基于神经网络的去噪模型在轴承故障诊断中的应用

针对轴承微弱故障稀疏振动信号的特征提取,提出了基于模型数据协同链接框架的端到端深度网络稀疏去噪(DNSD)策略。建立了全局可微稀疏模型,引入深度神经网络学习超参数,基于轴承内圈故障机理建立了多模式数据集模拟故障信号,通过DNSD对数据集以去噪自编码器的形式进行训练,重建损失并更新网络和稀疏理论的参数,通过轴承内圈故障的仿真和试验验证了DNSD模型在轴承微弱故障特征提取方面的优越性和鲁棒性。     

基于迭代滤波和MOMEDA的滚动轴承故障诊断方法

针对噪声环境下轴承故障微弱特征难以提取的问题,提出了一种基于迭代滤波和多点最优最小熵反褶积相结合的轴承故障特征提取方法。该方法首先运用迭代滤波分解方法将滚动轴承振动信号进行分解,得到多个本征模态分量,然后运用相关系数和峭度确定最能体现轴承故障信息的敏感分量,最后对敏感分量进行多点最优最小熵反褶积消噪处理后进行频谱分析,从而提取轴承故障特征。通过数值仿真信号的分析和内圈故障信号的分析验证了所提出方法的有效性。     

瞬态成分Laplace小波稀疏表示及其轴承故障特征提取应用

机械系统中轴承局部故障会导致振动信号中出现瞬态冲击响应成分,可通过对瞬态成分的分析与提取实现故障特征的提取。稀疏表示是强背景噪声下微弱特征提取的有效方法之一,在信号稀疏表示理论的基础上,针对冲击响应信号的特点,提出其在Laplace小波基底下的稀疏表示,并应用于轴承局部弱故障状态下振动信号中瞬态冲击成分的提取。在选定匹配基底函数的前提下,运用分裂增广拉格朗日收缩算法求解基追踪去噪(Basis pursuit denoising,BPD)问题,将信号中的瞬态冲击成分转化为一系列稀疏表示系数,实现强背景噪声下弱特征的有效提取。仿真信号和轴承微弱故障下的特征提取表明提出的方法能有效地检测和提取强背景噪声下的微弱故障。     

基于相关峭度准则EEMD及改进形态滤波的轴承故障诊断方法

针对滚动轴承早期微弱故障常被强烈的背景噪声湮没,造成故障特征提取困难的特点,提出了基于相关峭度准则EEMD及改进形态滤波的轴承故障诊断方法。首先利用EEMD将轴承故障信号分解成有限个IMF分量,然后采用相关峭度准则选取分量并重构,再利用基于相关峭度准则的改进形态滤波对重构信号进行滤波解调,最后将滤波后的信号进行Hilbert包络谱分析,找出故障特征进行识别。试验表明:该方法能有效抑制噪声,特征提取效果更加明显,适用于轴承故障的精确诊断。     

基于局部均值分解与拉普拉斯特征映射的滚动轴承故障诊断方法

针对滚动轴承非平稳振动信号的特征提取及维数优化问题,提出了融合局部均值分解与拉普拉斯特征映射的轴承故障诊断方法。首先,通过局部均值分解对非平稳振动信号进行平稳化分解,提取乘积函数分量、瞬时频率及瞬时幅值的高维信号特征集;然后,将高维特征集作为拉普拉斯特征映射算法的学习对象,提取轴承高维故障特征集的内在流形分布,以获得敏感、稳定的轴承振动特征参数,实现基于非平稳振动信号分析的滚动轴承故障特征提取;最后,结合支持向量分类模型量化LMD-LE方法的特征提取效果,实现不同状况下的轴承故障分类。轴承故障样本分类识别平均正确率达到91.17%,表明LMD-LE方法有效实现了高维局部均值分解特征集合的降噪,所提取的特征矩阵对轴承故障特征描述准确。     

