In the current study on hard turning, the skew and kurtosis parameters of the root mean square values of AE signal (AERMS) are used to monitor tool wear. The rubbing between the tool and the workpiece increases as the tool wear crosses a threshold, thereby shifting the mass of AERMS distribution to right, leading to a negative skew. The increased rubbing also led to a high kurtosis value in the AERMS distribution curve.     

Identification of tool wear using acoustic emission signal and machine learning methods

The work concerns the monitoring of the edge condition based on acoustic emission (AE) signals. The tool edge condition was determined by the wear width on the flank face. The processed material was an aluminum-ceramic composite containing 10% SiC. A carbide milling cutter with a diamond coating was used as the tool. Based on the AE signals, appropriate measures were developed that were correlated with the edge condition. Machine learning methods were used to assess the milling cutter's degree of wear based on AE signals. The applied approach using a decision tree allowed the prediction error of the tool condition class with a value below 6%. The method was also compared with other machine learning methods such as neural networks and the k-nearest neighbor algorithm.     

声发射信号处理在轮轴故障检测中的应用研究

声发射（Acoustic Emission）可以定义为物体或材料内部迅速释放能量而产生瞬态弹性波的一种物理现象,是材料或结构受内力或外力作用产生变形或断裂,以弹性波的形式释放出应变能的结果。在基于虚拟仪器的轮轴故障检测分析平台中,可实现对声发射信号的时域分析、频谱分析、参数分析、小波去噪等主要功能。通过该平台,对具有典型状态的滚动轴承的声发射信号进行了试验研究。试验研究结果表明,对于不同状态的轴承,所测取的声发射信号包络频率特征有着明显的不同,并且和理论特征频率有着一定的关系。     

小波降噪在起重机声发射信号方面的应用

检测起重机械的方法主要是常规无损检测,但是这种常规方法一般不具备实时性特点,为了弥补这点缺陷,提出采用声发射技术来实现检测。在本次实验中搭载了试验系统,研究了起重机常用钢材Q235试件在不同缺陷条件下的声发射信号特性,同时运用有限元分析,小波分析来研究声发射信号和预制缺陷之间的关系,通过比较频谱和声发射参数,来获取有用的的缺陷信息。试验结果表明,可以根据波形的分析简要判断所检测试件的受损情况。     

STFT在AE信号特征提取中的应用

机械故障或损伤引发的声发射信号南高频突发脉冲信号和长周期准平稳噪声信号组成,适宜用短时傅里叶变换(sTFT)描述其时频特征.本文通过分析典型AE信号及其特征提取,首次将STFT引入声发射故障诊断领域,并提出了AE信号的STFT分析法.通过理论分析和仿真,确定了AE信号STFT的理想窗函数及其参数选择,有效地克服了STFT只用一个同定窗分析多尺度信号的缺陷.将STFT用于声发射检测的滚动轴承损伤类型及部件的识别,诊断结果十分准确、清晰和直观.仿真分析和实验研究均表明了STFT能有效提取AE信号的特征,为AE信号的波形分析开辟了一条有效的途径.     

Wear studies using acoustic emission techniques

This paper describes measurements of acoustic emission RMS signals obtained from sliding metallic contacts. The results show that RMS measurements are able to differentiate between different wear mechanisms occurring in both dry and lubricated contacts. Further, for the test conditions studied there is a direct empirical relationship between the integrated RMS signal and the wear volume removed from the test ball.     

Chip formation in microscale milling and correlation with acoustic emission signal

This work investigated the effects of different workpiece materials on chip formation and associated mechanisms in microcutting. The wavelet transformation technique was used to decompose acoustic emission (AE) signals generated from orthogonal micromilling of different workpiece materials. This allowed studying energy levels corresponding to deformation mechanisms. Resulting chip forms were characterised. The results indicated that the computed energies of decomposed frequency bands can be positivity correlated with chip morphology. The work provides significant and new knowledge on the utility and importance of AE signals in characterising chip formation in micromachining. Understanding chip formation mechanisms is important in managing the size effect in micromachining.     

