基于决策树与多元支持向量机的齿轮箱早期故障诊断方法

针对齿轮箱部件故障形式多样的特点和典型故障训练样本数量有限的难点,提出了基于决策树与多元支持向量机的齿轮箱早期故障诊断方法。利用决策树分类速度快、效率高的优点和支持向量机在小样本二元分类方面突出的特点构建多元分类识别模型,在不同故障情形下提取齿轮箱振动信号典型特征参数作为故障特征向量训练模型,并对样本进行测试。实验结果表明,该方法在小样本情况下识别效果明显优于神经网络方法,同时在识别效率方面比常规多元支持向量机方法有了较大的提高。     

仿生鳍条姿态测量及其误差分析

在复杂环境下齿轮箱信号往往会淹没在噪声信号中,特征向量难以提取。为了有效的进行故障诊断,提出了基于最大相关反褶积(MCKD)总体平均经验模态分解(EEMD)近似熵和双子支持向量机(TWSVM)的齿轮箱故障诊断方法。首先采用MCKD方法对强噪声信号进行滤波处理,在采用EEMD方法对齿轮箱信号进行分解,分解后得到本征模函数(IMF)分量进行近似熵求解,得到齿轮特征向量,最后将其输入到TWSVM分类器中进行故障识别。仿真实验表明,采用MCKD-EEMD方法能够有效的提取原始信号,与其他分类器相比,TWSVM的计算时间短,分类效果好等优点。     

基于MCKD-EEMD近似熵和TWSVM的齿轮箱故障诊断

在复杂环境下齿轮箱信号往往会淹没在噪声信号中,特征向量难以提取;为了有效地进行故障诊断,提出了基于最大相关反褶积(MCKD)总体平均经验模态分解(EEMD)近似熵和双子支持向量机(TWSVM)的齿轮箱故障诊断方法;首先采用MCKD方法对强噪声信号进行滤波处理,在采用EEMD方法对齿轮箱信号进行分解,分解后得到本征模函数(IMF)分量进行近似熵求解,得到齿轮特征向量,最后将其输入到TWSVM分类器中进行故障识别;仿真实验表明,采用MCKD-EEMD方法能够有效地提取原始信号,与其他分类器相比,TWSVM的计算时间短,分类效果好等优点。     

基于激光自混合干涉技术和小波变换的齿轮箱故障诊断

激光自混和干涉(SMI)技术是一种利用光反馈原理进行的振动检测技术,它具有结构简单,非接触式测量振动信号的特点。为了解决齿轮箱故障诊断的问题,提出了用激光自混合干涉技术提取信号,并通过小波变换对信号分析进行处理的方法。通过分析小波变换的各个分量以及最终经过小波变换去噪后的信号,能够准确地识别出齿轮箱在运转时所存在的周期性振动故障信号,实验得到的结果与理论值结果完全吻合。     

基于激光自混合传感器的齿轮局部故障振动信号分析

建立了齿圈局部故障调频现象模型,分析了故障轮齿啮合频率及其倍频两侧边频带的产生机理,给出了齿圈局部故障特征频率的计算公式,建立了倒频谱分析模型。采用激光自混合传感器,分别从径向和轴向两个方向采集齿轮箱振动信号波形。在齿轮箱1Hz和2Hz两种不同输出转频下,分别研究了无故障齿轮箱和故障齿轮箱的振动信号特征。通过实验研究验证了理论推导结果。     

基于Parzen窗的油液原子光谱数据半监督FCM聚类研究

提出了一种基于Parzen窗的半监督模糊C-均值(Semi-supervised Fuzzy C-Means Based on Parzen window,PSFCM)聚类算法。根据训练样本确定出模糊C-均值(Fuzzy C-Means,FCM)的初始聚类中心;利用Parzen窗法计算出测试样本对各类状态的隶属度后,重新定义了隶属度迭代公式。通过齿轮箱磨损实验台模拟了齿轮箱的2种典型磨损故障并采集了油样。选取实验油样光谱分析数据中代表性元素Fe,Si,B的浓度值作为分析数据集的3维特征量,分别进行了FCM聚类和PSFCM聚类分析。聚类结果为:FCM聚类的正确率为48.9%,而融入了监督信息的PSFCM聚类的正确率为97.4%。实验说明,将PSFCM算法引入到油液原子光谱分析,降低了对人为经验和大量故障数据的依赖,提高了齿轮箱磨损故障诊断的准确度。     

