Enhanced diagnostics using orthogonal de-noising based nonlinear discriminant analysis and its application to multivariate data

Many multivariate statistical techniques have been developed to solve fault diagnosis problems for productivity and quality improvement. Recently, nonlinear kernel techniques (e.g. support vector machines) have been successfully applied to a number of applications such as bio-informatics, face recognition, handwritten digit recognition, etc. The basis of these techniques is to map input data into a nonlinear space; these mapped data are then analysed. Using the kernel trick on these methods makes it possible to develop powerful kernel-based nonlinear techniques and to extract information from the mapped data. This paper proposes a new diagnosis method based on kernel Fisher discriminant analysis (KFDA), a nonlinear kernel technique. It utilizes KFDA to extract nonlinear patterns of data effectively. In addition, an orthogonal de-noising technique, called orthogonal signal correction, is incorporated into the proposed framework and used as a pre-processing step. This de-noising is executed before KFDA modeling in order to remove unwanted variation of data. A case study on two processes has been conducted. The proposed method produced reliable diagnosis results and the use of KFDA modeling combined with the orthogonal de-noising technique was able to improve the classification performance.     

HHT统计特征在航空发动机振动分析中的应用

航空发动机振动信号包含了多种振源的振动信号和大量的噪声分量。通过对其进行Hilbert-Huang变换, 将复杂信号分解为代表不同物理意义的单分量固有模态函数（Intrinsic Mode Functions, IMF）,然后对每一个IMF子带信号提取基于能量加权的广义粗糙度特征实现对振动信号的描述。最后将上述特征送入SVM分类器进行训练,根据分类器的输出结果确定航空发动机的工作状态和故障类型。通过对实测航空发动机试车时得到的振动信号的实验分析结果表明,该算法可以有效地识别发动机的振动故障。     

基于商空间和支持向量机的滚动轴承故障智能诊断

针对滚动轴承故障诊断中存在的故障类型多样且有效特征难以选取等问题,提出了一种基于商空间和支持向量机的智能诊断模型。该模型利用商空间的粒化分层思想将输入样本按照不同等价关系进行粒化分层,并对每一粒度层的时域和频域特征进行约简,然后将每一层约简后的特征向量输入到支持向量机进行状态识别,最后对各粒度层状态识别结果加权融合得到最终结果。利用轴承全寿命试验数据对该模型进行验证,识别精度达到96.92%。     

基于EMD和AR模型的滚动轴承故障诊断方法

提出了基于EMD(Empirical Mode Decomposition)和AR模型的滚动轴承故障诊断方法。该方法用EMD将滚动轴承振动信号分解成若干个平稳的IMF(Intrinsic Mode Function)分量，对每一个IMF分量建立AR模型，以模型的自回归参数和残差的方差作为特征向量建立Mahalanobis距离判别函数，进而判断滚动轴承的工作状态和故障类型。实验结果分析表明，该方法能有效地应用于滚动轴承的故障诊断。     

基于SVDD和距离测度的齿轮泵故障诊断方法研究

提出了一种基于支持向量域描述和距离测度的齿轮泵故障诊断方法。该方法首先对齿轮泵各种工况下的振动信号进行小波包分解,提取各频带能量百分比作为特征向量;然后仅利用正常工况下的特征向量训练SVDD超球模型,通过定义绝对距离测度检测齿轮泵状态是否出现异常;最后针对每类工况下的特征向量单独训练SVDD超球模型,通过定义相对距离测度准确定位齿轮泵的不同故障工况。试验结果表明,采用小波包频带能量降低了数据维数,有效浓缩了故障信息;基于绝对距离测度和相对距离测度的SVDD故障诊断方法既能检测异常状态,又能区分各种故障工况,达到了状态监测和故障分类识别的目的。     

基于G-DPSO算法的决策树轴承故障诊断方法

针对机械设备状态监测与故障诊断技术中特征提取对诊断准确性的局限,从原始故障信号数据中提取出尽可能多的有用信息。提出通过最佳特征数据集对轴承故障进行诊断分析,分别从幅域和频域对故障数据进行特征提取。采用一种改善的粒子群(G-DPSO)算法对提取的特征数据集进行筛选,对传统粒子群算法权重系数进行优化,同时和故障诊断需要的决策树模型的信息熵增相结合,可以达到将最适合故障诊断的特征向量提取出来的目的。用5种轴承故障数据对所提方法进行实验分析,诊断正确率能达到97%之上,证明所提出的方法是有效、可靠的。     

