基于EMD多尺度威布尔分布与HMM的轴承性能退化评估方法

轴承作为旋转机械中的重要部件,对其性能退化状态进行准确评估是开展预测性维护的重要前提.针对现有性能退化指标在鲁棒性和敏感性上的不足,提出一种基于多尺度威布尔分布与隐马尔可夫模型(Hidden Markov model,HMM)的滚动轴承性能退化评估方法.首先,采用经验模态分解(empirical mode decomp...     

小波包变换和隐马尔可夫模型在轴承性能退化评估中的应用

轴承是旋转机械中的关键部件,有效地对其进行性能退化评估对指导设备维护、防止设备意外失效有非常重要的意义。本文提出了一种基于小波包变换和隐马尔可夫模型（HMM）的轴承性能退化评估方法。该方法使用小波包变换对轴承振动信号进行分析,并提取节点能量及其总能量作为特征,仅使用正常状态下的数据训练HMM,建立性能退化评估模型,然后使用该模型对轴承的退化程度进行定量评估。最后,通过对轴承加速疲劳寿命试验的研究,验证了所提出的方法的可行性和有效性。     

基于MMFE和可拓k-medoids聚类的轴承性能退化评估EI北大核心CSCD

传统轴承性能退化评估常为定性分析,且多以垂向振动信号为对象,忽略了不同方向振动信息之间的相关性。将评价多通道时间序列复杂度的多元多尺度熵引入到轴承运行状态的特征提取,构建多元多尺度模糊熵特征来考虑轴承不同方向振动信息之间的关联性。结合k-medoids算法和可拓学理论建立了轴承性能退化的定量评估模型。通过对轴承正常状态样本进行k-medoids聚类得到聚类中心,根据样本点与聚类中心之间的欧式距离确定可拓集合的边界,进一步利用可拓关联函数构建轴承性能退化评估模型,并采用轴承全寿命疲劳试验进行了验证。试验结果表明,本文所提方法能有效识别轴承的早期性能退化,并能实现对轴承性能退化程度的定量评估。     

基于小波包熵和高斯混合模型的轴承性能退化评估

为准确的描述设备性能退化的过程,采用小波包熵(Wavelet packet entropy, WPE)与高斯混合模型(Gaussian mixture model,GMM)对轴承性能退化状态进行评估。首先,提取轴承振动信号的小波包熵作为特征向量。接着以轴承正常状态数据的特征向量建立轴承性能的GMM评估基准模型。然后对试验中每一运行状态建立相应的GMM模型,并计算对应状态GMM相对基准模型的偏离程度,判断轴承是否发生退化以及退化程度。试验分析表明,与基于逻辑回归的设备性能退化方法相比,基于小波包熵与高斯混合模型的设备性能退化方法无需设备历史数据,不需要定义退化先验概率,能够较准确的反映轴承在全寿命周期中性能退化的过程。     

基于性能衰退评估的轴承寿命状态识别方法研究

针对滚动轴承退化性能难以评估、寿命状态难以识别的难题,提出一种基于性能衰退评估的轴承寿命状态识别新方法,该方法基于卷积自编码器(convolutional autoencoder,CAE)与多维尺度分析(multidimensional scaling,MDS)算法构建轴承性能衰退指标,再根据构建指标和改进卷积神经网络(convolutional neural network,CNN)建立轴承寿命状态识别模型,实现轴承寿命状态识别。将轴承信号样本输入CAE,实现轴承寿命状态特征的自动提取与表达,再将所提取的特征通过MDS算法进行约简获得低维特征,在低维特征空间构造欧氏距离作为轴承性能衰退指标,依据指标实现轴承数据标签化。使用标签化的轴承数据训练CNN,建立轴承寿命状态识别模型。在训练过程中,为抑制过拟合,对原始训练样本进行加噪处理,为提高模型抗干扰能力,将Leaky ReLU(LReLU)函数和dropout作为激活函数。运用轴承全寿命试验数据对识别模型进行检验,通过对比验证,结果表明所提出的轴承寿命状态识别方法能更准确的实现轴承寿命状态识别。     

基于DPMM-CHMM的机械设备性能退化评估研究

针对传统的HMM模型状态数必须预先设定的不足,提出了一种基于DPMM-CHMM的机械设备性能退化评估方法。该方法利用DPMM模型的自动聚类功能,实现了模型结构根据观测数据的自适应变化和动态调整,获得设备运行过程中的最优退化状态数,并结合CHMM良好的分析和建模能力,得到设备退化状态转移路径,实现机械设备运行过程中的退化状态识别和性能评估,并利用滚动轴承全寿命数据进行了应用研究。结果表明,该方法可以有效地识别轴承运行中的不同退化状态,为基于状态的设备维修提供了理论指导。     