非线性状态估计法在风电齿轮箱故障预警中的应用

针对现阶段在齿轮箱的状态监测方法中遇到的问题,提出一种以易于采集的油温信号来对齿轮箱故障进行预警的分析方法;通过非线性状态估计法(nonlinear state estimate technology)建立齿轮箱的温度预测模型,之后根据统计温度预测残差的变化趋势,然后与通过验证集合确定出的残差均值和标准差的故障阈值进行对比,以实现及早发现齿轮箱的潜在故障,优化运行的效果;并且与神经网络预测方法进行对比分析,结果表明非线性状态估计法对风电齿轮箱进行故障预警有着较好的效果。     

空间运输航天器故障诊断系统架构研究

故障诊断技术不仅是提高空间运输航天器的安全性和可靠性的重要手段,而且可以节约航天器整个寿命周期的运行维护成本,因此研究航天器故障诊断技术,特别是处理紧急故障的在轨故障检测和诊断技术是非常必要的。在分析国外航天器故障诊断系统发展趋势的基础上,提出了基于天地一体化设计思想的空间运输航天器故障诊断系统架构,阐明了设计原则,以及具体功能需求。介绍了在轨故障诊断系统和地面故障诊断系统,提出了地面故障诊断系统软件的组件模型构成。地面系统对航天器在轨故障诊断有较强的辅助作用,能有效补充故障分析、诊断、预测、处理能力。给出的系统架构对航天器故障诊断系统研制具有一定的参考价值。     

基于多信号流模型的电子设备故障诊断方法

为了提高产品的可靠性,并且在电子设备发生故障时迅速地确定故障源,保障设备的正常运行,基于多信号流模型的诊断建模方法,在多信号流基础上引入了以故障重要先验知识为主的多信号流故障诊断策略,通过引入故障模式的故障概率改进了多信号流诊断技术。该方法已应用于BEPCⅡ磁铁电源接口控制设备故障诊断系统,使用TEAMS测试工具箱建模实现了快速准确的故障诊断和定位,提高了磁铁电源控制设备的故障诊断检测率和隔离率,并且可以方便地扩展到其他设备和系统上。     

基于有色Petri网的机械系统故障诊断研究

故障诊断对于机械系统的使用与维护起着重要的作用;为了提高机械系统故障诊断的效率以及直观性,提出了一种使用基于知识的故障诊断方法,即使用有色Petri网诊断方法建立一种通用机械系统故障诊断模型并进行分析。针对数控机床液压元件故障这一案例,首先获取其故障来源建立故障树;其次在故障树基础上运用有色Petri网建模工具CPNTools建立有色Petri网模型;最后对模型进行了仿真分析以模拟故障的传递,进行状态空间分析以判断模型安全性,结果表明所提出的建模方法能够使得故障传递更加直观化,快速了解故障的发展趋势,并表明此模型有着较强的易用性以及通用性。     

Complex signal analysis for wind turbine planetary gearbox fault diagnosis via iterative atomic decomposition thresholding

The vibration signals from complex structures such as wind turbine (WT) planetary gearboxes are intricate. Reliable analysis of such signals is the key to success in fault detection and diagnosis for complex structures. The recently proposed iterative atomic decomposition thresholding (IADT) method has shown to be effective in extracting true constituent components of complicated signals and in suppressing background noise interferences. In this study, such properties of the IADT are exploited to analyze and extract the target signal components from complex signals with a focus on WT planetary gearboxes under constant running conditions. Fault diagnosis for WT planetary gearboxes has been a very important yet challenging issue due to their harsh working conditions and complex structures. Planetary gearbox fault diagnosis relies on detecting the presence of gear characteristic frequencies or monitoring their magnitude changes. However, a planetary gearbox vibration signal is a mixture of multiple complex components due to the unique structure, complex kinetics and background noise. As such, the IADT is applied to enhance the gear characteristic frequencies of interest, and thereby diagnose gear faults. Considering the spectral properties of planetary gearbox vibration signals, we propose to use Fourier dictionary in the IADT so as to match the harmonic waves in frequency domain and pinpoint the gear fault characteristic frequency. To reduce computing time and better target at more relevant signal components, we also suggest a criterion to estimate the number of sparse components to be used by the IADT. The performance of the proposed approach in planetary gearbox fault diagnosis has been evaluated through analyzing the numerically simulated, lab experimental and on-site collected signals. The results show that both localized and distributed gear faults, both the sun and planet gear faults, can be diagnosed successfully.     

