刀具破损状态声发射信号的多分辨率分析

刀具状态监控对保障生产安全和产品质量具有重要意义。采用声发射(AE)传感器来采集切削过程中发出的AE信号,采用多分辨率分忻法对正常切削、刀具破损、断屑时发出的AE信号进行分析,并提取出反映刀具破损状态的特征量;最后采用BP神经网络实现了刀具破损状态的自动识别。     

单通道AE信号盲分离的飞机构件监测方法研究

基于声发射(AE)技术的飞机结构件疲劳裂纹检测是飞机健康状态识别的一种有效方法。由于声发射信号的瞬态性、不确定性、微弱性和易受机电干扰性,使声发射检测技术很大程度上已演变成信号处理问题,目前多数研究报道的是单源声发射信号的降噪处理。然而,在实际应用中,不仅结构件出现疲劳裂纹时会产生AE信号,而且紧耦合的结构体之间也会因冲击载荷产生弹性波,以至观测信号一般是多源AE混合信号,波的传播时延的存在使得信号混合方式为卷积混合。针对目前测试方法不能正确识别AE信号,以致难以识别结构体是否存在疲劳裂纹的问题,提出一种具有信号源个数估计的单通道非负矩阵分解解卷积盲源分离算法。首先采用经验模态分解方法将单通道混合信号分解为多个本征模态函数;然后采用主成分分析法估计信号源个数,并重构观测信号;最后通过非负矩阵分解解卷积得到各个源信号。实验结果表明,单通道盲源分离算法能正确分离AE信号,为飞机关键结构件的疲劳裂纹监测提供了一种方法。     

刀具设备的监测与诊断技术动向（续）

(2)AE信号检测技术 刀具切削金属时,切削区的材料产生变形,由于塑性应变能的释放而产生弹性变形,即发出声波,即声发射(AE),其频率范围为100kHz～1MHz。刀具如果发生破损,AE信号的特征量会有显著变化。AK信号的特征有功率谱、信号有效值或经检波后的幅值、实发脉冲、脉冲计数率等。微小钻头或丝锥折断,或者刀具上有0.01mm~2的崩刃,也可以灵敏地反映出来。AE信号可由电压传感器来检测与采集。同时,AE信号直接与切削机理相联系,受切削条件变化的影响很小,抗环境干扰能力强,且可以预报刀具破损。该方法显示出广阔的应用前景。     

基于小波模糊神经网络刀具监控系统研究

针对切削过程中振动信号和AE信号的特点,利用小波分析技术提取信号深层特征,建立了新型的基于模糊推理的神经网络模型,该模型能融合振动和AE信号的特征和描述信号特征与刀具状态的非线性关系,以此识别刀具状态。试验表明小波模糊神经网络对提高在线刀具监控系统的可靠性极为有效。     

金属板材拉深成型裂纹识别实验

提出一种采用声发射(Acoustic Emission,AE)技术对金属板材拉深件的成型状态进行识别的方法。在此实验过程中,首先采集金属板材拉深成型时的裂纹AE信号,然后用独立分量分析法对其进行分离,进而采用时序分析法提取裂纹AE信号的特征参数-能量值,最后根据模糊综合评判法辨别制件是否有裂纹产生。通过实验结果分析可知,采用AE技术能够准确地监测产生裂纹的初始和扩展过程,也能有效识别拉深件成型状态,为拉深成型件的质量判断提供了有力依据。     

磨削过程的AE监视模型

开发了磨削时单切削刃作用的运动模型。该模型描述了切削刃处切屑形成产生的力脉冲。假定该脉冲激励声发射（AE）信号。它的典型特征决定所需的测量设备。当磨削时在工件上测出AE，并在70KHz和3．MHz的频率范围内对其进行分析。使用频域特征抽出，由AE信号抽取有意义的信息，开发了合适的信号分析方法。模型和测量的比较，输出模型参数的识别。该参数值对砂轮状态和磨削过程状态给出描述。     

在线检测铣刀磨损的实验研究

本文介绍了用加速度传感器和声发射(AE)传感器两种方法研究铣刀磨损的在线检测问题。文中对加速度信号进行了功率谱分析和均方根值分析;对AE信号进行了计数率分析和AE均值分析。结果表明,用加速度传感器可以在线检测出铣刀的破损。当切削用量基本不变或其变化规律已知时,两种方法均可检测出铣刀的磨损状态。     