全矢谱和稀疏分解结合的轴承故障特征提取

针对滚动轴承在故障早期特征信号微弱、故障特征提取困难以及单通道分析方法信息利用不充分等问题,提出了一种基于稀疏分解与全矢谱相结合的滚动轴承早期微弱故障特征提取方法。首先,在已构造的冗余字典基础上对滚动轴承同源双通道早期故障信号分别进行稀疏分解,得到各自的稀疏信号;然后,将同源双通道稀疏信号进行全矢信息融合;最后,对融合后的信号进行包络解调分析,以提取出故障特征频率。该方法将全矢谱拓展到早期微弱故障诊断领域,并通过实验验证了其在早期微弱故障特征提取方面的有效性。     

基于流形-奇异值熵的滚动轴承故障特征提取

提出一种基于流形-奇异值熵的滚动轴承时频故障特征提取方法。首先,在HHT(Hilbert-Huang transform,简称HHT)时频分析基础上,应用二维流形方法提取信号流行成分以达到对轴承故障特征进行降维和提取敏感参量的目的;然后,定义了奇异值熵来定量衡量不同故障状态下流行成分的差异;最后,将流形奇异值向量与概率神经网络相结合,有效实现了轴承故障样本分类。与一般的考虑欧式空间全局范围最优值的主分量(principal component analysis,简称PCA)方法及以向量为研究对象的一维流形方法不同,该方法直接以二维信息为研究对象,避免了一维流形算法需将二维信息转化为向量带来的信息损失,与PCA方法相比更能发现隐藏在高维数据流形结构中的局部数据特征。工程信号分析验证了该方法的有效性,为准确提取滚动轴承故障特征提供了一种可靠手段。     

基于MVMD-FRFT的滚动轴承早期故障特征提取研究

滚动轴承的振动信号具有非平稳、非线性的特点,造成其早期故障信号的特征提取困难,针对这一问题,对滚动轴承状态监测中常用的特征提取方法进行了研究,提出了一种基于多元变分模态分解(MVMD)和分数阶傅里叶变换(FRFT)的特征提取方法,并将其应用于滚动轴承的故障诊断中。利用MVMD算法将多传感器同时采集的多通道振动信号进行了同步分解,有效地提高了多通道数据融合处理能力,同时得到了若干个固有模态函数(IMF)分量;依据相关系数法从分解后得到的IMF分量中选取了包含故障信息最多的分量作为最优分量,利用FRFT对最优分量进行了滤波,降低了噪声对微弱故障信号的干扰;对滤波后的信号进行了1.5维包络谱解调,通过分析滤波后信号的包络谱,提取了滚动轴承的故障特征。研究结果表明:应用MVMD和FRFT相结合的方法能够有效地避免模态混叠现象,充分地利用故障特征信息,削弱低频信号与噪声的干扰,从而有效地提取出了滚动轴承的故障特征信息。     

滚动轴承特征提取的多分量解调方法

提出利用多个高频振动分量进行滚动轴承故障特征提取的多分量解调方法。与传统的基于单一高频振动分量的解调方法不同,多分量解调方法从多个高频振动分量中提取信号特征信息。首先构建带通滤波器组对原信号进行滤波,然后依据所提高频振动分量获取策略求取原信号中多个高频振动分量,并对各高频振动分量进行包络检波,其次用独立成分分析对所得包络信号进行盲分离,最后对分离信号进行频谱变换以提取故障特征信息。仿真信号和故障轴承信号的分析结果表明,所提方法较传统解调方法更能凸显滚动轴承故障振动信号中的特征信息。     

基于包络谱稀疏度和最大相关峭度解卷积的滚动轴承早期故障诊断方法

滚动轴承处于早期故障阶段时,特征信号微弱,并且受环境噪声影响严重,因此故障特征提取困难。针对这一问题,将最大相关峭度解卷积算法应用于轴承故障诊断,并通过包络谱稀疏度来筛选最佳解卷积周期参数,提出了基于包络谱稀疏度和最大相关峭度解卷积的滚动轴承早期故障诊断方法。利用最佳参数相对应的最大相关峭度解卷积算法对原信号进行处理,得到解卷积信号后计算其包络谱,通过分析包络谱中幅值突出的频率成分来判断故障类型。早期故障仿真信号及实测全寿命数据分析结果表明,该方法可有效应用于轴承早期故障诊断。     

