基于加权排列熵和DE-ELM的滚动轴承故障诊断

针对滚动轴承振动信号非平稳非线性的特征,提出一种基于加权排列熵和差分进化算法优化极限学习机(DE-ELM)的滚动轴承故障诊断方法。首先利用自适应噪声的完全集合经验模态分解处理轴承振动信号得到固有模态函数(IMF),然后计算主要IMF分量的加权排列熵组成故障特征向量,最后利用差分优化算法(DE)优化极限学习机隐含层输入权值和偏置,并将故障特征向量作为DE-ELM的输入。实验证明,加权排列熵能够精确提取故障特征,DE-ELM算法能有效提高故障分类精度。与多种方法相比,该方法更加准确可靠。     

基于多尺度排列熵的滚动轴承故障诊断

针对轴承发生故障,振动信号会表现出复杂性的情况,运用多尺度排列熵(Multiscale Permutation Entropy,MPE)方法对振动信号进行分析。首先对嵌入维数、延迟时间以及数据长度对排列熵的影响进行了分析,在此基础上分析尺度因子关于多尺度排列熵的影响,然后对滚动轴承振动信号进行更准确的故障特征提取,并利用极限学习机(Extreme Le arning Machine,ELM)方法对其进行故障分类,与神经网络的分类效果相比较,结果显示,极限学习机与多尺度排列熵相结合,可以很好地实现故障诊断。     

基于RCMDE与极限学习机的滚动轴承故障诊断

针对滚动轴承故障信号识别率低的情况,提出一种基于精细复合多尺度离散熵（RCMDE）与极限学习机（ELM）的故障诊断方法。首先,从原始振动信号中提取20个尺度的精细复合多尺度离散熵并以此构建故障特征集,然后利用ELM对其进行故障种类识别。通过凯斯西储大学的轴承数据验证提出方法的有效性,最后将提出方法与MPE-ELM进行对比。对比结果说明提出的故障诊断方法具有更高的分类精度。     

H-K-ELM在滚动轴承故障诊断中的应用

针对滚动轴承振动信号的不规则性和复杂性,导致轴承状态难以有效识别的问题,提出基于分层核极限学习机(Hierarchical Kernel Extreme Learning Machine,H-K-ELM)的滚动轴承故障诊断方法。首先,将测得信号经集合经验模态分解(Ensemble Empirical Mode Decomposition,EEMD)处理后得到一系列IMF本征模态分量,并提取各分量的排列熵PE值组成高维特征向量集;其次,利用高斯核函数的内积来表达ELM算法的隐含层输出函数,然后使用自动编码器对其分层,从而隐含层节点数自适应确定和隐含层阈值与输入权值满足正交条件;最后,将所得高维特征向量集作为H-KELM算法的输入,通过训练建立核函数极限学习机滚动轴承故障分类模型,进行滚动轴承不同故障状态的分类辨识。实验结果表明:H-K-ELM滚动轴承故障分类模型比ELM、K-ELM故障分类模型具有更高的精度、更强的稳定性。     

基于DE-VMD和GMDE的往复压缩机轴承间隙故障诊断方法

针对往复压缩机轴承间隙故障特征提取困难、识别准确率不高等问题,提出了差分进化算法优化变分模态分解方法和广义多尺度散布熵相结合的往复压缩机间隙故障诊断方法。首先,采用差分进化算法对变分模态分解算法的两个核心参数进行了优化,并利用优化后的变分模态分解方法对轴承间隙振动信号进行了信号分解和重构处理;然后,研究了多尺度散布熵的粗粒化过程,通过将方差粗粒化代替均值粗粒化,进行了多尺度处理,构建了广义多尺度散布熵算法,利用广义多尺度散布熵算法对重构信号进行了故障特征提取分析;最后,设计了核极限学习机模型对故障特征向量集进行了分类识别,完成了往复压缩机轴承间隙不同故障状态的智能诊断研究。研究结果表明,该故障诊断方法的识别准确率高达97%,高效地实现了轴承不同种类故障的智能诊断目的。     

改进的布谷鸟算法优化极限学习机的石化轴承故障分类

针对通用的智能故障诊断方法在石化滚动轴承中准确率不理想的问题,提出一种通过改进的布谷鸟算法( CS )优化极限学习机( ELM )使诊断准确率提高的模型。将实测轴承振动信号降噪处理,计算不同嵌入维度下的关联维数作为 ELM 的输入信号;通过改进的布谷鸟算法获取极限学习机最优的隐含层偏置、输入权重,最后输出诊断结果。经过实验证明,该方法可以有效地克服测量信号时的干扰,可以对不同故障下的滚动轴承准确识别,并与多种模型对比,该方法的故障诊断准确率为 97.5% 。     

