A hybrid fault diagnosis approach based on mixed-domain state features for rotating machinery

To make further improvement in the diagnosis accuracy and efficiency, a mixed-domain state features data based hybrid fault diagnosis approach, which systematically blends both the statistical analysis approach and the artificial intelligence technology, is proposed in this work for rolling element bearings. For simplifying the fault diagnosis problems, the execution of the proposed method is divided into three steps, i.e., fault preliminary detection, fault type recognition and fault degree identification. In the first step, a preliminary judgment about the health status of the equipment can be evaluated by the statistical analysis method based on the permutation entropy theory. If fault exists, the following two processes based on the artificial intelligence approach are performed to further recognize the fault type and then identify the fault degree. For the two subsequent steps, mixed-domain state features containing time-domain, frequency-domain and multi-scale features are extracted to represent the fault peculiarity under different working conditions. As a powerful time-frequency analysis method, the fast EEMD method was employed to obtain multi-scale features. Furthermore, due to the information redundancy and the submergence of original feature space, a novel manifold learning method (modified LGPCA) is introduced to realize the low-dimensional representations for high-dimensional feature space. Finally, two cases with 12 working conditions respectively have been employed to evaluate the performance of the proposed method, where vibration signals were measured from an experimental bench of rolling element bearing. The analysis results showed the effectiveness and the superiority of the proposed method of which the diagnosis thought is more suitable for practical application.     

基于小波包和AR谱分析的滚动轴承故障诊断

针对滚动轴承故障振动信号的非平稳性,提出了一种基于小波包和AR谱分析的滚动轴承故障诊断方法.该方法对系统输出信号进行小波包分解,然后进行重构,再对重构信号进行AR谱分析,从而提取出故障特征频率.试验结果表明,这种方法能有效地提取滚动轴承的故障特征,诊断其故障.     

基于局部特征尺度分解的经验包络解调方法及其在机械故障诊断中的应用

提出一种基于局部特征尺度分解(Local characteristic-scale decomposition, LCD)和经验包络(Empirical envelope method, EE)解调的非平稳信号分析方法。该方法通过局部特征尺度分解将一个复杂信号自适应地分解为若干个内禀尺度分量之和,对得到的各个内禀尺度分量进行经验包络解调,得到各个分量信号的瞬时幅值和瞬时频率信息,从而得到原始信号完整的时频分布。采用仿真信号将基于LCD和EE解调的时频分析方法和希尔伯特黄变换方法进行对比,结果表明,新提出的信号分解和解调方法在抑制端点效应和迭代所需时间,瞬时特征的精确性等方面优于希尔伯特黄变换方法。针对滚动轴承和齿轮故障振动信号的调制特点,将基于LCD和EE的时频分析方法引入机械故障诊断中,对试验信号的分析结果表明,基于LCD和EE的时频分析方法能有效地提取机械故障振动信号的特征。     

基于现代非线性理论的汽轮发电机组故障诊断技术研究

运用小波理论、分形理论和混沌理论等非线性理论,对汽轮发电机组转子故障进行了综合分析和研究。对 所测某28 MW发电机组转子在三种不同工作状态下的时间序列进行了关联维数计算、小波包分解以及最大李雅 普诺夫指数计算,并结合其相轨迹图和庞加莱截面进行了分析与研究。结果表明,小波包分解重构技术具有很强 的消噪和非平稳信号提取能力;发电机组转子在不同工作状态下其时间序列的关联维数、李雅普诺夫指数具有明 显差别,且两量值相互补充、相互对应。由此提出:关联维数、最大李雅普诺夫指数可以作为刻画发电机组机械 故障特征的综合量化指标。该研究为非线性运动系统的在线监测、故障诊断和状态预测开辟了有效途径。     

利用声场空间分布特征诊断滚动轴承故障

基于振动信号分析的特征提取是目前最主要的机械故障诊断方法,而振动信号的获取受到接触式测量的限制,基于声学测量的故障诊断能够克服这一缺点,但传统基于单通道测试的声学诊断技术存在测点选择难和局部诊断的不足。基于近场声全息技术提出一种用于滚动轴承故障诊断的声场分布特征提取方法。不同轴承故障能产生不同的振动特性,进而产生相应的声场分布,鉴于轴承状态与声场分布特性的对应关系,利用近场声全息算法重建声源附近各轴承运行状态下的声场,得到反映声场分布的二维声像图,再从声像图中提取故障相关的灰度共生矩阵特征,建立声场分布特性与轴承运行状态间的内在联系,结合支持矢量机模式分类,用于轴承的故障诊断。研究表明所提出的声场分布特征提取方法能够有效地用于滚动轴承的各类故障诊断,为机械故障诊断提供了新的参考。     