Subway Gearbox Fault Diagnosis Algorithm Based on Adaptive Spline Impact Suppression

In the signal processing of real subway vehicles, impacts between wheelsets and rail joint gaps have significant negative effects on the spectrum. This introduces great difficulties for the fault diagnosis of gearboxes. To solve this problem, this paper proposes an adaptive time-domain signal segmentation method that envelopes the original signal using a cubic spline interpolation. The peak values of the rail joint gap impacts are extracted to realize the adaptive segmentation of gearbox fault signals when the vehicle was moving at a uniform speed. A long-time and unsteady signal affected by wheel–rail impacts is segmented into multiple short-term, steady-state signals, which can suppress the high amplitude of the shock response signal. Finally, on this basis, multiple short-term sample signals are analyzed by time- and frequency-domain analyses and compared with the nonfaulty results. The results showed that the method can efficiently suppress the high-amplitude components of subway gearbox vibration signals and effectively extract the characteristics of weak faults due to uniform wear of the gearbox in the time and frequency domains. This provides reference value for the gearbox fault diagnosis in engineering practice.     

Comparisons of MFDFA,EMD and WT by Neural Network,Mahalanobis Distance and SVM in Fault Diagnosis of Gearboxes

A method for gearbox fault diagnosis consists of feature extraction and fault identification. Many methods for feature extraction have been devised for exposing nature of vibration data of a defective gearbox. In addition, features extracted from gearbox vibration data are identified by various classifiers. However, existing literatures leave much to be desired in assessing performance of different combinatorial methods for gearbox fault diagnosis. To this end, this paper evaluated performance of several typical combinatorial methods for gearbox fault diagnosis by associating each of multifractal detrended fluctuation analysis (MFDFA), empirical mode decomposition (EMD) and wavelet transform (WT) with each of neural network (NN), Mahalanobis distance decision rules (MDDR) and support vector machine (SVM). Following this, performance of different combinatorial methods was compared using a group of gearbox vibration data containing slightly different fault patterns. The results indicate that MFDFA performs better in feature extraction of gearbox vibration data and SVM does the same in fault identification. Naturally, the method associating MFDFA with SVM shows huge potential for fault diagnosis of gearboxes. As a result, this paper can provide some useful information on construction of a method for gearbox fault diagnosis.     

基于BP神经网络的变速箱故障诊断方法研究

针对变速箱的工作时间不能真实反映实际健康状况的问题,通过提取变速箱的振动信号作为状态参数,建立了基于BP神经网络的变速箱故障诊断模型。该模型首先提取振动信号中对故障反映灵敏的成分作为特征值,获得BP神经网络的训练数据,并通过对比确定最优的隐含层节点数,确定BP神经网络的结构参数。模型训练结束后,以验证数据为例进行故障诊断研究,并对诊断结果进行评估。评估结果表明,该模型准确度高,具有较好的应用和推广价值。     

基于Parzen窗的Vague集理论用于油液原子光谱特征优选

油液原子光谱信息量大且具有模糊性,严重影响了在故障诊断中的应用效率和精度.为选择数量少、效率高的光谱特征,提出了一种光谱特征选择的新方法.基于齿轮箱实验台架,模拟了齿轮正常磨损状态和两种典型放障,并采集了油液样本.将三种磨损状态视为三个Vague集,光谱特征值视为Vague集上的Vague值.基于Vague值之间的相似...     

A wavelet approach to fault diagnosis of a gearbox under varying load conditions

Varying load can cause changes in a measured gearbox vibration signal. However, conventional techniques for fault diagnosis are based on the assumption that changes in vibration signal are only caused by deterioration of the gearbox. There is a need to develop a technique to provide accurate state indicator of gearbox under fluctuating load conditions. This paper presents an approach to gear fault diagnosis based on complex Morlet continuous wavelet transform under this condition. Gear motion residual signal, which represents the departure of time synchronously averaged signal from the average tooth-meshing vibration, is analyzed as source data due to its lower sensitiveness to the alternating load condition. A fault growth parameter based on the amplitude of wavelet transform is proposed to evaluate gear fault advancement quantitatively. We found that this parameter is insensitive to varying load and can correctly indicate early gear fault. For a comparison, the advantages and disadvantages of other measures such as kurtosis, mean, variance, form factor and crest factor, both of residual signal and mean amplitude of continuous wavelet transform waveform, are also discussed. The effectiveness of the proposed fault indicator is demonstrated using a full lifetime vibration data history obtained under sinusoidal varying load.     

