GRINDING WHEEL CONDITION MONITORING WITH HIDDEN MARKOV MODEL-BASED CLUSTERING METHODS

Hidden Markov model (HMM) is well known for sequence modeling and has been used for condition monitoring. However, HMM-based clustering methods are developed only recently. This article proposes a HMM-based clustering method for monitoring the condition of grinding wheel used in grinding operations. The proposed method first extract features from signals based on discrete wavelet decomposition using a moving window approach. It then generates a distance (dissimilarity) matrix using HMM. Based on this distance matrix several hierarchical and partitioning-based clustering algorithms are applied to obtain clustering results. The proposed methodology was tested with feature sequences extracted from acoustic emission signals. The results show that clustering accuracy is dependent upon cutting condition. Higher material removal rate seems to produce more discriminatory signals/features than lower material removal rate. The effect of window size, wavelet decomposition level, wavelet basis, clustering algorithm, and data normalization were also studied.     

基于小波包能量谱的HMM钻头磨损监测

从工程应用的角度论述了小波包分解原理及其能量谱监测理论，并将该理论应用于钻削力信号特征提取中，针对钻削过程特征矢量与钻头磨损之间具有较强的随机性和不确定性的特点，提出一种基于隐马尔可夫模型（HMM）的钻头磨损监测方法。实验结果表明，通过对钻削力信号进行多层小波包分解，提取各频段能量谱作为特征矢量可准确刻画工艺系统随钻头磨损的演化规律，利用HMM建立的各钻头磨损状态小波包能量谱的统计模型可有效跟踪钻头磨损的发展趋势，实现钻头磨损状态和寿命的监测。     

Grinding wheel wear monitoring based on wavelet analysis and support vector machine

A novel grinding wheel wear monitoring system based on discrete wavelet decomposition and support vector machine is proposed. The grinding signals are collected by an acoustic emission (AE) sensor. A preprocessing method is presented to identify the grinding period signals from raw AE signals. Root mean square and variance of each decomposition level are designated as the feature vector using discrete wavelet decomposition. Various grinding experiments were performed on a surface grinder to validate the proposed classification system. The results indicate that the proposed monitoring system could achieve a classification accuracy of 99.39% with a cut depth of 10?μm, and 100% with a cut depth of 20?μm. Finally, several factors that may affect the classification results were discussed as well.     

基于小波包-连续HMM的故障诊断模型及应用

结合小波包分析方法适于处理非平稳信号的特点及隐马尔可夫模型(HMM)的训练样本少与可解释的优点，提出基于小波包-连续HMM故障诊断方法。通过小波包分析方法从滚动轴承振动信号中提取特征，训练连续高斯密度混合HMM，再利用训练好的HMM进行滚动轴承状态监测和故障诊断，实验结果表明该方法能利用少量样本进行训练和有效诊断。     

A weighted hidden Markov model approach for continuous-state tool wear monitoring and tool life prediction

Tool wear is one of the important indicators to reflect the health status of a machining system. In order to obtain tool’s wear status, tool condition monitoring (TCM) utilizes advanced sensor techniques, hoping to find out the wear status through those sensor signals. In this paper, a novel weighted hidden Markov model (HMM)-based approach is proposed for tool wear monitoring and tool life prediction, using the signals provided by TCM techniques. To describe the dynamic nature of wear evolution, a weighted HMM is first developed, which takes wear rate as the hidden state and formulates multiple HMMs in a weighted manner to include sufficient historical information. Explicit formulas to estimate the model parameters are also provided. Then, a particular probabilistic approach using the weighted HMM is proposed to estimate tool wear and predict tool’s remaining useful life during tool operation. The proposed weighted HMM-based approach is tested on a real dataset of a high-speed CNC milling machine cutters. The experimental results show that this approach is effective in estimating tool wear and predicting tool life, and it outperforms the conventional HMM approach.     

基于声发射信号的外圆切入磨削去除率监测

针对精密外圆切入磨削加工的在线监测需求,提出一种采用声发射信号实现轴类零件材料去除率在线监测的方法。根据声发射信号强度与磨削力之间的联系,建立了声发射信号均方根曲线的预测模型,利用该预测模型研究了砂轮进给阶段和驻留阶段磨削系统时间常数的理论计算方法,推导了声发射信号均方根曲线与工件材料去除率的关系;编写了在线监测软件,利用声发射传感器实现了精密外圆切入磨削的材料去除率预测。实验证明,所建立的声发射信号均方根曲线模型具有良好的预测精度,基于该模型能够实现磨削系统时间常数在线评估,并实现精密轴类零件材料去除率的实时在线监测。     

In-process endpoint detection of weld seam removal in robotic abrasive belt grinding process

This paper proposes a novel approach for in-process endpoint detection of weld seam removal during robotic abrasive belt grinding process using discrete wavelet transform (DWT) and support vector machine (SVM). A virtual sensing system is developed consisting of a force sensor, accelerometer sensor and machine learning algorithm. This work also presents the trend of the sensor signature at each stage of weld seam evolution during its removal process. The wavelet decomposition coefficient is used to represent all possible types of transients in vibration and force signals generated during grinding over weld seam. “Daubechies-4” wavelet function was used to extract features from the sensors. An experimental investigation using three different weld profile conditions resulting from the weld seam removal process using abrasive belt grinding was identified. The SVM-based classifier was employed to predict the weld state. The results demonstrate that the developed diagnostic methodology can reliably predict endpoint at which weld seam is removed in real time during compliant abrasive belt grinding.     

