Diesel Engine Valve Clearance Fault Diagnosis Based on Features Extraction Techniques and FastICA-SVM

Numerous vibration-based techniques are rarely used in diesel engines fault diagnosis in a direct way, due to the surface vibration signals of diesel engines with the complex non-stationary and nonlinear time-varying features. To investigate the fault diagnosis of diesel engines,fractal correlation dimension, wavelet energy and entropy as features reflecting the diesel engine fault fractal and energy characteristics are extracted from the decomposed signals through analyzing vibration acceleration signals derived from the cylinder head in seven different states of valve train. An intelligent fault detector FastICA-SVM is applied for diesel engine fault diagnosis and classification.The results demonstrate that FastICA-SVM achieves higher classification accuracy and makes better generalization performance in small samples recognition. Besides,the fractal correlation dimension and wavelet energy and entropy as the special features of diesel engine vibration signal are considered as input vectors of classifier Fast ICASVM and could produce the excellent classification results.The proposed methodology improves the accuracy of feature extraction and the fault diagnosis of diesel engines.     

基于Wigner分布和分形维数的柴油机故障诊断

针对柴油机配气机构故障诊断问题,提出了一种基于Wigner分布和差分分形盒维数的故障诊断方法。首先,利用改进局部均值分解算法对柴油机缸盖振动信号进行分解,并采用相关性分析剔除噪声和伪分量;然后,分别对各相关分量进行Wigner时频分析,将结果线性叠加得到振动时频图,再提取图像的差分分形盒维数作为故障特征;最后,利用k-最近邻(k-NN)实现故障诊断。仿真结果表明,改进局部均值分解算法可以抑制Wigner分布交叉项的干扰。实验结果显示,差分分形盒维数优于其他6种典型故障特征,利用本研究提出的方法对配气机构进行故障诊断的正确率为97.2%,该方法可以用于柴油机配气机构故障诊断。     

切片双谱分析在离心泵故障诊断中的应用

运用双谱及切片双谱分析技术对离心泵不同状态下的振动信号进行分析表明,离心泵在正常运行、地脚螺栓松动和空化状态下的双谱图的特征有着明显的差别,可以通过双谱对故障信号进行初步分类,且双谱的对角切片和反对角切片可以显著降低噪声干扰,进一步提取出故障特征频率,故可对离心泵的故障信号进行准确的分类和诊断。     

柴油机振动信号快速稀疏分解与二维特征编码

针对柴油机故障诊断方法中的信号时频表征及特征提取问题,提出一种基于振动信号快速稀疏分解与二维时频特征编码识别的柴油机智能故障诊断方法。首先,为了获得时、频聚集性优良的时频图像,提出一种随分解残差信号自适应更新Gabor字典的改进匹配追踪(adaptive matching pursuit,简称AMP)算法,利用AMP算法将柴油机振动信号分解后叠加各原子分量的Wigner-Ville分布,获取原信号的稀疏分解时频图像;然后,为提取时频图像的特征参量,提出了双向二维非负矩阵分解(two-directional,2-dimensional non-negative matrix factorization,简称TD2DNMF)算法,用于对时频图像的幅值矩阵进行特征编码,获取蕴含在时频图像内部的低维特征,并利用最近邻分类器实现了时频图像的自动分类识别。将提出的方法应用于4种不同状态柴油机气门故障的诊断试验中,结果表明,该方法能够获得无交叉项干扰、聚集性好的时频图像,使各时频分量的物理意义更加明确,并改进了传统图像模式识别中的特征参数提取方法,是一种有效的柴油机故障诊断方法。     

分形维数在内燃机振动诊断中的应用

将分形理论引入内燃机的振动诊断中,根据内燃机的配气定时,着重研究了缸盖振动信号中对应燃烧段的数据,计算其关联维数,将关联维数用于刻划内燃机缸盖在气门不同状态时表现的非线性行为,从而进行故障诊断与分类。结果表明,当气门在不同状态时,缺盖振动信号中对应燃烧段数据的关联维数是不同的,可以将其作为判断气门漏气的一个诊断特征量。     