ITD-多尺度熵和ELM的风电轴承健康状态识别

对风力发电机机组的运行状况进行实时监测,并识别其健康状态,是保证机组正常运行的关键,为此提出一种固有时间尺度分解(Intrinsic time-scale decomposition,ITD)-多尺度熵(Multiscale entropy,MSE)的振动信号分析方法,对振动信号进行预处理,提取重构信号时域特征,并结合极限学习机(Extreme learning machine,ELM)对风电轴承健康状态进行识别。首先采用ITD方法对风电轴承的振动信号进行分解,得到一系列固有旋转分量,并计算其多尺度熵值,以多尺度熵值大小为依据,选取固有旋转分量并进行信号重构。计算重构信号的均方根值、峭度值、峰值因子与峰峰值,并将其作为特征指标值,建立ELM识别模型,识别风电轴承的健康状态。风电轴承试验结果表明,本文模型可以准确识别风电轴承健康状态。     

基于CMMFDE与多传感器信息融合的旋转机械故障诊断研究

采用单一传感器采集的振动信号难以准确描述旋转机械动态特性,导致提取的故障特征无法准确辨识旋转机械故障。针对这一缺陷,提出了一种基于复合多元多尺度波动散布熵(CMMFDE)、多传感器信息融合和哈里斯鹰算法优化极限学习机(HHO-ELM)的旋转机械故障诊断方法。首先,引入复合多元粗粒化处理,提出了CMMFDE方法,避免了传统单变量分析方法只能处理单一通道振动信号而导致特征的表征性能不足的缺陷,增强了故障特征的表征性能;随后,利用布置在旋转机械不同部位的传感器收集了多种类型的信号,组成混合多通道信号,并进行了CMMFDE分析,构建了故障特征;最后,采用HHO对极限学习机的参数进行了自适应优化,并对特征样本进行了训练和测试,完成了旋转机械的故障识别工作;利用齿轮箱、离心泵两种典型的旋转机械数据集进行了实验分析。研究结果表明：该方法对多个通道的信号进行分析时,所获得的准确率达到了100%和98%,优于对单个通道信号进行分析时获得的准确率,同时CMMFDE方法的准确率和特征提取时间均优于精细复合多元多尺度熵(RCMMSE)、精细复合多元多尺度模糊熵(RCMMFE)、精细复合多元多尺度排列熵(RCM...     

基于EMD与深度信念网络的滚动轴承故障特征分析与诊断方法

为了实现滚动轴承故障的智能诊断,提出了一种基于经验模态分解(Empirical mode decomposition,EMD)和深度信念网络(Deep belief network,DBN)的轴承故障诊断模型。首先,采用经验模态分解对振动信号进行处理,选取有效的本征模态函数(Intrinsic mode function,IMF)分量及其Hilbert包络谱、边际谱,计算其统计参数,构造原始特征集;然后,提出了一种基于极限学习机(Extreme learning machine,ELM)的特征选择方法 (Features selection base on ELM,FSELM),以去除原始特征集中的冗余和干扰特征,选取出故障状态敏感特征;最后,利用深度学习在高维、非线性信号处理方面的优势,完成基于DBN的故障特征自适应分析与故障状态智能识别。通过对12种轴承状态进行分类实验,表明FSELM方法能够选取出故障的敏感统计特征,DBN方法的自适应特性能够有效提高故障状态识别准确率。     

应用多参数融合与ELM的自动机故障诊断

考虑到自动机工作环境复杂,各部件相互作用时间短,冲击性强从而导致各种响应信号相互叠加,敏感特征参量难以确定的问题,提出了一种应用多参数融合与ELM相结合的自动机故障诊断方法。首先,对自动机故障信号计算广义分形维数,在此基础上提取盒维数、信息维数、关联维数作为故障特征参量;然后引入信息熵模型,对自动机故障信号提取功率谱熵、奇异谱熵、特征空间谱熵作为特征参量来描述信号状态在频域、时域、时频域的能量变化;最后将特征参量输入到极限学习机中(ELM)进行分类。实验结果表明多参数融合能全面准确地反映故障信息,极限学习机学习速度快、结构简单,具有很好的故障分类效果。     