A vibration analysis method based on hybrid techniques and its application to rotating machinery

Vibration-based condition monitoring and fault diagnosis technique is a most effective approach to maintain the safe and reliable operation of rotating machinery. Unfortunately, the vibration signal always exhibits non-linear and non-stationary characteristics, which makes vibration signal analysis and fault feature extraction very difficult. To extract the significant fault features, a vibration analysis method based on hybrid techniques is proposed in this paper. Firstly, the raw signals are decomposed into a few product functions (PFs) using local mean decomposition (LMD), and meanwhile instantaneous frequency and instantaneous amplitude also are obtained. Subsequently, Fourier transform is performed on the derived PFs, and then, according to the spectra features, the useful PFs are selected to reconstruct the purified vibration signals. Lastly, several different fault features are fused to illustrate the operating state of the machinery. The experimental results show that the proposed method can accurately extract machine fault features, which proves that the combined application of LMD and other signal processing techniques is a successful scheme for the machine vibration analysis.     

Intelligent Fault Diagnosis of Rotary Machinery Based on Unsupervised Multiscale Representation Learning

The performance of traditional vibration based fault diagnosis methods greatly depends on those handcrafted features extracted using signal processing algorithms, which require significant amounts of domain knowledge and human labor, and do not generalize well to new diagnosis domains. Recently, unsupervised representation learning provides an alternative promising solution to feature extraction in traditional fault diagnosis due to its superior learning ability from unlabeled data. Given that vibration signals usually contain multiple temporal structures, this paper proposes a multiscale representation learning (MSRL) framework to learn useful features directly from raw vibration signals, with the aim to capture rich and complementary fault pattern information at different scales. In our proposed approach, a coarse-grained procedure is first employed to obtain multiple scale signals from an original vibration signal. Then, sparse filtering, a newly developed unsupervised learning algorithm, is applied to automatically learn useful features from each scale signal, respectively, and then the learned features at each scale to be concatenated one by one to obtain multiscale representations. Finally, the multiscale representations are fed into a supervised classifier to achieve diagnosis results. Our proposed approach is evaluated using two different case studies: motor bearing and wind turbine gearbox fault diagnosis. Experimental results show that the proposed MSRL approach can take full advantages of the availability of unlabeled data to learn discriminative features and achieved better performance with higher accuracy and stability compared to the traditional approaches.     

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.     

The envelope order spectrum based on generalized demodulation time–frequency analysis and its application to gear fault diagnosis

The generalized demodulation time–frequency analysis is a novel signal processing method, which is particularly suitable for the processing of multi-component amplitude-modulated and frequency-modulated (AM–FM) signals as it can decompose a multi-component signal into a set of single-component signals whose instantaneous frequencies own physical meaning. While fault occurs in gear, the vibration signals measured from gearbox would exactly display AM–FM characteristics. Therefore, targeting the modulation feature of gear vibration signal in run-ups and run-downs, a fault diagnosis method in which generalized demodulation time–frequency analysis and envelope order spectrum technique are combined is put forward and applied to the transient analysis of gear vibration signal. Firstly the multi-component vibration signal of gear is decomposed into some mono-component signals using the generalized demodulation time–frequency analysis approach; secondly the envelope analysis is performed to each single-component signal; thirdly each envelope signal is re-sampled in angle domain; finally the spectrum analysis is applied to each re-sampled signal and the corresponding envelope order spectrum can be obtained. Furthermore, the gear working condition can be identified according to the envelope order spectrum. The analysis results from the simulation and experimental signals show that the proposed algorithm was effective in gear fault diagnosis.     

Research on iterated Hilbert transform and its application in mechanical fault diagnosis

Multicomponent AM–FM demodulation is an available method for machinery fault vibration signal analysis, so a new method for mechanical fault diagnosis based on iterated Hilbert transform (IHT) is proposed. The principle of computing the asymptotically exact multicomponent sinusoidal model for an arbitrary signal by iterating Hilbert transform is introduced, and some properties of IHT are analyzed. Theoretical analysis for the generic two-component signal shows that there are limitations in the direct estimation of instantaneous frequencies via the phase signals of the previously obtained model. Therefore, a smoothed instantaneous frequency estimation (SIFE) method based on difference operator and zero-phase digital low-pass filtering is proposed, and then the accuracy and validity of this method have been proved by the simulation results. The analysis results of the mechanical fault signals show that the weak features of these signals can be efficiently extracted with the proposed approach.     