Particle monitoring method using acoustic emission signal for analysis of slider/disk/particle interaction

One of the most important reliability issues in an information storage device is the contamination problem. The slider and disk can be damaged by the particles intruded into the slider/disk interface (SDI). In this work, in order to monitor the slider/disk interaction due to particle injection the acoustic emission (AE) method, which is typically utilized for the detection of slider contact, was used. The raw as well as frequency spectrum of the AE signal were obtained during the particle injection test. The particles were artificially injected inside the test apparatus to simulate the effect of contamination on the slider/disk interaction. SiC and polystyrene particles were used for the tests. As a result, the 1st torsional and bending mode frequencies of the nano-slider were observed when 1 μm SiC particles and 60 nm polystyrene particles were injected into the SDI. Also, it was shown that the particle behavior at the SDI can be predicted from the characteristics of the AE raw signal.     

Development of the technique of clustering by acoustic emission signal parameters

The technique of clustering by a set of parameters of acoustic emission (AE) signals, which allows reducing the time of processing of the recorded data, is considered. A comparative analysis of the stability of three clustering techniques (by shape, leading edge rise rate, and a set of AE signal parameters) with respect to the effect of random noise distributed according to a normal law is performed. A possibility of using the considered clustering techniques for distinguishing different stages of duralumin specimen fractures and during welding of steel specimens is experimentally demonstrated.     

旋转机械碰摩声发射信号的分形特征分析算法研究

本文针对盒维和关联维运算复杂度高、Katz维的精度不高的特点,提出了一种基于波形的分形维计算方法,介绍了分形维算法的推导过程.实验数据是在转子实验台上采集的碰摩声发射信号,通过在该信号上叠加高斯白噪声和非平稳噪声来获得模拟的强噪声污染的声发射信号,然后将分形维算法对该信号进行有效声发射信号识别.理论分析和实验结果表明:该算法具有更强区分噪声和声发射信号的能力,无论在复杂度、精确度还是在抗噪性能方面均优于现有的分维算法,能够在强噪声环境下反映碰摩声发射的发生,为碰摩声发射的特征识别与分析提供了一条新的途径.     

不同小波基在碳钢材料声发射信号分析中的应用

为研究不同小波基对同一声发射信号分析结果之间的可比性,以碳钢在塑性变形和裂纹扩展时产生的声发射信号为研究对象,用db5和sym5两种常用小波基对检测信号进行了分析对比.结果表明,对碳钢在塑性变形和裂纹扩展时产生声发射信号,2种小波变换在信号能量分布趋势上分析结果一致,在主要信号峰值对应频率上分析结果接近,平均相对偏差仅为1.53%,而在各级信号占能量比例的具体值和信号峰值上偏差较大,平均相对偏差在10%左右,可比性较差.     

基于TL-LSTM的轴承故障声发射信号识别研究

针对多工况下滚动轴承故障声发射信号智能识别问题,提出了一种长短时记忆网络(LSTM)与迁移学习(TL)相结合的故障识别新方法。该方法仅以单一工况下原始声发射信号参数作为训练样本,构建LSTM模型充分挖掘出声发射信号与故障之间的深层次映射关系,以识别与训练工况具有相近分布特征的其他工况下故障;引入并结合TL来应对相异分布特征的其它工况下故障识别问题,从而可完成多种类型工况下故障特征的自适应提取与智能识别。实验结果表明,对于转速、采集位置或滚动轴承型号工况改变时内圈、外圈及保持架故障的识别均具有较高的准确率,可端对端的实现多种类型工况下故障的实时在线智能监测任务,摆脱了对先验故障数据的过分依赖,验证了该方法的可行性与优越性。     