Connected Components-based Colour Image Representations of Vibrations for a Two-stage Fault Diagnosis of Roller Bearings Using Convolutional Neural Networks

Roller bearing failure is one of the most common faults in rotating machines.Various techniques for bearing fault diagnosis based on faults feature extraction have been proposed.But feature extraction from fault signals requires expert prior information and human labour.Recently,deep learning algorithms have been applied extensively in the condition monitoring of rotating machines to learn features automatically from the input data.Given its robust per-formance in image recognition,the convolutional neural network(CNN)architecture has been widely used to learn automatically discriminative features from vibration images and classify health conditions.This paper proposes and evaluates a two-stage method RGBVI-CNN for roller bearings fault diagnosis.The first stage in the proposed method is to generate the RGB vibration images(RGBVIs)from the input vibration signals.To begin this process,first,the 1-D vibration signals were converted to 2-D grayscale vibration Images.Once the conversion was completed,the regions of interest(ROI)were found in the converted 2-D grayscale vibration images.Finally,to produce vibration images with more discriminative characteristics,an algorithm was applied to the 2-D grayscale vibration images to produce connected components-based RGB vibration images(RGBVIs)with sets of colours and texture features.In the second stage,with these RGBVIs a CNN-based architecture was employed to learn automatically features from the RGBVIs and to classify bearing health conditions.Two cases of fault classification of rolling element bearings are used to validate the proposed method.Experimental results of this investigation demonstrate that RGBVI-CNN can generate advan-tageous health condition features from bearing vibration signals and classify the health conditions under different working loads with high accuracy.Moreover,several classification models trained using RGBVI-CNN offered high performance in the testing results of the overall classification accuracy,precision,recall,and F-score.     

Using neural networks for the diagnosis of localized defects in ball bearings

Two neural network based approaches, a multilayered feed forward neural network trained with supervised Error Back Propagation technique and an unsupervised Adaptive Resonance Theory-2 (ART2) based neural network were used for automatic detection/diagnosis of localized defects in ball bearings. Vibration acceleration signals were collected from a normal bearing and two different defective bearings under various load and speed conditions. The signals were processed to obtain various statistical parameters, which are good indicators of bearing condition, and these inputs were used to train the neural network and the output represented the ball bearing states. The trained neural networks were used for the recognition of ball bearing states. The results showed that the trained neural networks were able to distinguish a normal bearing from defective bearings with 100% reliability. Moreover, the networks were able to classify the ball bearings into different states with success rates better than those achieved with the best among the state-of-the-art techniques.     

基于威布尔与模糊C均值的滚动轴承故障识别

提出一种基于威布尔分布与模糊C均值(fuzzy C-means,FCM)聚类算法相结合的滚动轴承故障识别方法。针对不同故障类型的威布尔分布模型的尺度参数、形态参数和威布尔负对数能够较好地刻画轴承运行的状态特性,提取其尺度、形态和威布尔负对数似然函数等3个参数构建表征轴承运行状态的特征向量。模糊C均值根据样本相对于聚类中心的隶属度确定样本的亲疏程度而实现分类。实验中,首先采用组合形态滤波器对滚动轴承原始信号进行降噪,然后建立威布尔分布模型,将提取的特征向量输入模糊C均值分类器进行故障诊断和识别。结果表明,该方法对机械故障诊断识别准确率高,可以作为滚动轴承故障识别的重要手段。     

A fault diagnosis approach for roller bearing based on VPMCD under variable speed condition

Essentially the fault diagnosis of roller bearing is a process of pattern recognition. However, existing pattern recognition method failed to capitalize on the nature of multivariate associations between the extracted fault features. Targeting such limitation, a new pattern recognition method – variable predictive model based class discriminate (VPMCD) is introduced into roller bearing fault identification. The VPMCD consider that all or part of the feature values will exhibit interactions in nature and these associations will have different performances between different classes, which is always true in practice when faults occur in roller bearings. Target to the characteristics of non-stationary and amplitude-modulated and frequency-modulated (AM–FM) of vibration signal picked up under variable speed condition, a fault diagnosis method based upon the VPMCD, order tracking technique and local mean decomposition (LMD) is put forward and applied to the roller bearing fault identification. Firstly, LMD and order tracking analysis method are combined to extract the fault features of roller bearing vibration signals under variable speed condition; Secondly, the feature values are regard as the input of VPMCD classifier; finally, the working condition and fault patterns of the roller bearings are identified automatically by the output of VPMCD classifier. The analysis results from experimental signals with normal and defective roller bearings indicate that the proposed fault diagnosis approach can distinguish the roller bearing status-with or without fault and fault patterns under variable speed condition accurately and effectively.     