混凝土结构安全检测的声发射阵列传感器系统设计

设计8阵元声发射(acoustic emission,AE)均匀圆阵传感器系统,针对大型混凝土板内部缺陷(声发射源)进行检测,并在此传感器系统基础上,分别用常规波束形成法(conventional beam forming,CBF)和最小方差无畸变响应法(mini-mum variance distortionless response,MVDR)对混凝土板内部AE源进行测向仿真分析,MVDR算法比CBF算法有较高的角分辨率。在混凝土甲板上(3 m×3 m)进行实验,结果表明CBF算法测向出现混淆现象,不能确定AE信号的入射方向,而MVDR算法较好地辨别出AE信号的入射方向,但与模拟AE信号源方位相差2°左右。     

利用模态声发射技术监测飞机主结构件的日历损伤

研究了腐蚀特别是点腐蚀过程产生声发射(AE)的源机制及AE信号特点,推导了AE信号幅度与腐蚀深度及频率的关系,并说明该关系对利用AE技术监测腐蚀损伤的意义。论述了利用模态声发射(MAE)技术识别腐蚀AE信号的理论根据,介绍了利用MAE技术对飞机主结构件日历损伤进行评估的方法。基于试验获得的航空用铝合金材料在加速腐蚀过程中的声发射信号与腐蚀损伤的关系对研究材料损伤程度与声发射强度之间的内在联系有重要意义。试验表明,腐蚀能远在被肉眼发现之前即可很方便地用AE仪器检测,利用AE技术探测早期腐蚀、研究腐蚀发展规律、监测和评估腐蚀损伤具有极其良好的应用前景。     

基于CVA-ICA的机械故障源动态盲分离方法

动态盲源分离问题是多故障源盲分离的一个热点。传统的机械故障源分离方法要求满足统计特征保持稳定,且混合系统保持不变等假设,而忽略了时序信息。针对此不足,结合规范变量分析(Canonical variate analysis,CVA)和独立分量分析(Independent component analysis,ICA),提出一种基于CVA-ICA的机械多故障源动态盲分离方法。该方法的基本思想是将源信号看成状态空间的状态变量,观测信号看成状态空间的输出变量,从而将动态混合盲源分离问题转化为状态空间盲源分离问题,利用规范变量分析作为降维工具来构造状态空间,再利用传统的ICA算法对规范的观测信号进行盲源分离。仿真研究表明,在处理动态混合的盲分离中,提出的方法明显优于静态ICA方法,取得了满意的分离效果。将该方法应用到滚动轴承内圈和滚动体的故障盲分离中,试验结果进一步验证了该方法的有效性。     

基于FFT-MCC分析的ICA(BSS)盲不确定性消除

为了消除ICA（BSS）估计的幅值、相位及排序等盲不确定性，提出一种基于快速傅里叶变换与最大相关准则分析的ICA（BSS）估计源自适应校正方法。借助对原始传感观测及估计源的频谱分析，近似获得各本底源信号在观测信号中所占的比重——初始放大权值；基于最大相关准则优化调整ICA（BSS）估计源的相位，并对初始放大权值进行微调，从而消除ICA（BSS）估计的盲不确定性，实现源波形的恢复及其混合参数的估计。仿真试验结果证明了该方法的有效性，也表明它在复杂系统源识别或重建方面具有较大的应用潜力。     

Investigation on the effect of EDM process variables and environments on acoustic emission signals

Abstract

The performance of electrical discharge machining (EDM) primarily depends on the spark quality generated in the inter-electrode gap (IEG) between the tool and workpiece. A method for obtaining accurate information about the spark gap is required to effectively monitor the EDM process. The rise and fall of thermal energy in the discharge zone at a rapid rate during the dielectric breakdown produces high-pressure shock waves. This work explores the suitability of using acoustic emission (AE) generated from these shock waves and the elastic AE waves released on the workpiece due to the induced stress to monitor the performance and spark gap in EDM. The information content of the AE signals acquired at various machining conditions was extracted using AE RMS, spectral energy and peak amplitude. These features were able to well discriminate the machining condition, tool material, workpiece material, flushing pressure, current density, the initial surface roughness of the tool. Additionally, the AE signal features had a good and consistent correlation with the performance parameters, including material removal rate, surface roughness (Ra and Rq) and tool wear. The findings lay the groundwork to develop an effective, non-intrusive in-situ AE-monitoring system for performance and IEG condition in EDM.     

