信息融合在飞行器智能健康诊断中的应用

提出了一种基于经验模态分析(Empirical mode decomposition,EMD)和D-S证据相结合的飞行器健康诊断方法.该方法首先对由声发射传感器募集到的飞行器关键结构部件原始声发射信号进行EMD,得到多个内禀模态分量,选取内禀模态能量构建声发射信号的特征向量,并分别采用模糊神经网络、GRNN网络和Elman神经网络对提取出的特征向量进行分类,最后运用D-S证据理论进行决策融合,对飞行器的健康状态进行诊断.实验表明,运用此方法对某型号真实飞行器关键结构部件的健康状态进行诊断,可以得到很好放入诊断结果.与单分类器相比,采用D-S证据理论进行决策融合有效地提高了故障诊断的精度.     

Fractional Envelope Analysis for Rolling Element Bearing Weak Fault Feature Extraction

The bearing weak fault feature extraction is crucial to mechanical fault diagnosis and machine condition monitoring. Envelope analysis based on Hilbert transform has been widely used in bearing fault feature extraction. A generalization of the Hilbert transform, the fractional Hilbert transform is defined in the frequency domain, it is based upon the modification of spatial filter with a fractional parameter, and it can be used to construct a new kind of fractional analytic signal. By performing spectrum analysis on the fractional envelope signal, the fractional envelope spectrum can be obtained. When weak faults occur in a bearing, some of the characteristic frequencies will clearly appear in the fractional envelope spectrum. These characteristic frequencies can be used for bearing weak fault feature extraction. The effectiveness of the proposed method is verified through simulation signal and experiment data.      

Using multi-sensor data fusion for vibration fault diagnosis of rolling element bearings by accelerometer and load cell

This paper presents a new method for bearing fault diagnosis using the fusion of two primary sensors: an accelerometer and a load cell. A novel condition-based monitoring (CBM) system consisting of six modules: sensing, signal processing, feature extraction, classification, high-level fusion and decision making module has been proposed. To obtain acceleration and load signals, a work bench has been used. In the next stage, signal indices for each signal in both time and frequency domains have been calculated. After calculation of signal indices, principal component analysis is employed for redundancy reduction. Two principal features have been extracted from load and acceleration indices. In the fourth module, K-Nearest Neighbor (KNN) classifier has been used in order to identify the condition of the ball bearing based on vibration signal and load signal. In the fifth module, a high-level sensor fusion is used to derive information that would not be available from single sensor. Based on situation assessment carried out during the training process of classifier, a relationship between bearing condition and sensor performance has been found. Finally, a logical program has been used to decide about the condition of the ball bearing. The test results demonstrate that the load cell is powerful to detect the healthy ball bearings from the defected ones, and the accelerometer is useful to detect the location of fault. Experimental results show the effectiveness of this method.     

基于DCT和GA-SVM的轴承故障诊断

针对轴承故障振动信号特点,提出一种基于离散余弦变换(DCT)、遗传算法(GA)和支持向量机(SVM)的轴承故障诊断方法.利用DCT的能量聚集性在广义频域建立原始特征向量集,运用GA以SVM的最低分类错误率为目标函数建立故障特征向量集,使用SVM完成轴承故障诊断.分别对轴承内圈故障、外圈故障、滚动体故障进行故障诊断,结果表明,该方法能够准确诊断轴承故障.     

Fault diagnosis of roller bearing using fuzzy classifier and histogram features with focus on automatic rule learning

Roller bearing is one of the most widely used elements in rotary machines. Condition monitoring of such elements is conceived as pattern recognition problem. Pattern recognition has three main phases: feature extraction, feature selection and feature classification. Histogram features can be used for fault diagnosis of roller bearing. This paper presents the use of decision tree for selecting best few histogram features (bin ranges) that will discriminate the fault conditions of the bearing from given train samples. These features are extracted from vibration signals. A rule set is formed from the extracted features and fed to a fuzzy classifier. The rule set necessary for building the fuzzy classifier is obtained largely by intuition and domain knowledge. This paper also presents the usage of decision tree to generate the rules automatically from the feature set. The vibration signal from a piezoelectric transducer is captured for the following conditions – good bearing, bearing with inner race fault, bearing with outer race fault, and inner and outer race fault. The histogram features were extracted and good features that discriminate the different fault conditions of the bearing were selected using decision tree. The rule set for fuzzy classifier is obtained by once using the decision tree again. A fuzzy classifier is built and tested with representative data. The results are found to be encouraging.     