基于多特征参数和概率神经网络的滚动轴承故障诊断方法

针对滚动轴承故障振动信号的非平稳特性,提出了一种基于多特征参数和概率神经网络的滚动轴承故障诊断方法。首先利用经验模态分解（EMD）方法将采集到的滚动轴承原始振动信号分解为有限个固有模式函数（IMF）之和,然后提取表征故障信息的若干个IMF的能量、峭度和偏度作为概率神经网络的输入参数来进行故障分类。试验结果表明,该方法可以准确、有效地识别滚动轴承的工作状态和故障类型,是一种可行的滚动轴承故障诊断方法。     

Low-speed rolling bearing fault diagnosis based on EMD denoising and parameter estimate with alpha stable distribution

When low-speed rolling bearings fail, it is hard to diagnose the extent of their damage. We developed a test rig to simulate the lowspeed rolling bearing operating condition, where bearings with various fault states are installed on the test wheelset and subjected to the same external loading condition. The collected bearing box acceleration time histories are processed with the Empirical mode decomposition (EMD) method combined with kurtosis criterion to filter the trend and noise components. Five characteristic parameters of Alpha stable distribution (ASD) are identified by fitting the ASD distribution to the vibration acceleration signals and computing the Probability density function (PDF). To highlight the advantage of ASD method in feature extraction, kurtosis also has be calculated. Through sensitivity and stability analysis of the six parameters and utilization of Least squares support vectors machine (LSSVM) with Particle swarm optimization (PSO), three most sensitive and stable feature parameters including the characteristic exponent α, the scale factor γ and the peak value of the PDF h are located and applied to evaluate the low-speed rolling bearings’ damage position and damage extent. The proposed method was validated by test data, and the results demonstrated that the ASD characteristics combined with PSO-LSSVM can not only achieve fault diagnosis of low-speed rolling bearings' damage position and damage extent, but also have better diagnosis accuracy and operational efficiency than other methods.     

基于路图拉普拉斯算子范数和马氏距离的滚动轴承故障诊断

为有效提取滚动轴承振动信号的故障特征,将图信号处理技术引入故障诊断领域。首先根据滚动轴承振动信号构造路图,获得路图信号;再将计算得到的路图拉普拉斯算子范数作为特征参数,构造不同故障的标准特征空间;最后通过测试样本与标准特征空间的马氏距离实现不同故障模式的识别。实测滚动轴承振动信号的分析结果表明,该方法能有效诊断轴承故障。     

基于RSGWPT-LCD的轴承信号故障特征提取及模式识别

为了有效提取滚动轴承振动信号的故障特征和提高分类识别精度,提出了一种基于冗余二代小波包变换-局部特征尺度分解(redundant second generation wavelet packet transform-local characteristic scale decomposition,简称RSGWPT-LCD)和极限学习机(extreme learning machine,简称ELM)相结合的故障特征提取和分类识别方法。首先,利用希尔伯特变换对原始振动信号进行处理,得到包络信号;其次,基于双层筛选机制,结合冗余二代小波包变换(redundant second generation wavelet packet transform,简称RSGWPT)和局部特征尺度分解(local characteristic-scale decomposition,简称LCD)方法对包络信号进行分解,筛选出包含主要信息的内禀尺度分量(intrinsic scale components,简称ISCs);然后,对提取的各ISCs分量构建初始特征矩阵并进行奇异值分解(singular value decomposition,简称SVD),将得到的奇异值作为表征各损伤信号的特征向量;最后,以提取的特征向量为输入样本,建立ELM模式分类器对滚动轴承损伤信号进行识别。信号仿真和实测数据表明,该方法可有效提取振动信号故障特征,提高分类识别精度,实现滚动轴承故障诊断。     

基于关联维数的滚动轴承故障诊断的研究

针对滚动轴承系统产生的非线性振动信号的特点,提出用关联维数来描述轴承振动信号的工作状态,进而对其进行故障诊断的方法。同时详细讨论了关联维数的计算方法,并对由轴承系统产生的非线性振动信号进行了关联维数的定量计算。实验表明,滚动轴承不同工作状态由不同的动力学机理产生,其关联维数明显不同。以关联维数作为滚动轴承的工作状态监测的依据,可以为提高滚动轴承故障诊断的准确率提供了一种有效的新方法。