基于排列熵的电磁声发射信号到达时间识别

排列熵算法简单高效,能够反映出信号的微小变化,是一种有效的信号突变检测工具。通过引入信号包络排列熵分析方法,对声发射信号到达时间识别问题进行求解。排列熵对信号幅值的大小不敏感,但对信号幅值的变化敏感,通过记录信号包络排列熵的变化,根据包络排列熵第一个极小值时刻来识别信号到达时间。根据裂纹电磁声发射实测信号识别结果可知,包络排列熵方法对声发射信号到达时间具有较高的识别精度。     

基于小波的声发射信号参数提取方法

介绍小波分析方法在声发射信号处理中的应用,提出一套基于声发射信号小波分析的小波基选取的规则方法,并通过实验和仿真证明此方法的有效性.     

Locating acoustic emission sources in complex structures using Gaussian processes

A standard technique in the field of non-destructive evaluation is to use acoustic emissions to characterise and locate the damage events that generate them. The location problem is typically posed in terms of the times of flight of the waves and results in an optimisation problem, which can at times be ill-posed. A method is proposed here for learning the relationship between time of flight differences and damage location using data generated by artificially stimulated acoustic emission (AE)—a classic problem of regression. A structure designed to represent a complicated aerospace component was interrogated using a laser to thermoelastically generate AE at multiple points across the structure's surface. Piezoelectric transducers were mounted on the surface of the structure, and the resulting waveforms were recorded. A Gaussian process (GP) with RBF kernels was chosen for regression. Since during AE monitoring not all events can be guaranteed to be detected by all sensors, a GP was trained on data for all possible combinations (subsets) of sensors. The inputs to the GPs were the differences in time of flight between sensors in the set, and the targets were the locations of the source of ultrasonic stimulation. Subsequent (test) data points were located by every possible GP, given the active sensors. It is shown that maps learned on a given structure can generalise effectively to nominally identical structures.     

基于小波变换的管道泄漏声发射检测信号处理

针对管道泄漏声发射检测信号中含有大量噪声导致定位精度低这一实际,研究了基于小波变换的声发射检测信号降噪技术,利用小波函数阀值降噪法对泄漏系统所采集的信号进行滤波处理,以保证采集到的瞬态信号有效性,并采用互相关分析法对泄漏点定位.10种工况下实验结果表明,采用小波变换对声发射检测信号处理处理后,管道的定位精度在5％之内,满足工程实际需要.     

RETRACTED ARTICLE: Development and application of intensified envelope analysis for the condition monitoring system using acoustic emission signal

The application of the high-frequency acoustic-emission (AE) technique in the condition monitoring of rotating machinery has been increasing of late. It has a major drawback, though, the attenuation of the signal, and as such, the AE sensor has to be close to its source. Two signal-processing methods, envelope analysis and wavelet transform, were found to be useful for detecting faults in the rolling element bearing and gearboxes. These methods have a disadvantage, though: their application is focused only on a component of the assembled machine. For example, envelope analysis is a powerful method for detecting faults in the bearing system, but it is not proper for use in the gear system. Thus, these methods could not be used to detect combined faults in the common assembled machines. Therefore, we propose a signal-processing method consisting of envelope analysis and DWT (discrete wavelet transform). In addition, a novel mother function optimized for the AE signal for DWT was extracted through a fatigue crack growth test, and is also proposed herein. Then the proposed method, called intensified envelope analysis (IEA), was used to detect the faults in the rolling element bearing and rotating shaft. According to the results, IEA can be a better signal processing method for the condition monitoring system using AE technique.     

Modal analysis of acoustic leak signal in pipelines using time-frequency analysis

It is important to analyze the propagation characteristics of guided waves in acoustic leak location in pipelines. In this paper, the acoustic leak signal is analyzed in the time-frequency domain. Based on the relation of time-frequency distribution of the acoustic leak signal and the dispersion curves of guided waves, the mode components of acoustic leak signals were obtained. The research can provide a guideline for the mode selection in pipeline leak location, and help improve the accuracy of leak location.