综合改进奇异谱分解和奇异值分解的齿轮故障特征提取方法

针对齿轮故障特征微弱，在强背景噪声下难以有效提取的问题，提出了一种改进奇异谱分解（ISSD）结合奇异值分解（SVD）的齿轮故障特征提取方法。针对奇异谱分解（SSD）算法中模态参数需凭经验选取的缺陷，基于散布熵优化算法对SSD算法进行了改进，在得到既定的一组奇异谱分量的基础上，根据峭度值最大准则筛选出了最佳奇异谱分量并进行了SVD处理，采用奇异值能量标准谱自适应地确定了信号重构阶数以还原信号和提高降噪效果。最后对信号进行包络解调以提取齿轮故障特征，将所提方法运用到仿真信号和齿轮实测信号中，并同传统包络谱、SSD包络谱以及经验模态分解结合SVD(EMD-SVD)方法进行了对比分析，结果表明，所提方法的降噪和特征提取效果更佳，能够更加有效地实现齿轮故障的判别。     

运用EMD和GA SVM的齿轮故障特征提取与选择

针对齿轮故障特征提取,首先将齿轮箱振动信号进行经验模态分解,得到一组固有模态函数.计算各固有模态函数的能量和矩阵的奇异值,采用Shannon熵和Renyi熵度量能量和奇异值分布,构成原始特征子集.再采用遗传算法和最小二乘支持向量机的Wrapper方法选择最优特征子集.该方法能够利用较少的特征参数集准确判别齿轮故障,提高了齿轮故障诊断的精度与效率.     

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。     

A Roller Bearing Fault Diagnosis Method Based on Improved LMD and SVM

Aiming at the non-stationary features of the roller bearing fault vibration signal,a roller bearing fault diagnosis method based on improved Local Mean Decomposition(LMD)and Support Vector Machine(SVM)is proposed.In this paper,firstly,the wavelet analysis is introduced to the signal decomposition and reconstruction;secondly,the LMD method is used to decompose the reconstruction signal obtained by the wavelet analysis into a number of Product Functions(PFs)that include main fault characteristics,thus,the initial feature vector matrixes could be formed automatically;Thirdly,by applying the Singular Value Decomposition(SVD)techniques to the initial feature vector matrixes,the singular values of the matrixes can be obtained,which can be used as the fault feature vectors of the roller bearing and serve as the input vectors of the SVM classifier;Finally,the recognition results can be obtained from the SVM output.The results of analysis show that the proposed method can be applied to roller bearing fault diagnosis effectively.     

基于小波—奇异值分解差分谱的弱故障特征提取方法

对于一些复杂信号中的弱故障特征信息,以往的两种小波—奇异值分解(Singular value decompositiom,SVD)组合模式的特征提取效果不佳,从小波的频率窗特性出发分析了出现这种问题的原因,进而对复杂信号的奇异值分布规律进行研究,据此提出一种新的小波-SVD差分谱组合模式。对原始信号做小波分解得到一系列细节信号后,不再将这些信号简单地排列成矩阵,而是利用每个细节信号构造特定结构的Hankel矩阵,再通过SVD对每个矩阵做正交化分解,并利用奇异值差分谱来选择特征奇异值进行SVD重构,由此实现对弱故障特征信息的提取。对一个轴承振动信号的处理结果证实该方法对复杂信号中的弱故障特征信息具有优良的提取效果,其获得的故障特征波形非常清晰,克服了以往小波-SVD组合模式对弱故障特征提取效果不佳的缺陷。     

一种基于EMD与多特征支持向量机(SVM)故障诊断方法

针对齿轮箱故障振动信号的不平稳非线性冲击行为,本文提出了一种基于经验模态分解的特征值提取及多特征支持向量机的智能诊断方法。在电机频率分别取30 Hz、35 Hz、40 Hz;载荷分别取0 N∙M、15 N∙M、30 N∙M;采样频率为1500 Hz条件下,进行齿轮正常状态、齿面磨损和齿轮裂痕故障模拟实验。试验结果表明:该创新方法在有限样本数据分析中可以准确、有效地对齿轮箱的工作状态和故障类型进行分类,且支持向量机在故障诊断中使用方便,可以提高诊断的精确性,在齿轮箱故障诊断或类似振动信号的检测应用中具有很强的实用性。     

