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.     

Fault diagnosis of rotating machinery based on the statistical parameters of wavelet packet paving and a generic support vector regressive classifier

The fault diagnosis of rotating machinery has attracted considerable research attention in recent years because such components as bearings and gears frequently suffer failure, resulting in unexpected machine breakdowns. Signal processing-based condition monitoring and fault diagnosis methods have proved effective in fault identification, but the revelation of faults from the resulting signals requires a high degree of expertise. In addition, it is difficult to extract the fault-induced signatures in complex machinery via signal processing-based methods. In this paper, a new intelligent fault diagnosis scheme based on the extraction of statistical parameters from the paving of a wavelet packet transform (WPT), a distance evaluation technique (DET) and a support vector regression (SVR)-based generic multi-class solver is proposed. The collected signals are first pre-processed by the WPT at different decomposition depths. In this paper, the wavelet packet coefficients at different decomposition depths are referred to as WPT paving. Statistical parameters are then extracted from the signals obtained via the WPT at different decomposition depths. In selecting the sensitive fault features for fault pattern expression, a DET is employed to reduce the dimensionality of the feature space. Finally, a SVR-based generic multi-class solver is proposed to identify the different fault patterns of rotating machinery. The effectiveness of the proposed intelligent fault diagnosis scheme is validated separately using datasets from bearing and gearbox test rigs. In addition, the effects of different wavelet basis functions on the performance of the proposed scheme are investigated experimentally. The results demonstrate that the proposed intelligent fault diagnosis scheme is highly accurate in differentiating the fault patterns of both bearings and gears.     

基于小波包和PSO-Elman神经网络的滚动轴承故障诊断

针对滚动轴承的故障诊断,分析滚动轴承故障机理及特点,提出基于小波包分析的滚动轴承振动信号的特征向量提取算法,并建立PSO-Elman神经网络进行故障诊断和识别。将滚动轴承故障振动信号进行小波包分解,构造频带能量谱作为特征向量,输入PSO-Elman神经网络对故障进行识别。试验结果表明,基于小波包分析和PSO-Elman神经网络相结合的方法可准确地实现滚动轴承的故障诊断。     

基于主成分分析的齿轮箱故障特征融合分析

为有效降低齿轮箱故障特征的维数并提高诊断准确率,提出了基于主成分分析法的齿轮箱故障特征融合方法,并结合支持向量机和BP神经网络对诊断的准确率进行了分析。以齿轮箱中不同裂纹齿轮为对象,选取能够表征齿轮箱故障状态的时域、频域和基于希尔伯特变换的36个特征,提取累积贡献率达到95%以上的主成分并输入支持向量机分类器中进行分类识别,用BP神经网络分类器进行结果的比较分析。结果表明,采用主成分分析法与支持向量机相结合的方法,既能降低特征维数,降低计算的复杂性,又能有效地表征齿轮箱的运行状态,识别不同裂纹水平的齿轮,比单独使用支持向量机分类器的方法诊断准确率更高,训练时间更短。     

小波分析在车辆故障诊断中的应用

车辆变速箱振动信号可用小波分析法预处理后，再用小波包能量尺度图分析法识别故障，按此法对BJ212变速箱准确地进行了故障识别，结果表明利用小波分析进行变速箱故障诊断的方法行之有效。     

多共振分量融合CNN的行星齿轮箱故障诊断

针对行星齿轮箱中各部件所激起的振动成分混叠、早期故障特征经常被较强的各级齿轮谐波成分以及环境噪声所湮没的问题，提出一种多共振分量融合卷积神经网络（multi-resonance component fusion based convolutional neural network，简称MRCF-CNN）的行星齿轮箱故障诊断方法。首先，对振动信号进行共振稀疏分解，得到包含齿轮谐波成分的高共振分量和可能包含轴承故障冲击成分的低共振分量；其次，构建多共振分量融合卷积神经网络，将得到的高、低共振分量和原始振动信号进行自适应的特征级融合，通过有监督的方式训练模型并进行行星齿轮箱故障诊断。对行星齿轮箱实验数据的分析结果表明，该方法能够有效分类行星齿轮箱中滚动轴承和齿轮的故障，成功对行星齿轮箱故障进行诊断，同时能够进一步增强卷积神经网络对振动信号所蕴含的故障信息的辨识能力。     

基于小波分析的重载卡车变速箱装配品质在线检测方法研究

为确定某型变速箱装配品质,从变速箱内部结构出发,简要介绍了变速箱常见装配故障,从理论上分析了变速箱在各挡位情况下各齿轮和轴承等零件的常见故障特征频率,并搭建声压信号采集平台,采集变速箱不同挡位运转时产生的声压信号,利用小波阈值去噪法对采集的原始声压信号进行去噪,并运用小波分析对去噪后的声压信号进行分解,对相应的频段信号进行谱分析,结合理论分析与实验分析的结果,获得变速箱的装配故障特征,为检查变速箱装配品质提供依据。该研究对变速箱装配品质检测具有一定的参考意义。     