柴油机缸盖振动信号典型特征提取

针对柴油机缸盖振动信号信噪比低且呈非平稳特性,提取柴油机振动信号的典型特征。通过分析缸盖在不同时刻受到的激振,判断汽缸各个部件的工作情况;提取信号振动烈度,并分析烈度与柴油机转速的变化关系,为柴油机的在线控制和故障诊断提供依据。     

A New Intelligent Fusion Method of Multi-Dimensional Sensors and Its Application to Tribo-System Fault Diagnosis of Marine Diesel Engines

Marine diesel engines, a critical component to provide power for entire ships, have been received and still need considerable attentions to ensure their safety operation. Vibration and wear debris analysis are currently the most popular techniques for diesel engine condition monitoring and fault diagnosis. However, they are usually used independently in practice, and limited work has been done to address the integration of data collected using the two techniques. To enhance early fault detections, a new fault diagnosis technique for the marine diesel engine has been proposed by the information fusion of the vibration and wear particle analyses in this paper. A new independent component analysis with reference algorithm (ICA-R) using the empirical mode decomposition based reference extraction scheme was adopted to identify the characteristic source signals of the engine vibration collected from multi-channel sensors. The advantage of this approach performed at a data fusion level is that the ICA-R can extract only the relevant source directly related to the engine fault features in one separation cycle via incorporating prior knowledge. The statistical values of the recovered source signals were then calculated. The above vibration features, along with the wear particle characteristics, were used as the feature vectors for the engine fault detection. Lastly, the improved simplified fuzzy ARTMAP (SFAM) was applied to integrate the distinctive features extracted from the two techniques at a decision level to detect faults in a supervised learning manner. Particularly, the immune particle swarm optimization was used to tune the vigilance parameter of the SFAM to improve the identification performance. The experimental tests were implemented on a diesel engine set-up to evaluate the effectiveness of the proposed diagnosis approach. The diagnosis results have shown that distinguished fault features can be extracted and the fault identification accuracy is satisfactory. Moreover, the fault detection rate of the integration approach has been enhanced by 16.0?% or better when compared with using the two techniques separately.     

基于小波包分解的机械振动信号分析

提出了一种新的基于小波包的振动信号故障特征提取方法,运用这种方法对柴油机表面振动信号经过小波包降噪处理,有效地剔除柴油机表面振动信号的噪声干扰,提高信号的信噪比。对降噪信号提取频带能量特征,为神经网络故障诊断提供了新的故障样本。     

关联维数分析方法在液压泵多故障诊断中的应用研究

针对液压泵故障信号非线性和非平稳性特征,提出了利用相空间重构技术和分形理论相结合的特征关联维数提取方法。该方法将液压泵不同故障模式下获取的一维振动信号重构到高维相空间,进行信息深层挖掘;通过对相空间特征信号关联维数变化规律的分析,找出对故障反映敏感的关联维数,由此进行故障识别。通过实验验证,该方法提取的关联维数能有效反映液压泵的故障特征,为液压泵多故障诊断方法的研究提供可靠的特征信息,具有良好的应用前景。     

基于CPSO-BP神经网络的柴油机排气门间隙故障诊断

针对柴油机排气门间隙故障信号不易提取的特点,提出了将混沌粒子群神经网(Chaotic particle swarm optimization-Back Propagation,CPSO-BP)聚类模型应用于柴油机排气门间隙故障诊断.首先,采用经验模式分解(Empirical Mode Decomposition,EMD)对柴油机振动信号进行分解,将得到的前6个模态函数能量百分比作为反映故障状态的特征参数,重构BP神经网并用混沌粒子群算法对其结构和权值进行优化;最后,基于优化的神经网对排气门间隙为0.2mm,0.4mm,0.6mm等3种故障工况的信号进行聚类.结果表明:所有样本的测试结果均与实际状况一致,该方法可以较好地用于排气门间隙故障诊断.     