基于小波旁瓣相消器的轴承故障特征提取

为解决强背景噪声下声信号提取的轴承故障特征不显著问题,提出一种基于小波旁瓣相消器的故障特征提取方法。该方法利用小波滤波器组将含噪故障轴承声信号变换到小波域,进行小波域阵列广义旁瓣相消自适应波束形成,再通过小波滤波器组重构增强后的故障轴承信号,最后对重构增强后的信号进行包络解调并提取故障特征频率进行故障诊断。实验结果表明,该方法能够在强背景噪声下有效提取滚动轴承故障特征,并且相较于传统的延时求和波束形成器具有更好的降噪和故障特征增强效果。     

基于径向基神经网络的新型齿轮故障诊断方法

非平稳工况下的齿轮故障检测是一项非常困难的工作,由于齿轮振动信号的复杂性,导致故障特征提取和故障诊断困难.针对这些问题,基于径向基(radial basis function, RBF)神经网络,提出一种在变速条件下齿轮的故障诊断方法 CIHDRFD.首先利用自适应白噪声的完整集成经验模态分解(complete ensemble empirical mode decomposition with adaptive noise, CEEMDAN),将原始振动信号分解为多个固有的模态函数(intrinsic mode function, IMF),并通过计算其信息熵(information entropy, IE)筛选出IE最小的4个IMF作为特征IMF;然后利用希尔伯特变换(hilbert transform, HT)处理特征IMF并求出Hilbert包络谱,利用Hilbert包络谱构建故障特征向量;最后利用改进的双RBF神经网络进行故障检测.通过搭建齿轮故障检测平台验证CIHDRFD方法的有效性,实验结果表明, CIHDRFD方法适用于齿轮故障诊断,在速度波动为3%的情况下,诊断准确率...     

协同训练算法在滚动轴承故障诊断中的应用

针对单个分类器方法在滚动轴承故障诊断中精度较低、故障样本标记稀缺、特征空间维度高等问题，提出一种将协同训练与集成学习相结合的Co-Forest轴承故障诊断算法。Co-Forest是半监督学习中的协同训练算法，包含多个基分类器，通过投票实现协同训练中的置信度估算。从滚动轴承的振动信号中提取时域、频域特征指标。利用少量带标签和大量未标记样本重复地训练基分类器。集成基分类器，实现对滚动轴承故障的诊断。实验结果表明，与同类型的协同训练算法（Co-Training、Tri-Training）相比，Co-Forest算法在轴承故障诊断中具有更高的正确率，与当前针对特征向量高维、标记样本稀缺问题的ISS-LPP算法，SS-LLTSA算法相比，Co-Forest算法在保持很高诊断正确率的情况下，不需要降维、参数设置简单，具有一定的实际应用价值。     

基于Hilbert-Huang变换的语音信号分离

针对短时傅里叶变换不能正确得到非平稳信号的能量频率分布问题,提出了一种基于Hilbert-Huang变换的单信道语音信号分离的算法。该算法首先对分解得到的各内蕴模式函数分量(IMF)进行Hilbert变换,得到混合信号时频面上的Hilbert谱,然后对混合信号的Hilbert谱运用独立子空间分析的方法得出代表各个独立源信号的子空间,并对其求逆变换,从而恢复出各个源信号。通过仿真实验验证了此算法的正确性和有效性,且与短时傅里叶变换时频分析法相比较,其分离性能明显得到改善,显示了Hilbert-Huang变换在处理非平稳信号的优越性。     

基于HHT的机翼盒段的健康监控

提出了一种基于HILBERTHUANG变换技术的结构微损伤检测方法.基于HHT方法,提取了同损伤相联系的特征量-瞬时频率变化量和瞬时能量变化量.给出了结构损伤前后瞬时频率的变化情况,根据结构损伤前后瞬时频率的变化量,可以判断结构发生了一定程度的损伤.最后研究了结构损伤前后瞬时能量的变换情况,并讨论了瞬时能量变化最大值与结构损伤程度之间的关系.结果表明,结构原始响应信号经过HHT变换后得到的瞬时能量变化最大值与结构损伤程度有一定的规律可寻.     