改进小波包与RBF网络在轴承诊断中的应用

基于故障轴承的特征提取,提出一种基于小波包与径向基RBF神经网络相结合的故障诊断方法,克服了以往常用诊断方法中的小波BP神经网络网络收敛慢、训练时间长、而且常常陷入局部极小点的缺点。采用小波滤波技术对采集到的滚动轴承振动信号进行滤波处理,利用小波包分解获得滚动轴承振动信号的特征向量作为故障样本对RBF网络进行训练,进行了详细的故障诊断试验研究。实验结果表明训练好的RBF网络能够很好地诊断出轴承故障类型,故本方法在旋转机械故障诊断方面具有良好的应用价值。     

基于小波包-模糊神经网络的发动机泵机组故障诊断

提出了利用小波包分解、神经网络和模糊诊断的方法进行发动机泵机组故障诊断;运用小波包频带能量分解,可以在不丢失振动信息的情况下降低信号的维数,提高神经网络的识别能力;运用了神经网络使故障诊断具有自适应、自学习能力,对发动机泵机组的各类故障进行分类和训练,得到了满意的效果.     

基于小波包分解和支持向量机的机械故障诊断方法

提出应用小波包分解和支持向量机进行机械故障诊断的方法。该方法将振动信号小波包分解后的频带能量作为特征向量，输入到由多个支持向量机构成的多故障分类器中进行故障识别和分类。试验结果表明，与神经网络相比，采用支持向量机进行故障诊断可以获得更高的诊断精度，表明该方法是有效的、可行的。     

基于小波包变换与样本熵的滚动轴承故障诊断

针对滚动轴承振动信号的不规则性和复杂性可以反映轴承故障的发生和发展,提出一种基于小波包变换与样本熵的轴承故障诊断方法。样本熵可以较少地依赖时间序列的长度,将轴承振动信号进行3层小波包分解,利用分解得到的各个频带的样本熵值作为特征向量,利用支持向量机对轴承故障进行分类。对轴承内圈故障、滚动体故障和外圈故障3种故障及不同损伤程度的实测数据进行实验,结果表明该方法取得较高的识别率,具有一定的工程应用价值。     

Gearbox fault detection using Hilbert and wavelet packet transform

Demodulation is an important issue in gearbox fault detection. Non-stationary modulating signals increase difficulties of demodulation. Though wavelet packet transform has better time–frequency localisation, because of the existence of meshing frequencies, their harmonics, and coupling frequencies generated by modulation, fault detection results using wavelet packet transform alone are usually unsatisfactory, especially for a multi-stage gearbox which contains close or identical frequency components. This paper proposes a new fault detection method that combines Hilbert transform and wavelet packet transform. Both simulated signals and real vibration signals collected from a gearbox dynamics simulator are used to verify the proposed method. Analysed results show that the proposed method is effective to extract modulating signal and help to detect the early gear fault.     

基于小波包变换与神经网络的齿轮故障诊断方法

对齿轮箱故障诊断问题进行研究,由于齿轮的振动信号是非平稳信号,常规的齿轮特征提取方法难以从振动信号中提取有效故障特征信息。笔者采用小波包理论对齿轮振动信号应用db12小波进行多层分解后,从而对信号进行消噪,并对消噪后的信号进行小波包3层分解及系数重构,再次对各频段能量进行处理分析从而得到特征向量。最终应用归一化方法对特征向量处理后再结合RBF神经网络进行故障诊断,并且取得了良好的诊断效果。     

基于小波包和极限学习机的汽车发动机失火故障识别

针对缸盖振动信号的非平稳特性,提出了基于小波包相关系数和极限学习机的汽车发动机失火故障诊断系统.首先,对原始信号进行小波包分解,然后计算得到每个样本的能量熵和每个样本各子频带重构信号与原始信号的相关性系数.分别利用相关系数法和能量熵融合峭度的方法建立特征向量,随后输入到BP神经网络和极限学习机中进行训练和测试.实验结果表明,该方法可以有效地反映故障产生的差异并准确地识别单缸失火故障,具有精度高、训练时间短的优点.     