基于BITD和同态滤波解调的齿轮故障诊断方法

针对齿轮故障振动信号的非平稳特征以及本征时间尺度分解(ITD)方法的缺点,提出了B样条改进的本征时间尺度分解(BITD)和同态滤波解调相结合的故障诊断方法。首先采用BITD方法对齿轮振动信号进行分解,将其分解为若干个合理旋转分量之和,然后用相关系数筛选出最能表征故障信息的合理旋转分量进行同态滤波解调来提取故障特征。仿真信号与齿轮故障诊断工程实例分析验证了该方法的有效性。     

基于奇异值融合的机械设备盲信息提取

针对机械设备的故障特征信息提取问题,提出了基于奇异值融合的机械盲信息提取方法。首先,由机械振动测量信号分离振动源信号,并进行包络解调组成包络信号矩阵,进而进行奇异值分解,提取矩阵的奇异值均值和奇异值熵作为故障特征信息;然后,针对分离矩阵直接进行奇异值分解,提取奇异值作为故障特征信息;最后,将包络信号矩阵奇异值均值、奇异值熵和分离矩阵奇异值进行特征层信息融合作为机械设备的故障特征信息。将该方法应用于液压齿轮泵可以有效地提取机械设备盲特征信息。     

VMD能量熵与随机森林相结合的齿轮故障诊断

针对齿轮故障的非线性、非稳定性特点和单个分类器在故障诊断中准确率低的问题,提出了一种基于变分模态分解(VMD)和随机森林(RF)的齿轮故障识别方法。首先,采用变分模态分解将振动信号分解成有限个本征模态函数(IMFs),并与总体平均经验模态分解对比其分解效果;其次,计算各模态函数的能量熵,将能量熵作为评判齿轮状态的标准,构建特征向量;最后,将特征向量输入随机森林进行故障分类。结果表明,与支持向量机(SVM)识别方法对比,该方法具有较强的学习能力以及较高的诊断精度。     

基于LCD和KNNCH分类算法的齿轮故障诊断方法

提出了一种基于局部特征尺度分解(LCD)和核最近邻凸包（KNNCH）分类算法的齿轮故障诊断方法。该方法采用LCD对齿轮原始振动信号进行分解得到若干内禀尺度分量(ISC),然后提取包含主要信息的ISC分量的能量作为特征向量输入到KNNCH分类器,根据其输出结果来判断齿轮的工作状态。实验分析结果表明,所提出的方法能有效地提取齿轮故障特征信息,而且在小样本的情况下仍能准确地对齿轮的工作状态进行识别。同时,与支持向量机(SVM)算法的对比分析结果表明,KNNCH算法能取得与SVM算法相当或更高的正确识别率。     

奇异值熵和支持向量机的齿轮故障诊断

提出了一种基于总体平均经验模态分解(ensemble empirical mode decomposition,简称EEMD)奇异值熵和支持向量机的齿轮故障诊断方法.首先,通过EEMD方法将非平稳的原始加速度振动信号分解成若干个平稳的本征模式分量,将得到的若干个本征模式分量自动形成初始特征向量矩阵;然后,对该矩阵进行奇异值分解,提取其奇异值作为故障特征向量,并对其进行归一化,求得奇异值熵,根据奇异值熵值大小可以判断齿轮的故障类型;最后,将奇异值故障特征向量作为支持向量机的输入,判断齿轮的工作状态和故障类型.试验结果表明,即使在小样本情况下,基于EEMD奇异值分解和支持向量机的故障诊断方法仍能有效地识别齿轮的工作状态和故障类型.     

