基于连续小波和多类球支持向量机的颤振预报

研究了一种应用连续小波特征和多类球支持向量机进行铣削系统颤振预报的方法,该方法基于连续小波变换提取铣削振动信号的特征,利用多类球支持向量机对正常铣削状态、颤振孕育状态和颤振爆发状态的振动信号进行三分类识别,通过识别颤振孕育状态预测颤振爆发。试验结果表明,在铣削颤振识别与预测中,铣削振动信号的连续小波特征与多类球支持向量机相结合具有良好的识别颤振孕育状态和颤振爆发状态的能力,颤振孕育状态的识别正确率达95.0%,颤振爆发状态的识别正确率达97.5%。     

铣削颤振过程中的振动非线性特征试验

为了分析铣削过程振动信号的非线性特征,使用双谱、李雅普诺夫系数、变形维数和近似熵分析变切深铣削过程中平稳铣削振动信号、颤振孕育振动信号和颤振振动信号.试验结果表明,振动信号在铣削颤振孕育和发生状态时具有强混沌特征,其双谱特征和混沌特征相结合可以作为识别颤振孕育、发生的有效手段,基于球形支持向量机分类器对平稳铣削、颤振孕育和颤振发生进行识别,识别准确率达98.0％.     

基于多类超球支持向量机的铣削颤振预测方法

为了预测薄壁件铣削过程颤振的发生,提出了一种应用小波系数特征和多类超球支持向量机进行铣削颤振预报的方法.首先基于连续小波变换分别提取高、低频段铣削振动信号的特征,然后利用多类超球支持向量机进行稳定铣削状态、铣削颤振孕育状态、铣削颤振状态识别.为了简化支持向量机进行多类分类时所带来的计算复杂性,该算法使每一类样本都获得一个超球支持向量机,在特征空间中以测试样本与超球中心距离、超球半径作为决策函数来进行识别.实验表明,在铣削颤振识别系统中多类双核超球支持向量机与连续小波系数特征向量相结合具有良好的识别效果,颤振孕育预报正确率达98.0％.     

铝合金薄壁件的铣削加工颤振的建模与识别

选取力信号和加速度信号来预测薄壁件的颤振状态,分别提取铣削力信号的实时方差特征与加速度信号的小波能量特征,并采用该两个特征量构建颤振信号识别特征量。用测力仪、加速度传感器等设备搭建了铝合金薄壁件铣削颤振实验台,在不同切削参数条件下设计了正交实验分组。区别于以往的二分类SVM模型,文中设计了基于二叉树决策的多分类SVM模型,并结合信号实时方差与小波能量特征,将机床加工状态分为稳定阶段、趋于颤振和颤振阶段这三种状态,实验获得的160组信号特征量数据分别用来完成多分类SVM模型的训练和检验。结果表明:在切削参数下,设计的SVM识别模型具有96.67%的准确率,能在工程实践中达到颤振预测的目的。     

基于自适应变分模态分解与功率谱熵差的机器人铣削加工颤振类型辨识

机器人铣削加工存在模态耦合颤振和再生颤振现象,有效地进行机器人铣削加工颤振类型的辨识是进行颤振精准抑制和保证加工质量的基础。为此,提出一种基于自适应变分模态分解与功率谱熵差的颤振类型辨识(AVMD-ΔPSE)方法。通过分析机器人铣削加工颤振特性和主导模态,将机器人铣削颤振分为机器人结构模态主导的模态耦合颤振和刀具-主轴结构模态主导的再生颤振两种类型。为了提取颤振敏感子信号,利用自适应变分模态分解方法对原始信号进行分解,根据功率谱熵和频率消除算法设计功率谱熵差颤振类型辨识指标,结合多组试验数据采用高斯混合模型自适应地确定辨识指标最佳分类阈值。颤振辨识试验表明机床铣削加工颤振辨识方法运用于机器人铣削加工中仅能识别颤振却无法区分不同的颤振类型,而AVMD-ΔPSE方法能准确有效地辨识和区分机器人铣削加工中的模态耦合颤振和再生颤振,为机器人铣削颤振的针对性抑制提供理论指导。     

基于多尺度排列熵的铣削颤振在线监测方法

排列熵是系统复杂性和规则性的一种测度,具有概念简单、稳健和计算速度快等优点。考虑到单尺度排列熵在反映铣削力信号特征方面的不足,通过试验分析提出基于单尺度排列熵和尺度4排列熵作指标的铣削颤振在线检测方法。通过试验验证,所提出的方法能有效地检测铣削颤振。同时基于多尺度排列熵的方法对于铣削力信号采集过程中的噪声、工艺参数变化等不敏感,因此这种方法适用于实际工业生产中的在线铣削颤振监测。     