基于信源估计和频域反卷积的滚动轴承故障特征分离与辨识

针对轴承故障的振动特征由于受到强振源的抑制作用而增加了故障分离与辨识难度的问题,建立了基于信源估计和频域反卷积的故障诊断方法。利用小波包分解将信号分离成多个子带信号,并和奇异值分解相结合,解决欠定条件下的信号源数估计问题;根据估计的源数,选取相应维数的观测信号,通过短时傅里叶变换、复数域独立分量分析、相关排序、短时傅里叶逆变换,完成频域反卷积的分析过程,实现故障特征的分离与提取。仿真信号和实验数据均验证了该方法在故障特征分离与微弱特征辨识中的有效性。     

基于EMD和分形维数的转子系统故障诊断

提出了一种基于EMD方法和分形维数的转子系统故障诊断方法。利用EMD方法将转子振动信号进行分解,得到若干个基本模式分量,然后将包含主要故障信息的几个基本模式分量相加得到降噪后的转子振动信号,求得降噪后的转子振动信号的分形维数。试验数据的分析结果表明,在不同的故障状态下,采用EMD方法对转子振动信号降噪后求得的分形维数是不同的,从而可以通过分形维数的大小有效地判断转子系统的工作状态和故障类型。     

发动机异常检测多目标优化方法

针对柴油发动机异常检测中的特征选择和分类器参数与检测精度之间的耦合关系,提出了一种基于非支配排序粒子群优化的柴油发动机异常检测封装式多目标同步优化方法.利用双树复小波包的分解与重构,对发动机振动信号进行时域、频域和时频域多角度特征提取,构建了较完备的特征参数集,分析了故障诊断中特征选择与分类器参数优化对检测精度的影响,运用非支配排序粒子群优化算法对多个优化目标进行协调和折衷处理,同时追求特征参数子集维数最小化和分类正确率最大化.实验数据分析表明,该方法能够寻找出最优的特征子集和分类器参数,提高柴油发动机异常检测的精度和效率.     

基于LabVIEW的柴油机故障诊断虚拟仪器开发

开发了一套基于分形理论,使用柴油机声音信号进行故障诊断的虚拟仪器.介绍了其硬件平台的搭建,结合LabVIEW与MATLAB混合编程阐述了软件平台的设计,该平台由声音信号采集、信号预处理、故障特征提取、故障诊断4个模块构成.在故障特征提取模块中对分形关联维数的G-P算法进行了论述.结合柴油机故障实例测试表明:柴油机声音信号关联维数随工作状况改变有明显变化,能作为故障诊断的特征量,通过该虚拟仪器能迅速有效地识别出故障.     

基于瞬时转速双谱分析的柴油机气阀泄漏诊断方法

在对双谱和瞬时转速信号的特点进行分析的基础上,测量了6-135柴油机在正常和气阀泄漏故障状态下的瞬时转速,分别计算其双谱,得到了具有明显区别的双谱图;通过计算双谱对角切片,可以容易且有效地识别故障的存在;根据瞬时转速的双谱特征进行故障诊断,故障特征明显,诊断效果良好。     

一类滚动轴承振动信号特征提取与模式识别

复杂工况下滚动轴承振动信号通常表现出强烈的非平稳性,而一些典型的故障特征往往容易被其他成分所掩盖,这为故障特征提取带来了很大的困难。针对这一问题,首先,提出一种基于同步压缩小波变换的滚动轴承信号特征提取方法,对多种工况下的滚动轴承振动信号进行分析,提取出能够有效反映滚动轴承工况的信号特征空间;其次,采用非负矩阵分解对信号特征空间进行精简和优化,提炼出用于滚动轴承故障诊断和模式识别的特征参数;最后,采用支持向量机对多种工况的滚动轴承振动信号进行分类。研究结果表明,与传统的时域特征参数提取方法相比,所提出的方法具有更高的分类准确率。     