基于柔性形态滤波和支持矢量机的滚动轴承故障诊断方法

针对滚动轴承故障振动信号的强噪声背景以及现实中不易获取大量典型故障样本的特点,提出一种基于柔性形态滤波和支持矢量机(Support vector machine, SVM)的滚动轴承故障诊断方法。柔性形态滤波既可以有效地提取出信号的边缘轮廓和信号的形状特征,同时又具有稳健性;SVM具有良好的分类性能,特别在小样本、非线性及高维特征空间中具有较好的推广能力;SVM分类器的惩罚因子和核函数参数采用经典粒子群优化算法进行优化,避免传统方法对初始点和样本的依赖。首先对振动信号进行柔性形态滤波,然后提取滤波后信号的故障特征频率的归一化能量为特征矢量作为SVM分类器的输入参数,用于区分滚动轴承的外圈、内圈和滚动体故障,SVM分类器的参数采用标准粒子群优化算法进行优化。试验结果表明了方法的有效性。     

A roller bearing fault diagnosis method based on hierarchical entropy and support vector machine with particle swarm optimization algorithm

Targeting the non-linear dynamic characteristics of roller bearing faulty signals, a fault feature extraction method based on hierarchical entropy (HE) is proposed in this paper. SampEns of 8 hierarchical decomposition nodes (e.g. HE at scale 4) are calculated to serve as fault feature vectors, which takes into account not only the low frequency components but also high frequency components of the bearing vibration signals. HE can extract more faulty information than multi-scale entropy (MSE) which considers only the low frequency components. After extracting HE as feature vectors, a multi-class support vector machine (SVM) is trained to achieve a prediction model by using particle swarm optimization (PSO) to seek the optimal parameters of SVM, and then ten different bearing conditions are identified through the obtained SVM model. The experimental results indicate that HE can depict the characteristics of the bearing vibration signal more accurately and more completely than MSE, and the proposed approach based on HE can identify various bearing conditions effectively and accurately and is superior to that based on MSE.     

基于小波包参数模型的滚动轴承智能故障诊断

针对平稳自回归模型无法准确描述滚动轴承振动信号的非平稳性,提出一种结合小波包分解与自回归模型的故障特征提取方法,以提取能准确反映轴承运行状态的特征向量。首先,通过小波包变换对滚动轴承运行时产生的非平稳振动信号进行分解,得到一系列刻画原始信号特征的系数;然后,利用自相关算法对各系数建立自回归模型,并将自回归模型的参数作为特征向量;最后,采用支持向量机分类器对提取的特征向量进行故障分类,从而实现滚动轴承的智能故障诊断。仿真结果表明该方法的有效性。     

基于奇异值分解和支持向量机的转子故障诊断

为了准确识别转子不平衡、不对中、碰摩和油膜涡动等故障,利用小波分析对转子故障信号进行4层分解,将频率由高到低的5个分支信号作为奇异值分解（Singular Value Decomposition,SVD）矩阵的行向量,经奇异值分解后得到信号的故障特征值。通过支持向量机（Support Vector Machine,SVM）在选择不同的核函数和结构参数下比较其对转子故障诊断结果的影响。结果表明在选择最优SVM模型和参数的基础上,对SVD获得的故障特征值进行诊断,得出了准确的诊断结果。     

IMPROVED SINGULAR VALUE DECOMPOSITION TECHNIQUE FOR DETECTING AND EXTRACTING PERIODIC IMPULSE COMPONENT IN A VIBRATION SIGNAL

Vibration acceleration signals are often measured from case surface of a running machine to monitor its condition. If the measured vibration signals display to have periodic impulse components with a certain frequency, there may exist a corresponding local fault in the machine, and if further extracting the periodic impulse components from the vibration signals, the severity of the local fault can be estimated and tracked. However, the signal-to-noise ratios (SNRs) of the vibration acceleration signals are often so small that the periodic impulse components are submersed in much background noises and other components, and it is difficult or inconvenient for us to detect and extract the periodic impulse components with the current common analyzing methods for vibration signals. Therefore, another technique, called singular value decomposition (SVD), is tried to be introduced to solve the problem. First, the principle of detecting and extracting the signal periodic components using singular value decompos     