基于频域特征变分自编码器的轴承故障诊断研究

针对深度学习故障诊断模型泛化能力差、网络复杂的问题,提出一种通用的特征提取网络,在此基础上应用轴承故障诊断的方法。首次提出频域特征变分自编码器,增强了信号特征提取的鲁棒性。然后,采用局部异常因子算法剔除离群点,防止分类器过拟合,提高分类器泛化性能。最后,构建分类器进行故障诊断。实验验证表明在不同损伤程度下特征提取的界限清晰,故障分类效果好,并且模型表现出良好的可迁移性。     

HHT方法在人体下肢表面肌电信号分析中的应用

针对表面肌电信号是非线性非稳态信号的特点,为了得到信号的有效特征并对信号特征进行有效分析,采用HHT(Hilbert-Huang Transformation)分析方法,通过经验模态分解将信号分解为一组内蕴模态函数。基于各内蕴模态函数的频率特征的分析,对它们进行HHT变换建立表面肌电信号的时间-频率-能量三维Hilbert谱,进而得到信号的边际谱。文中给出基于经验模态分解阈值消噪方法,和小波阈值方法相比,其消噪效果明显,在抑制噪声的同时,能够较好保留信号边缘和细节信息。初步实验表明HHT方法为表面肌电信号的特征提取和模式识别提供了可靠的依据,具有很好的应用前景。     

基于EMD和优化K-均值聚类算法诊断滚动轴承故障

考虑到滚动轴承振动信号的非平稳特征和实际应用中典型故障样本不易获得等原因,而在实际应用中,故障程度识别和故障类型诊断一样重要,提出一种滚动轴承故障类型及故障程度识别方法。首先对原始振动信号进行EMD分解,对含故障特征的IMF(intrinsic mode function)分量进行信号重构,随后对重构信号进行Hilbert包络谱分析,在提取特征量的基础上,应用优化K-均值聚类算法进行故障类型和故障程度分类。实验结果表明:基于EMD和优化K-均值聚类的故障类型和故障程度识别算法,可将含不同故障类型的样本集,按故障类型进行正确分类;也可将含同种故障类型、不同故障程度的样本集,按故障程度进行正确分类。     

基于改进小波去噪和EMD方法的轴承故障诊断

将改进的小波阈值去噪与EMD分解相结合应用于轴承故障诊断中。该方法首先利用改进的小波阈值去噪法对原始信号进行去噪,然后采用EMD方法将去噪后的信号自适应地分解成一系列IMF分量之和,通过能量-相关系数法选取能够反映故障特征的IMF分量进行包络谱分析提取故障频率。实验结果表明该方法能够有效识别故障特征频率。     

基于HHT变换的起动电动机特征信号时频分析

针对车辆起动电动机电气和机械故障发生时特征信号的时变不平稳特性,进行了时频域分析处理,提出了利用现代信号处理方法对故障信号提取特征向量的方法,主要对起动电动机的电枢和轴承故障进行诊断。在构建电机故障测试实验平台的基础上,利用破坏性实验构造了故障类型,测取了电枢电流和振动信号,分别采用小波分析理论和HHT变换对信号进行分析,通过分解再重构的方式将信号分解成了频率由高到低的不同分量,并获得了故障的特征频率,提取了特征向量。实验结果表明,基于HHT变换的现代信号处理方法在处理时变非平稳信号方面比小波分析理论更具有自适应性,更易识别。     

Passive acoustic monitoring of head disc interface interactions

A hard disc drive (HDD) recording head thermal protrusion is monitored by the passive acoustic characterization technique where adaptive discrete wavelet (ADW) filtering has been introduced to declare the contact. A phenomenological model is built to demonstrate detectability of the passive acoustic monitoring. The model is based on the mechanical impedance approach where impedances of head disc interface (HDI) and acoustic emission (AE) sensor are compared for matching over air bearing/head gimble assembly frequency bandwidth. A synthesized HDI response signal derived from the HDI mechanical impedance function is compared to the real AE signal obtained during the thermal protrusion based contact detection. A methodology of HDD level AE signal characterization presented in this work consists of the ADW filtering technique where the fifth order DB7 wavelet base function is used in AE signal decomposition. The signal decomposition order is selected by the AE signal entropy minimization.     