基于Matlab的柴油机故障诊断

利用小波分析、BP神经网络技术处理柴油机工作时产生的振动信号。在输入层对振动信号进行小波变换,提取其在多尺度下的特征作为故障特征向量。根据这些特征向量进行BP网络的分析,以对柴油机进行故障诊断。在实验台上模拟了多个故障,并对柴油机工作时在汽缸盖上方振动信号采集和处理,对几种故障模式进行了成功的判别。结果表明此方法是可行和有效的。     

Weak fault feature extraction of rolling bearing under strong poisson noise and variable speed conditions

Fault feature extraction of the rolling bearing under strong background noise is always a difficult problem in bearing fault diagnosis. At present, most of the research focuses on weak signal extraction under Gaussian white noise and has certain practical significance. However, the noise in engineering is often complex and changeable, Gaussian white noise cannot fully simulate the actual strong background noise. Poisson white noise is a type of typical non-Gaussian noise, which widely exists in complex mechanical impact. It is of great significance to study the weak fault feature extraction of a faulty bearing under this type of noise. At the same time, variable speed conditions occupy most rotating machinery speed conditions. Non-stationary vibration signals make it difficult to extract fault features, and the frequency spectrum ambiguity will occur because of speed fluctuation. To solve the above problems, a method of weak feature extraction of a faulty bearing based on computed order analysis (COA) and adaptive stochastic resonance (SR) is proposed. Firstly, by numerical simulation, the non-stationary fault characteristic signal corrupted with strong Poisson noise is transformed into a stationary signal in the angle domain by COA. Secondly, the influence of the parameters of the pulse arrival rate and noise intensity of Poisson white noise on the optimal SR response in the angle domain are studied, and the influence of the parameters of Poisson white noise on the fault feature extraction is given. Then, adaptive SR method is used to extract and enhance fault feature information. Finally, the effectiveness of this method in weak fault characteristic signal extraction under strong Poisson noise is verified by experiments. Numerical simulation and experimental results verify the effectiveness of the proposed method in bearing fault diagnosis under strong Poisson noise and variable speed conditions.

     

基于多尺度核独立成分分析的柴油机故障诊断

为提高利用缸盖振动信号进行柴油机故障诊断的精度和速度,提出了一种基于多尺度核独立成分分析提取故障敏感频带的柴油机故障诊断方法。首先,提出奇异值能量标准谱对缸盖振动信号中的微弱冲击特征进行增强;然后,对信号进行固有时间尺度分解,并基于相关性准则选择有效频带分量;最后,利用核独立成分分析消除有效频带之间的频带混叠,得到故障敏感信息集中的独立频带,并计算其自回归模型(auto regression model,简称AR)参数、模糊熵和标准化能量矩作为特征向量输入核极限学习机(kernel extreme learning machine,简称KELM)进行柴油机故障诊断。试验分析结果表明,该方法可以快速准确地提取缸盖振动信号中的柴油机故障敏感频带,增强故障敏感特征,故障诊断准确率达到99.65%。     

Diagnosis of bearing defects using tunable Q-wavelet transform

Defects in rolling element bearings are foremost cause of failure in rotating machines. The accurate and fast diagnosis of bearing defects like spall, dents, pits, cracks etc. on the various component of bearing can be accomplished by analysis of vibration signals using various advanced signal processing techniques. In this work, a new technique for the diagnosis of bearing defects using tunable Q-wavelet transform and fractal based features has been presented. The vibration signals have been recorded experimentally. These signals are decomposed into a number of sub-bands using tunable Q-wavelet transform for effective feature extraction. Classical statistical features and fractal dimension based features such as Higuchi fractal dimensions and Katz fractal dimensions are computed for each decomposed sub-band. These features obtained using tunable Q-wavelet transform of vibration signal are having better capability to classify defects through various machine learning algorithms.