基于JRD和CUSUM的滚动轴承性能退化状态识别与评估

退化特征提取是滚动轴承性能退化状态识别和评估的关键,JRD克服了传统特征无法准确反应轴承当前技术状态的不足,但在全寿命阶段上稳定性、单调性差,应用累积和(CUSUM)对其进行改进,从而准确识别和评估轴承性能退化状态。应用小波包变换对原始信号进行降噪;计算不同技术状态下信号的Renyi熵,并对比与标准状态的相似程度得出JRD值,作为滚动轴承退化状态特征;应用CUSUM增强JRD值对于寿命微弱变化的敏感性及轴承全寿命的单调性。通过试验验证,滚动轴承性能退化状态的识别率能达到100%,同时能够分阶段、单调性地评估轴承性能退化状态。     

基于CHMM的齿轮箱状态识别研究

针对离散隐Markov模型(HMM)在状态识别中的不足,结合齿轮箱全寿命实验数据,研究了基于连续隐Markov模型(CHMM)的状态识别方法。建立了基于齿轮箱原始振动信号的CHMM状态识别框架,提出了基于K均值算法和交叉验证相结合的状态数优化方法,通过计算待确定观测数据的极大似然概率值来确定齿轮箱当前状态。结果表明,用原始振动信号作为CHMM的输入可以实现状态识别,验证了模型的有效性,为齿轮箱基于状态的维修提供了科学依据。     

小波包-支持向量数据描述在轴承性能退化评估中的应用研究

轴承是旋转机械中的关键部件,相对于故障模式识别,性能退化评估可以更为有效地服务于设备主动维护以实现零停机率。小波包分解可以对信号进行更为精细的刻画,基于统计学习理论的支持向量数据描述是一种具有良好计算性能的单值分类方法。基于此,本文提出了一种基于小波包－支持向量数据描述的轴承性能退化评估方法,该方法以小波包分解的节点能量构成特征向量,仅需要正常状态下的数据样本即可用支持向量数据描述建立知识库,在一定程度上实现了对待测样本退化程度的定量评估。通过应用于轴承不同点蚀大小和其加速疲劳寿命试验的全寿命周期,验证了所提出方法的可行性和有效性。     

基于LFSS和改进BBA的滚动轴承在线性能退化评估特征选择方法

在滚动轴承性能退化评估中,不同工况会影响振动信号特征对故障程度的敏感性,在早期有限样本中选择适用于状态评估的有效特征是实现在线评估轴承性能退化程度的关键。首先提出一种基于均方根的早期有限样本判定方法 Limited Feature Select Sample(LFSS),其次提出一种针对性能退化评估特征选择的改进Binary Bat Algorithm(BBA)算法——Feedback Seeking Binary Bat Algorithm(FSBBA),将其应用于滚动轴承早期有限样本中进行故障特征选择,克服了原始BBA容易陷入局部寻优的缺点。基于LFSS与FSBBA算法,构建了滚动轴承在线状态评估模型,并将其运用于两例滚动轴承全寿命数据特征选择,性能退化评估指标分析结果表明了所提出方法的有效性。     

基于AR模型的Kolmogorov-Smirnov检验性能退化及预测研究

设备性能退化评估是对现有故障诊断技术的全新拓展,它为更有效地实现智能主动维护提供参考,更有利于实现设备的零停机率。开展对设备的性能退化评估研究,还可以实现对设备的性能预测维护功能,大大提高设备运行的可靠性。提出了基于AR预测白噪化的Kolmogorov-Smirnov检验方法,同时实现了滚动轴承的全寿命实验。通过对轴承全寿命实验数据的分析研究,论证了本方法在设备性能退化评估及预测中的研究价值,相对于有效值等传统方法,它不仅能够显著地表现前期的微弱退化状态,而且还能有条件地更早指示设备的异常状态,对于故障预测的研究具有较大的意义。     

滚动轴承的振动性能退化过程与保持可靠性研究

为了分析滚动轴承的振动性能退化过程与保持可靠性之间的关系,提出一种基于最大熵法和相似度法的滚动轴承振动性能退化模型,并对滚动轴承的退化过程进行评估;然后基于最大熵法和泊松过程建立滚动轴承振动性能保持可靠性模型;最后基于灰关系理论对滚动轴承的性能退化序列和保持可靠性序列进行分析。实验结果表明,所提出的滚动轴承振动性能退化模型能够有效地识别滚动轴承的退化状态,并且滚动轴承振动性能保持可靠性的演变历程与振动性能退化过程之间有明显的灰关系,可信水平均达到80%以上。     

Designing optimal degradation tests via multi-objective genetic algorithms

The experimental determination of the failure time probability distribution of highly reliable components, such as those used in nuclear and aerospace applications, is intrinsically difficult due to the lack, or scarce significance, of failure data which can be collected during the relatively short test periods. A possibility to overcome this difficulty is to resort to the so-called degradation tests, in which measurements of components' degradation are used to infer the failure time distribution. To design such tests, parameters like the number of tests to be run, their frequency and duration, must be set so as to obtain an accurate estimate of the distribution statistics, under the existing limitations of budget. The optimisation problem which results is a non-linear one. In this work, we propose a method, based on multi-objective genetic algorithms for determining the values of the test parameters which optimise both the accuracy in the estimate of the failure time distribution percentiles and the testing costs. The method has been validated on a degradation model of literature.     

