基于小波分析和GA-SVM的金刚石 砂轮磨损的声发射监测研究

针对工程陶瓷磨削中金刚石砂轮磨损状态判别准确度不高的问题,在部分稳定氧化锆陶瓷金刚石砂轮精密磨削的声发射智能监测实验中,在深入研究部分稳定氧化锆陶瓷磨削机理的基础上,对磨削声发射信号进行了5层离散小波分解。研究结果表明:金刚石砂轮磨损后,磨削声发射信号小波分解系数的有效值和方差,以及声发射信号小波能谱系数在低频率段都有所增大;利用部分稳定氧化锆磨削声发射信号的小波能谱系数或小波分解系数的有效值和方差值的组合,作为判别金刚石砂轮磨损状态的特征值,采用基于遗传算法支持向量机对金刚石砂轮的磨损状态判别准确度达100%,判别准确度明显优于BP神经网络方法。     

基于小波包变换的油液磨损信号降噪研究

为提高油液分析对润滑系统磨损状态监测的准确性和可靠性,通过采用小波包变换(WPT)对光谱和直读铁谱检测信号进行降噪,得到反映稳态和奇异状态的近似系数、细节系数,为挖掘有效诊断特征作准备。结果表明,对于油液磨损信号的降噪,小波包变换有效,且Daubechies1小波基效果最好,噪声类型很可能是未知刻度白噪声。     

CPS系统中刀具加工状态实时监测的新方法

机床是信息物理系统(CPS系统)中主要的执行单元和感知单元,对其加工状态的动态监测和实时感知可以提高产品质量。为了实现加工现场信号采集和刀具加工状态在线监测,设计了主轴功率信号采集系统,同时引入力信号作为对比分析,应用希尔伯特-黄变换和小波变换根据特征频率段的信号特征构造了刀具磨损系数,将刀具磨损状态和磨损系数对应起来,在加工现场实现了刀具状态的在线监测。通过和小波变换的对比,证明了希尔伯特-黄变换在处理功率信号方面可以有效抑制噪声信号,提高监测的准确性。     

基于最佳小波基小波特征的神经网络刀具磨损状态监测方法

以小波分析理论为基础,提出了以对数熵理论确定最佳小波包分解树结构的方法,提出了基于声发射信号最佳小波基最佳小波分量频段能量的声发射信号小波特征,开发了基于最佳小波基小波特征的神经网络刀具磨损状态在线监测系统,实验结果表明,该系统具有较高的监测精度,能满足工业现场对刀具磨损状态实时在线监测的要求.     

基于小波分析的切削力信号奇异性检测

利用小波变换模的极大值和信号奇异点的关系,分析了用Lip指数来描述的切削力信号局部奇异性.通过观察奇异点的位置等信息得到切削刀具的磨损情况.通过对实际刀具磨损的在线监测数据分析,证明了采用小波变换检测刀具磨损这一方法的有效性.     

自适应提升小波在往复机械故障检测中的应用

提出了一种基于信号特征的自适应提升小波方法,即以提升小波为基础,根据信号分解后的熵来选择预测滤波器系数和更新滤波器系数,它克服了传统小波变换的不足,和提升小波只能依据信号特征来设计预测滤波器,而不能设计更新滤波器的问题.该方法用于往复机械气阀的振动信号特征提取,有效地提取了气阀的故障特征信号.实验中采用不同的小波对信号进行降噪性能比较,自适应提升方法设计的小波明显优于实验室中采用的其它小波.     

小波包和小波脊线相结合的解调方法在液压泵故障诊断中的应用

针对轴向柱塞泵故障振动信号呈现出的非平稳和非线性特点,提出了一种基于小波包能量法与小波脊线法相结合的信号解调方法,将其用于液压泵故障诊断中的信号解调过程。该方法首先对原始振动信号进行功率谱分析,明确故障振动信号反映出的能量集中频带带宽;根据确定的带宽和原始信号分析频率设定小波包分解的层数,采用小波包能量法提取出分解系数对应频带能量最大的特征信息进行信号重构;利用小波脊线法对重构后的频带信号进行解调处理,通过信号的包络解调谱提取故障的特征频率,利用解调后的时频谱对液压泵单柱塞滑靴磨损、斜盘磨损以及中心弹簧故障进行分析。通过实验结果验证,该方法能有效地对液压泵的故障信号进行解调,并能找出反映故障的敏感特征频率。     

基于人工神经网络的铣削磨损监测研究

利用铣削刀具磨损多参量信号进行预处理及特征量提取,采用特征融合方法建立信号级、模型级、特征级和融合级层次结构实验方案,通过样本训练模糊小波神经网络逼近系统,建立刀具补偿系统的最优控制策略,从而对被检测对象进行有效的识别与估计.由实验结果对比可见,人工神经网络模型的预测精度基本在范围之内.实验表明该模型适用于切削条件下的铣刀磨损监控,可以较准确地监控铣刀的剧烈磨损.     