An Intelligent Fault Diagnosis Method of Multi-Scale Deep Feature Fusion Based on Information Entropy

For a single-structure deep learning fault diagnosis model,its disadvantages are an insufficient feature extraction and weak fault classification capability.This paper proposes a multi-scale deep feature fusion intelligent fault diagnosis method based on information entropy.First,a normal autoencoder,denoising autoencoder,sparse autoencoder,and contractive autoencoder are used in parallel to construct a multi-scale deep neural network feature extrac-tion structure.A deep feature fusion strategy based on information entropy is proposed to obtain low-dimensional features and ensure the robustness of the model and the quality of deep features.Finally,the advantage of the deep belief network probability model is used as the fault classifier to identify the faults.The effectiveness of the proposed method was verified by a gearbox test-bed.Experimental results show that,compared with traditional and existing intelligent fault diagnosis methods,the proposed method can obtain representative information and features from the raw data with higher classification accuracy.     

Iterative HOEO fusion strategy: a promising tool for enhancing bearing fault feature

As parameter independent yet simple techniques, the energy operator (EO) and its variants have received considerable attention in the field of bearing fault feature detection. However, the performances of these improved EO techniques are subjected to the limited number of EOs, and they cannot reflect the non-linearity of the machinery dynamic systems and affect the noise reduction. As a result, the fault-related transients strengthened by these improved EO techniques are still subject to contamination of strong noises. To address these issues, this paper presents a novel EO fusion strategy for enhancing the bearing fault feature nonlinearly and effectively. Specifically, the proposed strategy is conducted through the following three steps. First, a multi-dimensional information matrix (MDIM) is constructed by performing the higher order energy operator (HOEO) on the analysis signal iteratively. MDIM is regarded as the fusion source of the proposed strategy with the properties of improving the signal-to-interference ratio and suppressing the noise in the low-frequency region. Second, an enhanced manifold learning algorithm is performed on the normalized MDIM to extract the intrinsic manifolds correlated with the fault-related impulses. Third, the intrinsic manifolds are weighted to recover the fault-related transients. Simulation studies and experimental verifications confirm that the proposed strategy is more effective for enhancing the bearing fault feature than the existing methods, including HOEOs, the weighting HOEO fusion, the fast Kurtogram, and the empirical mode decomposition.     

Multi-fault diagnosis study on roller bearing based on multi-kernel support vector machine with chaotic particle swarm optimization

A novel intelligent fault diagnosis model based on multi-kernel support vector machine (MSVM) with chaotic particle swarm optimization (CPSO) for roller bearing fault diagnosis is proposed. Multi-kernel support vector machine is a powerful new tool for roller bearing fault diagnosis with small sampling, nonlinearity and high dimension. Chaotic particle swarm optimization is developed in this study to determine the optimal parameters for MSVM with high accuracy and great generalization ability. Moreover, the feature vectors for fault diagnosis are obtained from vibration signal that preprocessed by time-domain, frequency-domain and empirical mode decomposition (EMD) and the typical manifold learning method LTSA is used to select salient features. The experimental results indicate that this proposed approach is an effective method for roller bearing fault diagnosis, which has more strong generalization ability and can achieve higher diagnostic accuracy than that of the single kernel SVM or the MSVM which parameters are randomly extracted.     

广义精细复合多尺度样本熵与流形学习相结合的滚动轴承故障诊断方法

针对滚动轴承故障特征提取困难的问题，提出了一种广义精细复合多尺度样本熵(GRCMSE)与流形学习相结合的特征提取方法。利用GRCMSE提取滚动轴承故障特征信息；采用判别式扩散映射分析(DDMA)方法对高维特征进行降维处理；将低维故障特征输入粒子群优化支持向量机多故障分类器中进行故障识别。滚动轴承故障实验分析结果表明：GRCMSE特征提取效果优于多尺度样本熵(MSE)、精细复合多尺度样本熵(RCMSE)和广义多尺度样本熵(GMSE)； DDMA降维效果优于等度规映射(Isomap)和局部切空间排列(LTSA)的降维效果；GRCMSE和DDMA相结合后的滚动轴承故障识别精度达到100%。     