基于改进HMM和Pearson相似度分析的滚动轴承自适应寿命预测方法

基于数据驱动思想,提出了一种相同工况下的滚动轴承寿命预测方法。针对轴承全寿命监测数据,根据K-means聚类算法划分轴承运行状态空间,考虑到隐马尔科夫模型主链为状态链的不足,对状态转移矩阵重新定义,将主链改进为寿命链,建立了基于改进HMM的全寿命状态驻留时间模型;将观测轴承数据、实时与建模数据进行Pearson相似度分析,构造寿命比例调节系数,实现寿命模型参数的动态修正和观测轴承寿命的自适应预测。采用美国辛辛那提大学实验中心轴承试验数据开展了应用研究,通过一组轴承全寿命数据实现了对其它轴承不同阶段及全寿命的预测,与传统的隐马尔科夫模型、灰色模型预测等方法预测结果相比,所提算法兼具较好的预测准确性和模型的泛化性。     

Combination of probability approach and support vector machine towards machine health prognostics

This study presents a combined method of the probability approach and support vector machine (SVM) to predict failure degradation based on simulated and experimental failure bearing data. The failure rate as a degradation parameter is calculated using the Cox-proportional hazard model and the reliability theory based on simulated and experimental data. Kurtosis is used to show the bearing condition under specified operating conditions up to final failure occurrence. For simulated data, a failure degradation is calculated using the Cox model, where the baseline hazard is assumed having Weibull probability. In the case of experimental data, a reliability formula is employed to estimate the failure degradation of the bearing based on run-to-failure datasets. Both failure degradations are regarded as target vectors which indicate the bearing health to failure condition. Moreover, an SVM is employed as an artificial intelligence prognostics method and trained by kurtosis and the target vector to build the prediction model. The trained SVM is then utilized to predict the final failure time of individual bearing data. The result shows that the proposed method has the potential to be a machine health prognostics framework.     

Probabilistic life analysis of vital components considering multistage degradation under variable working conditions

The lifespan of a mechanical product is related to its working conditions; the product's performance typically shows a multistage degradation pattern throughout its life profile. The performance degradation is generally researched under constant test conditions, while the effects of different working conditions on life are seldom considered. This paper proposes a staged recursive derivation method for the multistage degradation under variable working conditions. The proposed method works by merging measured degradation data with an empirical degradation model. The measured degradation data of a new prototype are utilized to update the staged degradation model based on a Bayesian posterior probability analysis. The staged degradation model is derived stage by stage, and then the probabilistic life of the new prototype is predicted. The degradation data of a machine‐gun barrel are used as a case study to demonstrate and validate the proposed method. The results show that the probabilistic life of the test prototype can be predicted effectively in the case of relatively little measured degradation data at the product development stage. Furthermore, the proposed method appears to be especially suited to mechanical components requiring short test periods or low test costs.     

同步抽取变换与复小波结构相似性指数的滚动轴承性能退化评估

为更早地检出滚动轴承异常并量化其性能退化程度,该研究提出同步抽取变换与复小波结构相似性(SET-CWSS)指数的滚动轴承性能退化评估新方法。利用同步抽取变换(SET)对当前时刻的振动信号进行时频分析,以获得能量更加集中的时频图,将SET后得到的时频图与刚投入运行时无故障振动信号的SET时频图进行复小波结构相似性(CWSS)评价,得到当前时刻滚动轴承性能退化评估SET-CWSS指数。通过疲劳试验验证及与其他性能退化评估方法对比,结果表明:SET-CWSS指数能有效的刻画出滚动轴承性能退化过程、量化评估其性能退化程度且对滚动轴承早期异常更加敏感。     

Degradation modeling and classification of mixed populations using segmental continuous hidden Markov models

With the market demands, the classification for highly reliable products becomes more and more significant. The degradation data can provide information about the degradation states and can be used to classify products to various classes according to the reliability attribute. In this paper, a temporal probabilistic approach, named segmental continuous hidden Markov model (SCHMM), is proposed to tackle the problem of degradation modeling and classification for mixed populations. Separate SCHMMs are built for each class of the mixed populations. The SCHMMs can directly depict the correspondence between actual degradation and the hidden states. A novel method called self‐training algorithm for the preprocessing of the original data from the mixed populations is proposed. Furthermore, the unknown parameters of the SCHMMs are estimated by the maximum likelihood method with the complete degradation data. The root mean square error of the estimated degradation value compared with the actual physical degradation value, as well as Akaike information criterion and Bayesian information criterion, is used for the evolution of the fitting accuracy and the selection of model topologies and discretization methods. Then the maximum posterior probability‐based classification criteria are developed. Degradation tests are designed for the data collection. To obtain the optimal classification policies, a cost function that consists of the degradation test cost and misclassification cost is constructed. A numerical example is used to illustrate the proposed method and demonstrate its advantages by comparing with other classification methods.