Condition monitoring and classification of rotating machinery using wavelets and hidden Markov models

Condition monitoring and classification of machinery state is of great practical significance in manufacturing industry, because it provides updated information regarding machine status on-line, thus avoiding the production loss and minimising the chances of catastrophic machine failure. In this paper, the condition classification is based on hidden Markov models (HMMs) processing information obtained from vibration signals. We present an on-line fault classification system with an adaptive model re-estimation algorithm. The machinery condition is identified by selecting the HMM which maximises the probability of a given observation sequence. The proper selection of the observation sequence is a key step in the development of an HMM-based classification system. In this paper, the classification system is validated using observation sequences based on the wavelet modulus maxima distribution obtained from real vibration signals, which has been proved to be effective in fault detection in previous research.     

FAULT DIAGNOSIS APPROACH BASED ON HIDDEN MARKOV MODEL AND SUPPORT VECTOR MACHINE

Aiming at solving the problems of machine-learning in fault diagnosis, a diagnosis approach is proposed based on hidden Markov model (HMM) and support vector machine (SVM). HMM usually describes intra-class measure well and is good at dealing with continuous dynamic signals. SVM expresses inter-class difference effectively and has perfect classify ability. This approach is built on the merit of HMM and SVM. Then, the experiment is made in the transmission system of a helicopter. With the features extracted from vibration signals in gearbox, this HMM-SVM based diagnostic approach is trained and used to monitor and diagnose the gearbox's faults. The result shows that this method is better than HMM-based and SVM-based diagnosing methods in higher diagnostic accuracy with small training samples.     

Grinding Burn Detection Based on Cross Wavelet and Wavelet Coherence Analysis by Acoustic Emission Signal

Grinding burn monitoring is of great importance to guarantee the surface integrity of the workpiece. Existing methods monitor overall signal variation. However, the signals produced by metal burn are always weak. Therefore, the detection rate of grinding burn still needs to be improved. The paper presents a novel grinding burn detection method basing on acoustic emission(AE) signals. It is achieved by establishing the coherence relationship of pure metal burn and grinding burn signals. Firstly, laser and grinding experiments were carried out to produce pure metal burn signals and grinding burn signals. No-burn and burn surfaces were generated and AE signals were captured separately. Then, the cross wavelet transform(XWT) and wavelet coherence(WTC) were applied to reveal the coherence relationship of the pure metal burn signal and grinding burn signal. The methods can reduce unwanted AE sources and background noise. Novel parameters based on XWT and WTC are proposed to quantify the degree of coherence and monitor the grinding burn. The grinding burn signals were recognized successfully by the proposed indexes under same grinding condition.     

基于HMM-SVM的故障诊断模型及应用

针对直升机减速器故障诊断中机器学习方法存在的问题，根据隐马尔可夫模型（HMM）适合于处理连续动态信号与支持向量机（SVM）适合于模式分类的长处，提出了基于HMMSVM串联结构的故障诊断模型。通过从减速箱振动信号中有效提取AR特征，利用HMM汁算未知信号与减速器各状态的匹配程度，形成特征向量提供给SVM最后判别，实验结果表明该方法优于单纯的HMM或SVM诊断方法，能利用少量训练样本有效地完成直升机减速器的故障诊断。     

基于小波变换和波形特征分析的峰电位分类

峰电位分类是细胞外记录中一个重要的技术。提出了一个基于离散小波变换和波形特征分析的新的峰电位分类方法（DWT-SFA）,同时定义了3个不同的波形特征。首先,对信号进行小波消噪处理,然后,使用这3个不同的波形特征进行信号分类。通过对大壁虎嗅觉神经信号的分类处理,证明该方法明显优于主成分分析方法。此外,通过对该方法与Offline Sorter软件的分类对比,也验证了它的正确性和精确性。     

Real-time detection of the breakage of small diameter drills with wavelet transform

This paper presents a real-time tool breakage detection method for small diameter drills using acoustic emission (AE) and current signals. Using the transmitted properties of the AE signal, apparatus for detecting the AE signal for tool breakage monitoring was developed for a machine centre. The features of tool breakage were obtained from the AE signal using typical signal processing methods. The continuous wavelet transform (CWT) and the discrete wavelet transform (DWT) were used to decompose the spindle current signal and the feed current signal, respectively. The tool breakage features were extracted from the decomposed signals. Experimental results show that the proposed monitoring system possessed an excellent real-time capability and a high success rate for the detection of the breakage of small diameter drills using combined AE and current signals.     