风电机组齿轮箱早期故障预警方法研究

为实现风力发电机组等变工况机电设备的早期故障预警,研发了变工况齿轮箱状态监测系统。在基于该系统的多种变工况行星齿轮磨损实验研究基础上,提出了一种基于流形学习的早期故障预警方法。该方法首先研究采用完全总体经验模态分解与改进快速独立成分分析盲源分离技术,有利于对复杂振动信号的滤波与盲源分离;然后研究改进了局部线性嵌入流形学习方法,基于时域、频域信息融合提取了早期故障敏感特征;最后应用k-近邻分类器实现变工况齿轮箱早期故障预警。实验研究表明,该方法提高了早期故障预警准确率,能够应用于风电机组等变工况机电设备的安全保障及科学维护,具有广泛工程实用前景。     

一种基于非线性流形的滚动轴承复合故障诊断方法

针对滚动轴承振动信号的非平稳以及非线性特点,提出了一种基于非线性流形的滚动轴承复合故障诊断方法。该方法首先提取振动信号的时域指标和小波包频带分解能量所构成的频域指标,组成原始特征空间,采用基于判别准则的邻域因子优化选择算法,运用基于局部切空间排列算法的非线性降维算法对原始特征空间进行学习,极大地保留了信号中内在的整体几何结构信息,从而提取出振动信号最优的敏感故障特征。试验结果表明,与经典的线性降维方法相比,该方法的聚类效果更好。     

Bearing running state recognition based on non-extensive wavelet feature scale entropy and support vector machine

In order to effectively recognize the bearing running state, a new method based on non-extensive wavelet feature scale entropy and the Morlet wavelet kernel support vector machine (MWSVM) was proposed. Firstly, the gathered vibration signals were decomposed by the wavelet to obtain the corresponding wavelet coefficients. Then, based on the integration of non-extensive entropy and the coefficients, the features were extracted by the wavelet feature scale entropy. However, the extracted features remained high-dimensional and excessive redundant information still existed. Therefore, the manifold learning algorithm locality preserving projection (LPP) was introduced to extract the characteristic features and to reduce the dimension. The extracted characteristic features were inputted into the MWSVM to train and construct the running state identification model; the bearing running state identification was thereby realized. Cases of test and actual fault were analyzed. The results validate the effectiveness of the proposed algorithm.     

Machinery fault diagnosis using supervised manifold learning

Fault diagnosis is essentially a kind of pattern recognition. How to implement feature extraction and improve recognition performance is a crucial task. In this paper, a new supervised manifold learning algorithm (S-LapEig) for feature extraction is proposed first. Via combining preserving the consistency of local neighbor information and class labels information, S-LapEig can not only gain a perfect approximation of low-dimensional intrinsic geometric structure within the high-dimensional observation data, but also enhance local within-class relations. Based on S-LapEig, a novel fault diagnosis approach is proposed. The approach extracts the intrinsic manifold features from high-dimensional fault data by directly learning the data, and translates complex mode space into a low-dimensional feature space, in which pattern classification and fault diagnosis are carried out easily. Comparing with other feature extraction methods such as PCA, LDA and Laplacian eigenmaps, the proposed method obviously improves the classification performance of fault pattern recognition. The experiments on benchmark data and engineering instance demonstrate the feasibility and effectiveness of the new approach.     

面向转子故障特征提取的多尺度拉普拉斯特征映射方法

融合多尺度分解理论和流形学习思想,提出了一种面向转子故障特征提取的多尺度拉普拉斯特征映射算法。首先对转子故障振动信号进行多尺度小波包分解,提取各独立频带信号的最优尺度小波熵,构建特征参量矩阵并估计其固有维数,然后通过拉普拉斯特征映射将特征参量数据嵌入到低维本征空间,得到故障的最敏感特征,最后融合决策实现故障的准确识别。实验表明,相对于主成分分析算法、局部线性嵌入算法和拉普拉斯特征映射算法,多尺度拉普拉斯特征映射方法提取的转子故障信号特征更容易识别。