基于改进小波阈值的激光陀螺漂移信号降噪

针对固定阈值法对激光陀螺漂移信号去除噪声会出现"过扼杀"小波系数的现象,提出一种称为E-median的小波阈值.信号进行平稳小波变换,计算各尺度高频小波系数的E-median阈值,采用软阈值法修正高频小波系数,通过平稳小波逆变换重构信号.对激光陀螺漂移仿真信号和实测信号去除噪声,该阈值均能保留原信号的特征并有效去除噪声...     

OFDM水声通信系统语音信号的小波包消噪方法

在阐述和构造了正交频分复用(OFDM)水声通信系统的基础上,利用小波包分解与重构对OFDM水声通信系统进行语音信号消噪处理.小波包分解方法依据信号与噪声小波变换系数分布特性不同来进行,首先将语音信号分层,确定最佳小波包分解树,再进行阈值量化,完成小波包分解,并对所得阈值进行消噪处理,最后利用小波包逆变换重构传输信号.计算机仿真结果表明在OFDM水声通信系统中利用小波包分解方法对语音信号进行处理,可有效消噪,并可较为完整地保存有效信号.     

刀具磨损声发射信号处理中小波基选取的研究

通过对小波基性质和刀具磨损声发射（AE）信号特点的研究,从理论上分析了小波变换中刀具磨损AE信号处理中小波基选取的方法。在试验验证过程中,根据小波包信号分解遵循能量守恒原理,用四种小波基对刀具磨损AE信号进行三层小波包分解;以AE信号经小波包分解后各频带上的能量为特征参数,比较四种情况下特征参数的变化,验证了理论分析的正确性。     

Tool condition monitoring based on numerous signal features

This paper presents a tool wear monitoring strategy based on a large number of signal features in the rough turning of Inconel 625. Signal features (SFs) were extracted from time domain signals as well as from frequency domain transforms and their wavelet coefficients (time–frequency domain). All of them were automatically evaluated regarding their relevancy for tool wear monitoring based on a determination coefficient between the feature and its low-pass-filtered course as well as the repeatability. The selected SFs were used for tool wear estimation. The accuracy of this estimation was then used to evaluate the sensor and signal usability.     

基于云理论与LS-SVM的刀具磨损识别方法

针对刀具磨损过程中产生声发射信号的不确定性以及神经网络学习算法收敛速度慢、易陷入局部极小值、对特征要求较高等问题,提出了基于云理论和最小二乘支持向量机的刀具磨损状态识别方法。首先,对声发射信号进行小波包分解与重构,滤除干扰频段对求取特征参数的影响;其次,对重构后的信号利用逆向云算法提取云特征参数:期望、熵、超熵,分析刀具磨损声发射信号的云特性及磨损状态与云特征参数之间的关系;最后,将云特征参数组成特征向量送入最小二乘支持向量机进行识别。研究结果表明:所提取的特征可以很好地反映刀具的磨损状态,云-支持向量机方法可以有效地实现刀具磨损状态的识别,与传统神经网络识别方法相比具有更高的识别率,识别率达到96.67%。     

基于神经网络的多特征融合刀具磨损量识别

采用切削力信号监测钻削过程钻头的磨损量 ,分别从时域、频域提取了切削力信号的均值、方差、峭度系数和特定频段能量作为刀具磨损的特征信号 ,讨论了特征信号随着刀具磨损量增加的变化规律 ,并将各个特征信号构成的特征矢量输入多层反传神经网络进行融合 ,实现钻削过程刀具磨损量的智能识别。试验结果表明该方法能有效实现多特征融合 ,但识别精度和推广能力有待进一步提高     