采用一维卷积神经网络的铣削振动状态识别

由于铣削加工中发生颤振会极大地降低工件的加工质量,铣削振动状态的高效与精准辨识一直是颤振研究的热点问题之一。基于LetNet-5经典卷积网络提出一维卷积网络模型,直接对时域铣削力信号进行处理与识别,针对信号量较少与数据不均衡等问题,采用重叠-随机协同采样的方法对数据进行处理。应用T-分布随机邻域嵌入技术可视化模型在训练集上的学习进程并对端到端的学习目标进行验证。对比基于支持向量机与卷积神经网络识别策略,所提方案在测试集上取得了最高的96.17%准确率,识别结果表明：该方法相较于对比方法过程简单、识别快速且辨识准确率高。     

基于小波包能谱熵的铣削颤振监测方法

针对切削加工过程中容易出现颤振,导致零件表面加工质量降低,本文以铣削加工为研究对象,提出了基于小波包能谱熵的铣削颤振监测方法。信号的采集是一个连续的过程,为避免刀具不参与切削对这种方法的影响,本文提出基于铣削力幅值平方和的方法以识别刀具是否参与切削。试验结果表明,无论对于刀具是否参与切削的识别或者是否出现铣削颤振的监测都能有效的监测。     

铣削颤振在线智能控制方法研究

针对铣削加工中颤振降低加工效率的情况,研究了颤振在线自主识别与控制的方法。使用传感器拾取加工状态信息,提取振动信号时域均方差特征及频域幅度谱特征,提出了具有广泛适用性的颤振在线识别算法。以2π作为刀具前后两次铣削振纹间的最优相位差,依据颤振频率调整主轴转速,消除颤振。以SIEMENS 840D系统为平台研究了机床转速在线实时调整的方法。进行了铝合金工件的铣削实验,验证了颤振在线抑制、提高加工效率的有效性。     

基于小波包及Hilbert-Huang变换的数控铣削颤振诊断技术

为了提高产品加工质量,根据试验测得铣削系统颤振稳定域,制定并采集数控铣削振动信号,以保证采集信号的准确性;融合小波包变换与希尔伯特黄变换,从能量频域分布与幅值概率统计分布两方面提取信号特征值,其中小波包降噪作为信号前置处理能有效降低环境噪声干扰的影响,提高经验模式分解的精度;建立基于模糊支持向量机的颤振诊断模型,将振动信号分为平稳铣削信号、微弱颤振铣削信号、颤振铣削信号及刀具磨损铣削信号。实验结果表明,该模型具有良好的铣削振动信号辨识与诊断能力,预测准确率达97.3%,为数控铣削加工振动信号的准确辨识与诊断提供了一种新方法。     

Method for early detection of the regenerative instability in turning

Nowadays, approaches in chatter detection and control are based on chatter prediction, by using a machining system dynamic model, or on chatter detection by different techniques, but after chatter onset. They are not efficient because the models are complicated and specific (in the first case) respectively because of chatter unwanted consequences occurrence (in the second case). This paper presents a method for early detection of the process regenerative instability state (as a specific process current dynamical state), based on cutting force monitoring. Using the cutting force records, the process current dynamical state is assessed. Appropriate cutting force signal features are defined, based on signal statistic processing, signal chaotic modeling or signal harmonic analysis, and used on this purpose. The process dynamical state evolution is modeled aiming the features values prediction. Two types of models were used in this purpose: linear and neural. The instability regenerative mechanism is identified by using either dedicated features or input variable selection. The method was conceived and experimentally implemented in the case of turning process. The results show the method reliability and the possibility of using it in developing an intelligent system for stability control.     

基于电流变材料的切削颤振在线监控技术研究

提出可以利用电流变材料的电控流变特性,通过在线调控切削系统动态特性以提高切削稳定性。并针对镗削系统,开发出一套可根据实时采集的切削振动信号自适应地快速调整系统动态特性以避免颤振发生的颤振智能监控系统。     

ESPRIT- and HMM-based real-time monitoring and suppression of machining chatter in smart CNC milling system

Suppression of machining chatter during milling processes is of great significance for surface finish and tool life. In this paper, a smart CNC milling system integrating the function of signal processing, monitoring, and intelligent control is presented with the aim of real-time chatter monitoring and suppression. The algorithm of estimation of signal parameters via rotational invariance techniques (ESPRIT) is adopted to extract the frequency characteristics of acceleration signals, and then, cutting state is categorized as stable state, chatter germination state, and chatter state based on amplitude-frequency characteristics of identified acceleration signals. The model of chatter identification is acquired by training a hidden Markov model (HMM), which combines acceleration signals and labeled cutting state. To implement real-time chatter suppression, the algorithm of fuzzy control is integrated into a smart CNC kernel to determine the relationship between cutting force and spindle speed. Furthermore, spindle speed of machine tool could be adjusted timely in the presented system once the chatter is identified. Finally, the effectiveness of the proposed real-time chatter monitoring and suppression system is experimentally validated.     