基于盲源分离技术的故障特征信号分离方法

信号采集过程中，传感器测量到的信号是实际振动信号在此测量方向的投影值，由于其他不相干振源的影响，测量信号由多个振动信号成分组成。在分析多振源信号混合模型的基础上，采用盲源分离技术分离不同的振源信号，讨论分离结果的广义初等相等性质的影响，研究估计振源数目的方法和选取测量信号的方法，利用二阶特征矩阵联合近似对角化算法，从测量信号中分离故障特征源信号。该算法可减小信号采集不当造成的影响，有效提高特征信号的提取。     

Application of time–frequency entropy method based on Hilbert–Huang transform to gear fault diagnosis

When faults occur in the gear, energy distribution of gear vibration signals measured in time–frequency plane would be different from the distribution under the normal state. Therefore, it is possible to detect a fault by comparing the energy distribution of gear vibration signals with and without fault conditions. Hilbert–Huang transform can offer a complete and accurate energy–frequency–time distribution. On the other hand, Shannon entropy could give a useful criterion for analyzing and comparing probability distribution and offer a measure of the information of any distribution. Targeting the feature of energy distribution of gear vibration signal, the merit of entropy and Hilbert–Huang transform, the concept of time–frequency entropy based on Hilbert–Huang transform is defined and furthermore gear fault diagnosis method based on time–frequency entropy is proposed. The analysis results from simulated signals and experimental signals with normal and defective gears show that the diagnosis approach proposed could identify gear status-with or without fault accurately and effectively. However, further study is needed to the classify gear fault pattern such as crack fault or broken teeth.     

基于等距特征映射和支持矢量机的转子故障诊断方法

针对振动信号的非线性特征,提出一种基于等距特征映射(Isometric feature mapping,ISOMAP)和支持矢量机(Support vector machine,SVM)的转子故障诊断方法。利用ISOMAP把数据从高维空间投影到低维空间而不改变数据内在属性的特点,对高维的故障振动信号降维并提取出低维的数据作为特征矢量,采用一种新核函数支持矢量机作为分类器进行故障诊断。将该方法应用于转子故障诊断,结果表明,ISOMAP-SVM方法不仅具有较高的故障诊断率,而且取得振动信号在低维空间的可视化表示。与其他核函数相比新核函数支持矢量机具有较好的诊断效果。     

基于EMD的能量算子解调方法及其在机械故障诊断中的应用

为了提取多分量的AM-FM信号的频率和幅值信息,提出了基于EMD (Empirical mode decomposition)的能量算子解调法,并将它应用于机械故障诊断中。该方法首先采用EMD将多分量的AM-FM信号分解成若干个IMF(Intrinsic mode function)分量之和,然后对每一个IMF分量进行能量算子解调,从而提取多分量的AM-FM信号的幅值和频率信息。对机械故障振动信号的分析结果表明,基于EMD的能量算子解调法能有效地提取机械故障振动信号的特征。     

Supervised locally linear embedding projection (SLLEP) for machinery fault diagnosis

Following the intuition that the measured signal samples usually distribute on or near the nonlinear low-dimensional manifolds embedded in the high-dimensional signal space, this paper proposes a new machinery fault diagnosis approach based on supervised locally linear embedding projection (SLLEP). The approach first performs the recently proposed manifold learning algorithm supervised locally linear embedding (SLLE) on the high-dimensional fault signal samples to learn the intrinsic embedded multiple manifold features corresponding to different fault modes, and map them into a low-dimensional embedded space to achieve fault feature extraction. For dealing with the new fault sample, the approach then applies local linear regression to find the projection that best approximates the implicit mapping from high-dimensional samples to the embedding. Finally fault classification is carried out in the embedded manifold space. The ball bearing data and rotor bed data are both used to validate the proposed approach. The results show that the proposed approach obviously improves the fault classification performance and outperform the other traditional approaches.     

Blind vibration component separation and nonlinear feature extraction applied to the nonstationary vibration signals for the gearbox multi-fault diagnosis