Detecting discharge status of small-hole EDM based on wavelet transform

Discharge waveforms contain information representing the gap discharge status of an EDM process. The gap discharge status has a great influence on the machining performance including the machining efficiency, workpiece surface integrity, and tool wear rate in EDM processes. In order to identify the gap discharge status effectively, wavelet transform is used to analyze the discharge waveforms. A data acquisition and processing system based on DSP is developed for high-speed wavelet transforms and related calculations. The wavelet transform result shows that each EDM pulse can be classified by judging the approximation coefficients of the wavelet transform result. Experimental results demonstrate that the wavelet transform detection is capable of capturing the primary features of each single discharge pulse, which are usually unable to be discovered by conventional discharge detection methods such as the average gap voltage detection. By analyzing the local extreme values of approximation coefficients, the numbers of different pulses within a detection time period can be identified. The gap discharge status coefficient, which is a function of the numbers of different pulses, is then calculated and used as a feedback signal to an adaptive EDM process controller. A small-hole machining test demonstrates that, with the online adaptive controller based on the wavelet transform method, the machining efficiency and stability are improved significantly.     

Cutting force-based real-time estimation of tool wear in face milling using a combination of signal processing techniques

In this paper, combinations of signal processing techniques for real-time estimation of tool wear in face milling using cutting force signals are presented. Three different strategies based on linear filtering, time-domain averaging and wavelet transformation techniques are adopted for extracting relevant features from the measured signals. Sensor fusion at feature level is used in search of an improved and robust tool wear model. Isotonic regression and exponential smoothing techniques are introduced to enforce monotonicity and smoothness of the extracted features. At the first stage, multiple linear regression models are developed for specific cutting conditions using the extracted features. The best features are identified on the basis of a statistical model selection criterion. At the second stage, the first-stage models are combined, in accordance with proven theory, into a single tool wear model, including the effect of cutting parameters. The three chosen strategies show improvements over those reported in the literature, in the case of training data as well as test data used for validation—for both laboratory and industrial experiments. A method for calculating the probabilistic worst-case prediction of tool wear is also developed for the final tool wear model.     

Tool wear monitoring in ramp cuts in end milling using the wavelet transform

Tool wear identification and estimation present a fundamental problem in machining. With tool wear there is an increase in cutting forces, which leads to a deterioration in process stability, part accuracy and surface finish. In this paper, cutting force trends and tool wear effects in ramp cut machining are observed experimentally as machining progresses. In ramp cuts, the depth of cut is continuously changing. Cutting forces are compared with cutting forces obtained from a progressively worn tool as a result of machining. A wavelet transform is used for signal processing and is found to be useful for observing the resultant cutting force trends. The root mean square (RMS) value of the wavelet transformed signal and linear regression are used for tool wear estimation. Tool wear is also estimated by measuring the resulting slot thickness on a coordinate measuring machine.     

FUZZY RADIAL BASIS FUNCTION (FRBF) NETWORK BASED TOOL CONDITION MONITORING SYSTEM USING VIBRATION SIGNALS

Thriving automation in industries leads to more research on the tool condition monitoring systems for better accuracy and fast recognition/evaluation of tool wear. Research on the applicability of the new advances in the soft-computing as well as in the signal processing fields is the inevitable consequence. In this work, a new soft-computing modeling technique, fuzzy radial basis function (FRBF) network has been applied to the prediction of drill wear using the vibration signal features. This work presents the wear prediction performance comparison of this new model with three other already tried and established soft-computing models, such as back propagation neural network (BPNN), radial basis function network (RBF) and normalized radial basis function network (NRBF), for both time-domain as well as wavelet packet approaches of feature extraction. Experimental results show that FRBF model with wavelet packet approach produces the best performance of predicting flank wear.     

基于切削力信号时域频域特征融合的刀具磨损监测

从时域、频域提取了切削力信号特征参数随着刀具磨损量增加的变化规律,提取了切削力信号的峰值因子、Kurtosis系数和频段带能量作为刀具磨损量监测特征参数,并将各个特征量构成的特征矢量输入改进的多层反传神经网络进行融合,实现钻削过程刀具磨损量的智能识别。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。     

基于连续小波变换的钻削力信号灰度矩特征提取

利用小波分析良好的时频特性,分析了钻削过程中钻削力信号在时间-尺度域中的变化特征,提出用“灰度矩”的概念来描述连续小波变换的统计特性,并通过实验研究了整个钻头磨损历程中钻削力信号小波变换结果的“1 1”阶矩的变化规律。结果表明:随着钻头磨损的增加,其“1 1”阶矩统计特征呈上升趋势,根据其变化特征可有效实现钻头磨损状态的监测。