四辊冷带轧机三倍频颤振机理的研究

研究了四辊冷带轧机三倍频颤振的产生机理,发展了轧件振动模型,分析了由于轧件失稳所导致的轧机颤振现象,提出了轧机三倍频再生颤振模型,并对其进行了理论研究,仿真结果和现场测试进一步论证了三倍频再生颤振理论模型的正确性及其工业价值。     

镗削颤振快速预报技术研究

切削颤振切导致产品质量、生产效率、刀具和机床使用寿命的降低 ,同时造成噪声污染 ,影响操作者身心健康。随着工厂自动化发展 ,操作者日益远离加工现场 ,对切削颤振进行在线监视预报和控制变得越来越重要。但由于其发生发展的过程极其短暂 ,使颤振的在线预报十分困难。本文在讨论了镗削颤振发展机理的基础上 ,提出了一种基于神经网络进行颤振预报的新方法。用 L O- RBF模型进行传感信号预处理 ,结果输入 Fuzzy ARTMap模型进行颤振识别 ,大大缩短了信号处理时间 ,提高了识别的准确性 ,取得了满意的结果。     

再生型切削颤振诊断技术的研究

本文着重讨论了再生型切削颤振的诊断原理和诊断方法。理论分析和试验结果都证明,再生型切削颤振系统的稳定性与被切工件前后两转向振纹的相位差ψ存在某种对应关系;因此,可通过实际测量切削过程中相位差ψ的大小来诊断现场加工中发生的颤振是否属于再于型颤振。相位差ψ与颤振频率、工件转速有关,为使诊断结果准确可靠,本文试验工作采用了频率细化技术。     

切削颤振模型及机理研究

提出了同时考虑工件系统和刀具系统对切削颤振影响的２自由度切削系统模型,用此模型解释了双频颤振和单频颤振产生的机理,提出了产生的条件,并进行了试验验证。     

Chatter prevention for milling process by acoustic signal feedback

This paper presents how real-time chatter prevention can be realized by feedback of acoustic cutting signal, and the efficacy of the proposed adaptive spindle speed tuning algorithm is verified as well. The conventional approach to avoid chatter is to select a few appropriate operating points according to the stability lobes by experiments and then always use these preset cutting conditions. For most cases, the tremble measurement, obtained by accelerometers or dynamometers, is merely to monitor spindle vibration or detect the cutting force, respectively. In fact, these on-line measures can be more useful, instead of always being passive. Furthermore, most of these old-fashioned methodologies are invasive, expensive, and cumbersome at the milling stations. On the contrary, the acoustic cutting signal, which is fed into the data acquisition interface, Module DS1104 by dSPACE, so that an active feedback loop for spindle speed compensation can be easily established in this research, is non-invasive, inexpensive, and convenient to facilitate. In this research, both the acoustic chatter signal index (ACSI) and spindle-speed compensation strategy (SSCS) are proposed to quantify the acoustic signal and compensate the spindle speed, respectively. By converting the acoustic feedback signal into ACSI, an appropriate spindle speed compensation rate (SSCR) can be determined by SSCS based on real-time chatter level. Accordingly, the compensation command, referred to as added-on voltage (AOV), is applied to actively tune the spindle motor speed. By employing commercial software MATLAB/Simulink and DS1104 interface module to implement the intelligent controller, the proposed chatter prevention algorithm is practically verified by intensive experiments. By inspection on the precision and quality of the workpiece surface after milling, the efficacy of the real-time chatter prevention strategy via acoustic signal feedback is further examined and definitely assured.     

Chatter detection by monitoring spindle drive current

The purpose of this work is to investigate a new method for detecting chatter in milling. In this method, the spindle drive current signal of a vertical milling machine is used for monitoring process instability. Both simulations and experimental work are conducted. Results show that current signals can transmit chatter frequencies reliably. The sensitivity of the current signal to slight process instability is assessed. A statistical indicator, the R-value is used to evaluate this sensitivity. Statistical analysis of experimental data shows that the R-value is insensitive to variations in speed, feed and geometry of cut. Also, experiments show that slight variations in the process instability results in a significant increase in the R-value.