Fault diagnosis of gearboxes, especially the gears and bearings, is of great importance to the long-term safe operation. An unexpected damage on the gearbox may break the whole transmission line down. It is therefore crucial for engineers and researchers to monitor the health condition of the gearbox in a timely manner to eliminate the impending faults. However, useful fault detection information is often submerged in heavy background noise. Thereby, a new fault detection method for gearboxes using the blind source separation (BSS) and nonlinear feature extraction techniques is presented in this paper. The nonstationary vibration signals were analyzed to reveal the operation state of the gearbox. The kernel independent component analysis (KICA) algorithm was used hereby as the BSS approach for the mixed observation signals of the gearbox vibration to discover the characteristic vibration source associated with the gearbox faults. Then the wavelet packet transform (WPT) and empirical mode decomposition (EMD) nonlinear analysis methods were employed to deal with the nonstationary vibrations to extract the original fault feature vector. Moreover, the locally linear embedding (LLE) algorithm was performed as the nonlinear feature reduction technique to attain distinct features from the feature vector. Lastly, the fuzzy k-nearest neighbor (FKNN) was applied to the fault pattern identification of the gearbox. Two case studies were carried out to evaluate the effectiveness of the proposed diagnostic approach. One is for the gear fault diagnosis, and the other is to diagnose the rolling bearing faults of the gearbox. The nonstationary vibration data was acquired from the gear and rolling bearing fault test-beds, respectively. The experimental test results show that sensitive fault features can be extracted after the KICA processing, and the proposed diagnostic system is effective for the multi-fault diagnosis of the gears and rolling bearings. In addition, the proposed method can achieve higher performance than that without KICA processing with respect to the classification rate.     

Supervised locally tangent space alignment for machine fault diagnosis

How to deal with the high-dimensional and nonlinear data is a challenging problem for fault diagnosis. An unsupervised locally tangent space alignment (LTSA) has recently proven to be an effective unsupervised manifold learning algorithm for high-dimensional data analysis. In this paper, a supervised expansion of LTSA (named S-LTSA) is proposed, which takes full advantage of class label information to improve classification performance. Based on S-LTSA, a novel machine fault diagnosis approach is proposed to deal with the high-dimensional fault data that contain multiple manifolds corresponding to fault classes. The experiment results with bearing fault data show that the proposed approach outperforms the other fault pattern recognition approaches such PCA, ICA, LDA and LTSA.     

Fault feature extraction of a rotor system based on local mean decomposition and Teager energy kurtosis

Feature extraction is the most important step for machine fault diagnosis, but useful features are very difficult to extract from the vibration signals, especially for intelligent fault diagnosis based on data-driven technique. An integral method for fault feature extraction based on local mean decomposition (LMD) and Teager energy kurtosis (TEK) is proposed in this paper. The raw vibration signals are first processed via LMD to produce a group of product functions (PFs). Then, the Teager energies are computed using the derived PFs. Subsequently, each Teager energy data set is directly used to calculate the corresponding TEK. A vibration experiment was performed on a rotor-bearing rig with rub-impact fault to validate the proposed method. The experimental results show that the proposed method can extract different TEKs from the mechanical vibration signals under two different operating conditions. These TEKs can be employed to identify the normal and rub-impact fault conditions and construct a numerical-valued machine fault decision table, which proves that the proposed method is suitable for fault feature extraction of the rotor-bearing system.     

基于K-L散度的机械或传感器故障判别方法

机械故障诊断系统中,对同一监测部位通常采用双传感器配置（如水平和垂直方位）。文中首先运用核密度估计方法得到两传感器输出信号的概率密度函数估计,然后计算两输出信号间K-L（Kullbaek—Leiber）散度,并提出一种基于K-L散度值的机械或传感器故障判别准则。通过对一个齿轮减速箱实测振动信号和模拟的传感器故障信号的计算,可以发现,与无故障状态时K-L散度相比,监测部位出现机械故障时两传感器输出信号间K-L散度显著减小;而两传感器之一出现故障时其K-L散度显著增大。因此,两信号间K-L散度的变化可用于区别机械和传感器故障。     

Detecting dominant resonant modes of rolling bearing faults using the niching genetic algorithm

In this paper we propose an improvement of methods for adaptive selection of frequency bands containing transients which indicate the presence of the dominant resonant modes of rolling bearing faults using niching genetic algorithm optimization. The main aim of this approach is to diagnose the condition of the bearings and to be able to recognize faults on various parts of bearings and possible combinations of faults. Because the vibration signals corresponding to faults on bearings are typically transients with a wide frequency range occurring around the excited mechanical resonant modes and drowned in the acquired vibration signals, it is necessary to emphasize these excited transients using a matched bank of filters. The dominant resonant modes of a bearing and the system modes produced from fault source are usually unknown, and so there is a need for robust global search methods able to deal with non-linear problems with multiple optima. Instead of applying an optimization method repeatedly for every optimum, non-dominated extensions of the genetic algorithm can be applied only one time to find and maintain multiple optimal solutions. The efficiency of the proposed approach - niching genetic algorithm with fitness sharing - was evaluated using vibration signals acquired on four tapered roller bearings with defined combinations of seeded faults.