基于圆域分析的大型回转支承初期故障诊断

为解决真实工况下大型回转支承振动信号背景噪声大、常用故障诊断方法难以适用的问题,提出了一种基于圆域分析的振动信号处理方法。将时域信号进行圆域转换,并按一定角度将转换后的圆域信号划分成多个区域;判断各区域信号邻域相关离散点拟合椭圆的倾角方向,得到回转支承整圈对应的多个异常向量;以异常向量的平均向量作为圆域分析的特征向量,分析其均值、方差、歪度和峭度指标的变化情况,实现回转支承的故障诊断。对某型号回转支承进行了加速寿命试验,结果表明,该方法能够有效诊断出回转支承滚道的区域滑移、点蚀等初期故障,相比常见的时域特征、小波分析等方法准确度更高,故障可识别度更强,因此可以用于实际工况下回转支承的故障诊断。     

基于EMD的奇异值分解技术在滚动轴承故障诊断中的应用

针对滚动轴承故障振动信号的非平稳特征,提出了一种基于经验模态分解(EmpiricalModeDecomposition,简称EMD)和奇异值分解技术的滚动轴承故障诊断方法。该方法首先采用EMD方法将滚动轴承振动信号分解为多个平稳的内禀分量(IntrinsicModefunction,简称IMF)之和,并形成初始特征向量矩阵。然后对初始特征向量矩阵进行奇异值分解得到矩阵的奇异值,将其作为滚动轴承振动信号的故障特征向量,并输入神经网络来识别滚动轴承的工作状态和故障类型。实验分析结果表明,本文方法能有效地应用于滚动轴承故障诊断。     

Variable-weighted PLS

In multivariate calibration methods like partial least squares (PLS), especially when the spectra data consists of measurements at hundreds and even thousands of analytical channels, it is widely accepted that before a multivariate regression model is built, a well-performed variable selection can be helpful to improve the predictive ability of the model. In the present paper, the idea of variable selection is extended. Unlike in traditional variable selection methods, where the deleted variables and the variables included in the regression model are essentially weighted with discrete values 0 and 1, respectively, the strategy adopted in this paper is to weight the variables with continuous non-negative values. A recently proposed global optimization method, particle swarm optimization (PSO) algorithm is used to search for the weights of variables optimizing the training of a calibration set and the prediction of an independent validation set. Since variable selection is just a special case of variable weighting, the latter is expected to be more rational and flexible. Variable weighting would reduce the negative influence of wavelengths with undesirable qualities while retaining the useful information carried by them. Variable weighting would also prevent the possible spoiling of the multi-channel advantage of the model by variable selection, which would happen when the number of selected wavelengths is small. Two real data sets are investigated and the results of variable-weighted PLS and those of PLS are compared to demonstrate the advantages of the proposed method.     

基于支持向量机的齿轮故障诊断方法研究

故障样本的不足从一定程度上制约了基于知识的方法在实际故障诊断中的应用，针对这一问题，利用支持向量机在小样本情况下具有较强分类能力的特点，提出了一种基于支持向量机的齿轮故障诊断方法。该方法采用小波变换对齿轮的振动信号进行处理来构造特征向量，并直接输入到支持向量机的多故障分类器中进行故障识别。试验结果表明该方法是有效、可行的，且在小样本情况下比BP神经网络具有更高的诊断精度。     

基于EMD的奇异值熵在转子系统故障诊断中的应用

提出了一种基于EMD（Empirlcal Mode Decomposition）和奇异值熵的转子系统故障诊断方法。该方法首先用EMD方法分解转子系统的振动信号，得到若干个基本内禀模式函数（Intrinsic Mode Function，简称IMF），然后利用IMF分量形成初始特征向量矩阵，并对初始特征向量矩阵求奇异值熵，奇异值熵的大小反映了转子系统运行状态的差别，从而可以通过奇异值熵的大小判断转子系统的工作状态和故障类型。对实验数据的分析结果证明了该方法的有效性。     