Quantitative diagnosis of fault severity trend of rolling element bearings

The condition monitoring and fault diagnosis of rolling element bearings are particularly crucial in rotating mechanical applications in industry. A bearing fault signal contains information not only about fault condition and fault type but also the severity of the fault. This means fault severity quantitative analysis is one of most active and valid ways to realize proper maintenance decision. Aiming at the deficiency of the research in bearing single point pitting fault quantitative diagnosis, a new back-propagation neural network method based on wavelet packet decomposition coefficient entropy is proposed. The three levels of wavelet packet coefficient entropy(WPCE) is introduced as a characteristic input vector to the BPNN. Compared with the wavelet packet decomposition energy ratio input vector, WPCE shows more sensitive in distinguishing from the different fault severity degree of the measured signal. The engineering application results show that the quantitative trend fault diagnosis is realized in the different fault degree of the single point bearing pitting fault. The breakthrough attempt from quantitative to qualitative on the pattern recognition of rolling element bearings fault diagnosis is realized.     

基于小波包分解与DAG SVM的柱塞泵故障诊断

针对柱塞泵检测诊断中故障特征模糊、成因复杂、难以准确定位的问题,结合决策树与支持向量机提出一种基于小波包分解与DAG SVM的柱塞泵故障诊断方法。该方法预先对所用C SVM和RBF核函数的参数进行优化,而后采用db5小波包对泵体振动信号进行三层分解以提取特征向量,将特征向量输入支持向量机完成其训练及模式识别过程。同时设计了柱塞泵故障诊断的一体化装置,通过模拟不同故障,利用已知故障样本完成支持向量机的训练过程,进而对待测样本进行故障模式识别。诊断结果与样本已知状态相符,验证了该方法的准确性。     

HYBRID WAVELET PACKET-TEAGER ENERGY OPERATOR ANALYSIS AND ITS APPLICATION FOR GEARBOX FAULT DIAGNOSIS

Based on wavelet packet decomposition (WPD) algorithm and Teager energy operator (TEO), a novel gearbox fault detection and diagnosis method is proposed. Its process is expatiated after the principles of WPD and TEO modulation are introduced respectively. The preprocessed signal is interpolated with the cubic spline function, then expanded over the selected basis wavelets. Grouping its wavelet packet components of the signal based on the minimum entropy criterion, the interpolated signal can be decomposed into its dominant components with nearly distinct fault frequency contents. To extract the demodulation information of each dominant component, TEO is used. The performance of the proposed method is assessed by means of several tests on vibration signals collected from the gearbox mounted on a heavy truck. It is proved that hybrid WPD-TEO method is effective and robust for detecting and diagnosing localized gearbox faults.     

Digital communication signals identification using an efficient recognizer

Automatic recognition of the communication signals plays an important role for various applications. Most of the existing techniques require high levels of signal to noise ratio (SNR). In this paper, we propose a high efficient technique for classification of the digital modulations that requires a low level of SNRs. This technique includes two main modules: feature extraction module and the classifier module. In the feature extraction module we use the auto-regressive modeling together other useful features. These features are a combination set of the entropy and energy of the signal, variance of the coefficients wavelet packet transform, fourth order of moment and zero-crossing rate. In the classifier module we have used the two structures of the neural networks: multi-layer perceptron (MLP) neural network and radial basis neural networks. Simulation results show the proposed technique has very high recognition accuracy for identification of the considered digital modulations even at very low SNRs.     

基于核超限学习机的轴向柱塞泵故障诊断

由于柱塞泵内部结构复杂且结构之间相互耦合, 致使对其进行故障诊断的难度也随之增加。为了提高算法的可靠性和诊断速度, 将核函数与超限学习机结合的方法用于柱塞泵故障诊断。首先, 通过加速度计和流量计采集到泵在正常和不同故障工况下的振动和流量信号, 同时对其采用小波包分解进行去噪;然后提取了时域无量纲指标和小波包分解的频带能量值中最大频带能量和系统中流量计的流量值, 共8维特征向量;最后用核超限学习机对4种故障(滑靴磨损、配油盘磨损、中心弹簧失效、松靴)进行识别与诊断。结果表明, 将核超限学习机用于故障诊断, 相比于超限学习机和传统的智能诊断算法支持向量机、BP神经网络有明显的优势。     

基于小波包能量谱和ELM的光伏逆变器多故障在线诊断

以三电平光伏逆变器为研究对象,提出一种多故障模式快速诊断新方法。首先,利用小波包分解提取出三电平逆变器的桥臂电压和上、下管电压信号的能量谱特征向量,并利用主成分分析降维后获取故障特征向量;然后,基于极端学习机诊断模型分离出单器件及多器件开路等多种故障模式。实验结果表明,相比于传统BP神经网络、最小二乘支持向量机故障诊断方法,该方法检测信号易获取,抗干扰性强,诊断速度快、精度高,减小了诊断成本和复杂性,适用于在线诊断。