Subspace-based gearbox condition monitoring by kernel principal component analysis

Feature extraction is a key step for gearbox condition monitoring. The statistical features of the measured vibrations can be used to characterise gearbox conditions; however, their regularity and sensitivity in pattern space are different and may vary considerably under different operating conditions. This paper addresses the non-linear feature extraction scheme from the time-domain features with wavelet packet preprocessing and frequency-domain features of the vibration signals using the kernel principal component analysis (KPCA). Then two different KPCA-based subspace structures are constructed for representing and classifying the gearbox conditions. The proposed methods can extract the non-linear features of gearbox conditions using KPCA effectively, and perform conveniently with low computational complexity based on subspace methods. Experimental analysis with a fatigue test of an automobile transmission gearbox shows that the KPCA features outperform PCA features in terms of clustering capability, and both the two KPCA-based subspace methods can be effectively applied to gearbox condition monitoring.     

基于时间特征分割和降维谱聚类的液压系统内泄漏故障诊断

针对数据量较小情况下的液压系统内泄漏的故障诊断问题,提出基于时间特征分割和降维谱聚类的故障诊断方法.使用db4小波对液压压力信号进行间断点检测,分割出高压平稳段的时域信号并提取其时域和小波域特征,然后通过主成分分析的方式提取有效特征剔除分敏感特征,最后使用谱聚类对泄漏的严重程度进行诊断.分别在液压缸、液压泵和换向阀上进...     

基于AR-连续HMM的故障诊断模型及应用

在状态监测与故障诊断中,被测设备的状态一般不能直接观察到,要通过测量被测设备的表现来感知,这和隐马尔可夫模型(HMM)在本质是相通的。因此可以利用连续高斯密度混合HMM分析被测设备的振动信号,首先以AR模型系数为特征,研究不同状态数与不同混合高斯数对HMM模型分类的影响,再利用较优的状态数与混合高斯数HMM模型进行状态监测和故障诊断,诊断与对比实验结果表明该方法能利用少量样本进行训练和有效诊断。     

DHMM＋SVM在切削颤振中的应用

根据切削颤振的特点,结合隐马尔可夫模型（Hidden Markov Model,HMM）和支持向量机（Support Vector Machine,SVM）的特点,提出了一种新的状态预测技术,同时也提出了一种新的特征提取方法。首先在等时间间隔内对切削信号实时进行小波包分解,然后通过SVM对各频带区间能量变化趋势进行回归预测,最后通过HMM对预测结果进行分类。结果表明,该方法取得了较好的预测结果。     

基于小波包分解的脑电信号特征提取

在脑机接口研究中,针对脑电信号的特征抽取,提出一种基于小波包分解的方法,利用Fisher距离准则,选择具有较大可分离性的特定子带小波包系数和能量作为有效特征,构成特征矢量,并采用BCI2003竞赛数据,通过对该特征矢量的可分性和识别精度2个指标的评估,表明了所提出方法的有效性。     

采用小波神经网络的刀具故障诊断

为了有效的进行刀具状态监测，采用小波神经网络的松散型结合对刀具进行故障诊断。通过小波变换提取刀具磨损声发射（AE）信号的特征．即对AE信号进行小波分解，提取了5个频段的均方根值作为神经网络的输入，来识别刀具磨损状态。试验表明，均方根值完全可以作为刀具磨损过程中产生AE信号的特征向量。仿真结果表明，基于小波神经网络的刀具故障诊断对刀具磨损状态的识别效率高．该方法是有效的。     

基于小波—奇异值分解差分谱的弱故障特征提取方法

对于一些复杂信号中的弱故障特征信息,以往的两种小波—奇异值分解(Singular value decompositiom,SVD)组合模式的特征提取效果不佳,从小波的频率窗特性出发分析了出现这种问题的原因,进而对复杂信号的奇异值分布规律进行研究,据此提出一种新的小波-SVD差分谱组合模式。对原始信号做小波分解得到一系列细节信号后,不再将这些信号简单地排列成矩阵,而是利用每个细节信号构造特定结构的Hankel矩阵,再通过SVD对每个矩阵做正交化分解,并利用奇异值差分谱来选择特征奇异值进行SVD重构,由此实现对弱故障特征信息的提取。对一个轴承振动信号的处理结果证实该方法对复杂信号中的弱故障特征信息具有优良的提取效果,其获得的故障特征波形非常清晰,克服了以往小波-SVD组合模式对弱故障特征提取效果不佳的缺陷。