WDBM: Weighted Deep Forest Model Based Bearing Fault Diagnosis Method

In the research field of bearing fault diagnosis, classical deep learning models have the problems of too many parameters and high computing cost. In addition, the classical deep learning models are not effective in the scenario of small data. In recent years, deep forest is proposed, which has less hyper parameters and adaptive depth of deep model. In addition, weighted deep forest (WDF) is proposed to further improve deep forest by assigning weights for decisions trees based on the accuracy of each decision tree. In this paper, weighted deep forest model-based bearing fault diagnosis method (WDBM) is proposed. The WDBM is regard as a novel bearing fault diagnosis method, which not only inherits the WDF’s advantages-strong robustness, good generalization, less parameters, faster convergence speed and so on, but also realizes effective diagnosis with high precision and low cost under the condition of small samples. To verify the performance of the WDBM, experiments are carried out on Case Western Reserve University bearing data set (CWRU). Experiments results demonstrate that WDBM can achieve comparative recognition accuracy, with less computational overhead and faster convergence speed.     

基于熵-流特征和樽海鞘群优化支持向量机的故障诊断方法

针对旋转机械设备故障特征提取困难的问题,提出一种熵-流特征和樽海鞘群优化支持向量机(salp swarm optimization support vector machine,SSO-SVM)的故障诊断方法。利用改进多尺度加权排列熵(improved multiscale weighted permutation entropy,IMWPE)提取机械设备不同工况下的故障特征;采用监督等度规映射(S-Isomap)流形学习进行降维处理,获取低维的熵-流特征集;将熵-流特征输入至SSO-SVM多故障分类器进行识别与诊断。行星齿轮箱故障诊断实验分析结果表明:IMWPE+S-Isomap熵-流特征提取方法优于现有的多尺度排列熵(multiscale permutation entropy,MPE)、多尺度加权排列熵(multiscale weighted permutation entropy,MWPE)和IMWPE等熵值特征提取方法以及IMWPE+等度规映射(Isomap)和IMWPE+线性局部切空间排列(linear local tangent space alignment,LLTSA)等熵-流特征提取方法;樽海鞘群算法对支持向量机参数寻优效果优于粒子群、灰狼群、人工蜂群和蝙蝠群等算法;所提故障诊断方法识别精度达到100%,能够有效诊断出行星齿轮箱各工况类型。     

基于部分集成局部特征尺度分解与拉普拉斯分值的滚动轴承故障诊断模型

提出了一种基于部分集成局部特征尺度分解(Partly ensemble local characteristic-scale decomposition,PELCD)、拉普拉斯分值(Laplacian score,LS)特征选择和基于变量预测模型模式分类(Variable predictive model based class discrimination,VPMCD)的滚动轴承故障诊断模型。PELCD是新提出的一种基于噪声辅助数据分析方法,克服了局部特征尺度分解的模态混淆问题,与传统的基于噪声辅助数据分析方法相比有一定的优越性,论文将其应用于滚动轴承振动信号的预处理。之后提取振动信号PELCD分量的时域和频域统计特征及振动信号的时频联合域特征;同时为了降低特征向量维数,提高诊断效率,采用LS优化特征向量。再将优化的特征向量输入到VPMCD分类器进行训练和测试。滚动轴承实验数据分析结果表明该模型能够有效地诊断故障程度和故障类型。     

基于EMD能量熵和支持向量机的齿轮故障诊断方法

针对齿轮振动信号的非平稳特征和现实中难以获得大量典型故障样本的实际情况,提出了基于经验模态分解（empirical mode decomposition,EMD)和支持向量机的齿轮故障诊断方法。首先通过EMD方法将非平稳的原始加速度振动信号分解成若干个平稳的本征模函数(intrinsic mode function, IMF);齿轮发生不同的故障时,在不同频带内的信号能量值会发生改变,故可以通过计算不同振动信号的EMD能量熵判断是否发生故障;从包含有主要故障信息的IMF分量中提取出来的能量特征作为输入建立支持向量机（support vector machine,SVM）,判断齿轮的工作状态和故障类型。实验结果表明,文中提出的方法能有效地应用于齿轮的故障诊断。     