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.     

The efficacy of back propagation neural network with delta bar delta learning in predicting the wear of carbide inserts in face milling

Face milling is a process predominantly affected by dynamic variation of cutting forces, thermo-mechanical shocks and vibration leading to catastrophic tool failure along with gradual wear of the inserts. Keeping in view the industrial importance of this process, it is necessary to devise suitable methods to predict in advance the onset of tool failure without grossly impairing the machining set-up and the job. Hence, the applicability of back propagation neural network with delta bar delta learning rule for faster convergence has been studied with the above objective. The multi sensor based tool condition monitoring strategy shows that the learning rate adaptation scheme combined with the selection of suitable process parameters drastically reduces the training time of the artificial neural network without dispensing with the prediction accuracy.     

刀具磨损监测中信号特征值的提取与聚类分析

声发射是近年刀具监测研究中采用的新技术之一,本文用包络分析法求取刀具磨损中声发射信号的包络线,用其时序模型参数作为特征值,采用神经网络对刀具磨损状态进行分析,试验表明效果良好。     

Feasibility study on the use of the Acoustic Emission technology for monitoring flow patterns in two phase flow

This paper presents an investigation into the detection of single bubble inception and burst with the Acoustic Emission (AE) technology. In addition, it presents results correlating the Gas Void Fractions in two phase gas–liquid flow with levels of AE activity. The findings demonstrate the feasibility of employing AE technology as an on-line monitoring tool for bubble detection and ascertaining flow patterns under two phase gas-liquid flow conditions.     

Evaluation of tribological properties of bearing materials for marine diesel engines utilizing acoustic emission technique

Acoustic Emission (AE) technique, which has detection capability for minute failures, has been tried to monitor the condition of a plain bearing under the laboratory conditions. In this paper, the bearing materials for marine diesel engines - tin alloy as known as “white metal”, aluminum alloy of 40% tin mass and aluminum alloy 40% tin mass with resin overlay - were tested using a sleeve-to-plate tribo-tester. The frictional force and back temperature were measured as well as the AE signals. The possibility of AE technique to monitor the bearing condition was also assessed by evaluating tribological properties under different operating conditions such as start-stop simulating the crankshaft turning during engine assembly and seizure tests. These results indicate that AE is useful for monitoring the lubricated condition of the sliding surfaces and evaluating tribological properties of the bearing.     

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.     

复合ICA-SVM机械状态模式分类

提出了一种新颖的、基于独立分量分析(ICA)的复合神经网络，用于不同机械状态模式的特征提取。利用支持向量机(SVM)进行最终分类。与通常的基于经验风险最小化(ERM)原理的神经网络方法相比，基于结构风险最小化(SRM)原理的支持向量机分类方法具有更好的推广能力。而借助多个独立分量分析网络，隐藏于多通道振动观测信号中的不变特征得到有效提取，从而实现了支持向量机分类器在分类能力和推广性两者间的合理平衡。     

涂层刀具高速铣削淬硬钢的声发射信号特征

通过测量不同涂层铣刀高速铣削不同硬度淬硬钢材料时的声发射信号和切屑形态,得到了电压-时间声发射信号以及声发射信号RMS值与切削工艺参数之间的关系。研究结果表明：声发射信号与淬硬钢材料硬度、刀具涂层类型及工艺参数有关;声发射信号可用来评价淬硬钢材料硬度的变化,随着淬硬钢材料硬度的增大,采集的声发射信号电压值呈逐渐增大的趋势;TiAlN涂层产生的锯齿形切屑的剪切带长度最小,切屑易于折断,从而导致其产生过程中的声发射RMS值偏小;随着切削速度和每齿进给量的增大,TiSiN、TiAlN、AlCrN和CrSiN四种涂层铣刀的声发射信号均快速增大,而随着轴向和径向铣削深度的增大,4种涂层铣刀的声发射信号变化不明显;在同一种切削参数条件下,可根据淬硬钢切屑变形特征的变化来间接评价刀具涂层的切削性能;声发射信号波形图的峰值大小可较好地反映锯齿形切屑的生成状态,进而可用来监控淬硬钢加工过程切削稳定性。