Intelligent fault diagnosis in microprocessor systems for vibration analysis in roller bearings in whirlpool turbine generators real time processor applications

Large steam turbines used for electrical power generation demand governing systems of very high integrity (safety) and availability. The latest generation of electronic governors uses microprocessors in a distributed, two level architecture to achieve the required integrity and availability and in addition provides greater configuration flexibilities and wider facilities than earlier governors. Rolling element bearings are one of the major machinery components used in industries like power plants, chemical plants and automotive industries that require precise and efficient performance. Vibration monitoring and analysis is useful tool in the field of predictive maintenance in small hydro electric power plants. Health of rolling element bearings can be easily identified using vibration monitoring because vibration signature reveals important information about the fault development within them. Numbers of vibration analysis techniques are being used to diagnosis of rolling element bearings faults. This paper proposes a new signal feature extraction and fault diagnosis method for fault diagnosis of low-speed machinery. Initially, the proposed work explores the Continuous Wavelet Transform (CWT) to adaptively remove the exact noises from vibration analysis and then feature extraction is performed by exploiting the noise removed pre-processed data. Statistic filter (SF) and Hilbert transform (HT) are combined with moving-peak-hold method (M-PH) to extract features of a fault signal, and Special bearing diagnostic symptom parameters (SSPs) in a frequency domain that are sensitive to bearing fault diagnosis are defined to recognize fault types. The SF is first used to adaptively cancel noises, and then fault detection is performed by exploiting the optimum symptom parameters in a time domain to identify a normal or fault state. For precise diagnosis, the SSPs are calculated after the signals are processed by M-PH and HT.     

基于Hilbert-Huang变换的特征能量法及其在滚动轴承故障诊断中的应用

Hilbert-Huang变换是一种新的自适应信号处理方法,非常适用于非线性和非平稳过程。该文在介绍Hilbert-Huang变换的基础上,针对滚动轴承故障振动信号的非平稳特征,提出了一种基于Hilbert-Huang变换的特征能量法。该方法在Hilbert-Huang变换的基础上定义滚动轴承振动信号在固有频率段的能量为特征能量,以此作为滚动轴承的故障特征向量,并通过建立M-距离判别函数来识别滚动轴承的故障类型。对滚动轴承外圈和内圈故障信号的分析结果表明,基于Hilbert-Huang变换的特征能量法可以有效地提取滚动轴承振动信号的故障特征。     

强噪声环境下基于改进HHT的语音端点检测

为提高语音端点检测系统在低信噪比环境下检测的正确率,提出一种强噪声环境下基于改进的希尔伯特-黄变换语音端点检测方法。对每帧信号进行经验模态分解,得到有限个固有模态函数,去掉第一个固有模态函数,其他的都让其通过一个带宽为250～3500Hz的带通滤波器,消除部分噪声。对所选固有模态函数加权,再进行希尔伯特变换得到能量特征值。通过分析噪声特性,估计噪声阈值。在希尔伯特能量谱上,根据阈值搜索语音起点以及终点。仿真实验表明,在低信噪比的情况下,方法的准确率有明显的提高,并具有很强的鲁棒性。     

Induction motors bearing fault detection using pattern recognition techniques

This paper proposes a systematic procedure based on a pattern recognition technique for fault diagnosis of induction motors bearings through the artificial neural networks (ANNs). In this method, the use of time domain features as a proper alternative to frequency features is proposed to improve diagnosis ability. The features are obtained from direct processing of the signal segments using very simple calculation. Three different cases including, healthy, inner race defect and outer race defect are investigated using the proposed algorithm. The ANNs are trained with a subset of the experimental data for known machine conditions. Once the network is trained, efficiency of the proposed method is evaluated using the remaining set of data. The obtained results indicate that using time domain features can be effective in accurate diagnosis of various motor bearing faults with high precision and low computational burden.