基于优化集合EMD的滚动轴承故障位置及性能退化程度诊断方法

为了更有效地同时诊断出滚动轴承故障位置及不同性能退化程度,提出了对滚动轴承不同状态振动信号进行特征提取和智能分类的故障诊断方法.该方法对各状态振动信号进行集合经验模态分解,但其效果依赖于总体平均次数和加入噪声的大小这2个重要参数,因此,提出集合经验模态分解中加入白噪声的准则.将分解后的一系列固有模态函数结合奇异值分解获取各状态的奇异值,并组成特征向量矩阵.将其输入到改进的超球结构多类支持向量机进行分类,从而实现滚动轴承正常、不同故障位置及性能退化程度的多状态同时智能诊断.实验结果表明,提出的集合经验模态分解方法中加入白噪声准则,可避免人为确定分解参数,提高其分解效率.基于优化参数的集合经验模态分解结合奇异值分解的智能诊断方法比已有的基于经验模态分解结合自回归模型的诊断方法识别率高.     

核函数主元分析及其在齿轮故障诊断中的应用

提出了基于核函数主元分析的齿轮故障诊断方法。该方法通过计算齿轮振动信号原始特征空间的内积核函数来实现原始特征空间到高维特征空间的非线性映射。通过对高维特征数据作主元分析,得到原始特征的非线性主元,以所选的非线性主元作为特征子空间对齿轮工作状态进行分类识别。用齿轮在正常状态、裂纹状态和断齿状态下的试验数据对该方法进行了检验,比较了主元分析与核函数主元分析的分类效果。结果表明,核函数主元分析能有效的检测裂纹故障的出现,正确区分不同的故障模式,更适于提取故障信号的非线性特征。     

CLASSIFICATION OF GEAR FAULTS USING HIGHER-ORDER STATISTICS AND SUPPORT VECTOR MACHINES

Gears alternately mesh and detach in driving process, and then working conditions of gears are alternately changing, so they are easy to be spalled and worn. But because of the effect of additive gaussian measurement noises, the signal-to-noises ratio is low; their fault features are difficult to extract. This study aims to propose an approach of gear faults classification, using the cumulants and support vector machines. The cumulants can eliminate the additive gaussian noises, boost the signal-to-noises ratio. Generalisation of support vector machines as classifier, which is employed structural risk minimisation principle, is superior to that of conventional neural networks, which is employed traditional empirical risk minimisation principle. Support vector machines as the classifier, and the third and fourth order cumulants as input, gears faults are successfully recognized. The experimental results show that the method of fault classification combining cumulants with support vector machines is very e     

基于迭代的集总经验模式分解算法的齿轮箱故障特征提取

针对集总经验模式分解方法(Ensemble Empirical Mode Decomposition,EEMD)在实际应用中存在的盲目添加白噪声的问题,提出了一种迭代的集总经验模式分解方法(Iterative Ensemble Empirical Mode Decomposition,IEEMD).首先介绍了IEEMD...     

Support vector machine with genetic algorithm for machinery fault diagnosis of high voltage circuit breaker

Based on empirical mode decomposition (EMD) method and support vector machine (SVM), a new method for the fault diagnosis of high voltage circuit breaker (CB) is proposed. The feature extraction method based on improved EMD energy entropy is detailedly analyzed and SVM is employed as a classifier. Radial basis function (RBF) is adopted as the kernel function of SVM and its kernel parameter γ and penalty parameter C must be carefully predetermined in establishing an efficient SVM model. Therefore, the purpose of this study is to develop a genetic algorithm-based SVM (GA-SVM) model that can determine the optimal parameters of SVM with the highest accuracy and generalization ability. The classification accuracy of this GA-SVM approach is tried by real dataset and compared with the SVM, which has randomly selected kernel function parameters. The experimental results indicate that the classification accuracy of this GA-SVM approach is more superior than that of the artificial neural network and the SVM which has constant and manually extracted parameters.     

灰狼算法优化支持向量机在风力机齿轮箱故障诊断中的应用

针对风力机齿轮箱振动信号非线性和非平稳性的特征,提出基于模糊熵(Fuzzy Entropy,FE)和灰狼算法优化(Grey Wolf Optimizer,GWO)的支持向量机(GWO Support Vector Machine,GWO-SVM)的故障诊断方法。通过集合经验模态分解算法(Ensemble Empirical Mode Decomposition,EEMD)对振动信号进行分解得到若干本征模态函数(Intrinsic Mode Function,IMF)分量;求取各状态IMF分量的模糊熵并构建特征向量;将各特征向量输入GWO-SVM模型进行故障识别及分类。结果表明:齿轮箱振动信号不同状态下的模糊熵有一定区分度,通过GWO-SVM能对其进行精确识别和分类,且GWO-SVM相对于粒子群优化(Particle Swarm Optimization,PSO) SVM模型和遗传算法(Genetic Algorithm,GA)优化SVM模型具有更短的运行时间和更高准确率,平均准确率高达92.5%。     

小波分析在深孔加工刀具故障诊断中的应用

在小波分析的理论基础上 ,讨论小波包在故障信息提取中的应用。小波包频段能量故障特征提取方法 ,克服了传统的信号处理方法不易提取微弱故障信息的不足。并举例说明该法的实用性     

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.     

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。     

半监督拉普拉斯分值在滚动轴承故障诊断中的应用

针对滚动轴承故障诊断过程中标签样本不足的问题,结合特征选择与二次挖掘,提出了基于半监督拉普拉斯分值(Semi Supervised Laplace Score, SSLS)和核主元分析(Kernel Principal Component Analysis, KPCA)的滚动轴承故障诊断模型。SSLS将半监督思想应用于拉普拉斯分值特征选择方法中,利用少量的有标签样本和大量无标签样本,结合KPCA对故障特征进行二次挖掘。同时,将粒子群优化的支持向量机(Particle Swarm Optimization-based Support Vector Machine, PSO-SVM)算法用于故障分类。最后,将该模型应用于实验数据分析过程。结果表明,该模型在减少样本标记工作量的同时,仍能在滚动轴承故障分类中保持较高的准确率,验证了所建立模型的有效性和工程实用性。