改进蝙蝠算法优化支持向量机的故障诊断方法

提出了一种基于变分模态分解（VMD）和时移多尺度散布熵（TSMDE）的故障特征提取结合改进的蝙蝠算法（IBA）来优化支持向量机（SVM）的滚动轴承故障诊断方法。通过变分模态分解,避免了模式混叠问题,提取各模态分量的散布熵构造故障特征向量,作为故障诊断模型的输入;提出了一种新的自适应速度权重因子用于构建改进的蝙蝠算法以优化支持向量机（IBA-SVM）,实现了对不同故障类型的轴承进行分类;利用实验数据对提出的诊断方法进行验证,并与用粒子群算法（PSO）优化支持向量机（PSO-SVM）的诊断方法进行对比。结果表明所提出的方法分类准确率更高,用时更少。     

基于形态奇异值分解和经验模态分解的滚动轴承故障特征提取方法

针对随机噪声和局部强干扰影响经验模态分解(Empirical mode decomposition,EMD)质量的问题,提出一种形态奇异值分解滤波消噪方法,并将其与EMD相结合形成一种新的故障特征提取方法。该方法首先对原始振动信号进行相空间重构和奇异值分解(Singular value decomposition,SVD),根据奇异值分布曲线确定降噪阶次进行SVD降噪,再形态滤波,最后把消噪后的信号进行EMD分解,利用本征模模态分量(Intrinsic mode function,IMF)提取故障特征信息。对仿真信号和实际轴承故障数据的应用分析表明,该方法能有效地提取轴承故障特征,诊断轴承故障,还可以减少EMD的分解层数和边界效应,提高EMD分解的时效性和精确度。     

基于稀疏分解的振动信号数据压缩算法

针对齿轮传动装置在状态监测与故障诊断过程中面临的大量振动信号传输困难问题,提出利用K-SVD算法进行信号的稀疏分解,进而完成对大量振动数据的压缩。传统K-SVD算法在字典更新过程中对时间的消耗量较大,特别是在大量振动数据压缩过程中,对数据压缩效率较低,为此提出一种K-SVD字典更新的改进算法。改进算法从单次迭代过程中参与更新的字典原子列数出发,每次奇异值分解后对多列字典原子同时进行赋值,从而减少单次迭代计算量。根据不同原子列数在稀疏分解过程中的迭代收敛次数、时间消耗与重构峰值信噪比,以此确定最佳的字典更新列数。实验结果表明:传统K-SVD算法对振动信号的数据压缩效率较低,改进算法能够在保证信号压缩比与重构效果的前提下,有效缩短训练字典的时间消耗。     

A roller bearing fault diagnosis method based on the improved ITD and RRVPMCD

Targeting that the measured vibration signal of roller bearing contains the characteristics of non-stationary and nonlinear, and the extraction features may contain smaller correlation and redundancy characteristics in the roller bearing fault diagnosis, the vibration signal processing method based upon improved ITD (intrinsic time-scale decomposition) and feature selection method based on Wrapper mode are put forward. In addition, in the design of the classifier, targeting the limitation of existing pattern recognition method, a new pattern recognition method-variable predictive model based class discriminate (VPMCD) is introduced into roller bearing fault identification. However, the parameters are fitted by using least squares in VPMCD method, while least squares regression is sensitive to “abnormal value”. Therefore, a robust regression-variable predictive mode-based class discriminate (RRVPMCD) method is proposed in this paper, robust regression is adopted to estimate parameters and the effect of “abnormal value” in the estimation of parameters would be reduced by giving each feature a weight. Firstly, improved ITD method and feature selection method based on Wrapper mode are combined to extract the fault features of roller bearing vibration signals, and feature vector matrixes are established, then a predictive model is built through the method of RRVPMCD, finally, the established predictive model is used for pattern recognition. Experimental results show that the model based on the improved ITD, the Wrapper feature selection and RRVPMCD method can effectively identify work status and fault type of roller bearing.