Weighted compression of spectral color information

Spectral color information is used nowadays in many different applications. Accurate spectral images are usually very large files, but a proper compression method can reduce needed storage space remarkably with a minimum loss of information. In this paper we introduce a principal component analysis (PCA) -based compression method of spectral color information. In this approach spectral data is weighted with a proper weight function before forming the correlation matrix and calculating the eigenvector basis. First we give a general framework for how to use weight functions in compression of relevant color information. Then we compare the weighted compression method with the traditional PCA compression method by compressing and reconstructing the Munsell data set consisting of 1,269 reflectance spectra and the Pantone data set consisting of 922 reflectance spectra. Two different weight functions are proposed and tested. We show that weighting clearly improves retention of color information in the PCA-based compression process.     

基于微分经验模式分解和隐马尔科夫模型的滚动轴承故障诊断方法

提出基于微分经验模式分解（DEMD）和隐马尔科夫模型(HMM）的旋转机械故障诊断方法,并应用到滚动轴承故障诊断中。首先,对故障信号进行基于微分的经验模式分解,提取瞬时能量作为故障特征向量;然后将故障特征向量输入HMM分类器进行模式识别,输出各状态似然概率值;以最大似然概率所对应的故障状态作为诊断结果,最终实现滚动轴承故障诊断。滚动轴承点蚀故障的诊断实验证明了该方法的有效性。与基于EMD-HMM的故障诊断方法相比,基于DEMD-HMM的故障诊断方法更适用于滚动轴承故障诊断。     

极点加权模态分解及其在故障诊断中的应用

经验模态分解(EMD)是一种自适应信号分解方法,由于其能够同时提供振动信号时域和频域的局部信息,在机械故障诊断领域得到广泛应用。受EMD思想的启发,基于相邻极值加权构造均值曲线,提出一种新的自适应信号分解方法—极点加权模态分解(EPWMD)。通过仿真信号分析,将提出的EPWMD方法与EMD和局部特征尺度分解(LCD)等方法进行对比,结果表明,与EMD和LCD相比,EPWMD方法在分解性能和分解精度方面有显著提高。最后,将提出的EPWMD方法应用于转子碰摩和滚动轴承局部故障信号分析,并与EMD方法进行对比,分析结果表明,EPWMD方法不仅能够有效识别故障特征,而且其诊断效果优于EMD方法。     

基于神经网络的关联规则在故障诊断中的应用

采用加权关联规则算法对设备历史数据库进行挖掘,建立加权关联规则模式库。设备监控数据通过与模式库匹配,实现设备故障诊断。同时,针对钢铁企业中液压设备的特殊性,提出利用自组织竞争神经网络模型确定权值,即将设备故障信息的3个主要属性:重要程度、易损程度、故障等级作为模型的输入,通过训练样本确定设备故障的加权关联规则的权值。实例证明了该方法的有效性。     

基于NIC-DWT-WOASVM的齿轮箱混合故障诊断

由于齿轮箱中振动信号的复杂性和非平稳性,致使齿轮箱混合故障诊断工作具有一定难度。针对这一问题提出基于NIC-DWT-WOASVM的齿轮箱混合故障诊断方法。首先通过窄带干扰消除(Narrow Band Interference Canceller, NIC)滤除原始信号中齿轮啮合和转轴等窄带干扰信号,接着对信号进行离散小波变换(Discrete Wavelet Transform, DWT),重构小波系数得到小波分量,提取分量的方差作为特征参数构成特征矩阵样本。针对传统优化支持向量机收敛速度慢及容易局部最优等问题,提出鲸鱼算法优化的支持向量机(Whale Optimization Algorithm Support Vector Machine, WOASVM),运用训练样本对WOASVM进行训练得到优化分类模型,将测试样本输入到优化模型中得到诊断结果。为验证方法的有效性,开展了变工况下齿轮箱混合故障实验,通过实验分析及与其他方法的比较,证明方法对于齿轮箱混合故障诊断是有效的。