A time domain approach to diagnose gearbox fault based on measured vibration signals

Spectral analysis techniques to process vibration measurements have been widely studied to characterize the state of gearboxes. However, in practice, the modulated sidebands resulting from the local gear fault are often difficult to extract accurately from an ambiguous/blurred measured vibration spectrum due to the limited frequency resolution and small fluctuations in the operating speed of the machine that often occurs in an industrial environment. To address this issue, a new time-domain diagnostic algorithm is developed and presented herein for monitoring of gear faults, which shows an improved fault extraction capability from such measured vibration signals. This new time-domain fault detection method combines the fast dynamic time warping (Fast DTW) as well as the correlated kurtosis (CK) techniques to characterize the local gear fault, and identify the corresponding faulty gear and its position. Fast DTW is employed to extract the periodic impulse excitations caused from the faulty gear tooth using an estimated reference signal that has the same frequency as the nominal gear mesh harmonic and is built using vibration characteristics of the gearbox operation under presumed healthy conditions. This technique is beneficial in practical analysis to highlight sideband patterns in situations where data is often contaminated by process/measurement noises and small fluctuations in operating speeds that occur even at otherwise presumed steady-state conditions. The extracted signal is then resampled for subsequent diagnostic analysis using CK technique. CK takes advantages of the periodicity of the geared faults; it is used to identify the position of the local gear fault in the gearbox. Based on simulated gear vibration signals, the Fast DTW and CK based approach is shown to be useful for condition monitoring in both fixed axis as well as epicyclic gearboxes. Finally the effectiveness of the proposed method in fault detection of gears is validated using experimental signals from a planetary gearbox test rig. For fault detection in planetary gear-sets, a window function is introduced to account for the planet motion with respect to the fixed sensor, which is experimentally determined and is later employed for the estimation of reference signal used in Fast DTW algorithm.     

ARX model-based gearbox fault detection and localization under varying load conditions

The development of the fault detection schemes for gearbox systems has received considerable attention in recent years. Both time series modeling and feature extraction based on wavelet methods have been considered, mostly under constant load. Constant load assumption implies that changes in vibration data are caused only by deterioration of the gearbox. However, most real gearbox systems operate under varying load and speed which affect the vibration signature of the system and in general make it difficult to recognize the occurrence of an impending fault.This paper presents a novel approach to detect and localize the gear failure occurrence for a gearbox operating under varying load conditions. First, residual signal is calculated using an autoregressive model with exogenous variables (ARX) fitted to the time-synchronously averaged (TSA) vibration data and filtered TSA envelopes when the gearbox operated under various load conditions in the healthy state. The gear of interest is divided into several sections so that each section includes the same number of adjacent teeth. Then, the fault detection and localization indicator is calculated by applying F-test to the residual signal of the ARX model. The proposed fault detection scheme indicates not only when the gear fault occurs, but also in which section of the gear. Finally, the performance of the fault detection scheme is checked using full lifetime vibration data obtained from the gearbox operating from a new condition to a breakdown under varying load.     

Low-Pass Filtering Empirical Wavelet Transform Machine Learning Based Fault Diagnosis for Combined Fault of Wind Turbines

Fault diagnosis of wind turbines is of great importance to reduce operating and maintenance costs of wind farms. At present, most wind turbine fault diagnosis methods are focused on single faults, and the methods for combined faults usually depend on inefficient manual analysis. Filling the gap, this paper proposes a low-pass filtering empirical wavelet transform (LPFEWT) machine learning based fault diagnosis method for combined fault of wind turbines, which can identify the fault type of wind turbines simply and efficiently without human experience and with low computation costs. In this method, low-pass filtering empirical wavelet transform is proposed to extract fault features from vibration signals, LPFEWT energies are selected to be the inputs of the fault diagnosis model, a grey wolf optimizer hyperparameter tuned support vector machine (SVM) is employed for fault diagnosis. The method is verified on a wind turbine test rig that can simulate shaft misalignment and broken gear tooth faulty conditions. Compared with other models, the proposed model has superiority for this classification problem.     

基于极限学习机与规则推理的NPC三电平逆变器二级故障诊断方法

针对NPC三电平逆变器故障诊断问题,提出一种基于极限学习机与规则推理的二级故障诊断方法。分析了依据输出电流诊断故障的可区分性,以及故障模式的分类。然后对输出电流提取故障特征,并采用极限学习机完成故障初级分类。对于初级分类结果为电流不可区分故障情况,再根据桥臂电压信息运用规则推理法实现故障二级精确诊断。诊断实验表明,该方法能够实现NPC三电平的多模式故障诊断,且故障诊断方法简单、定位精确、快速、鲁棒性强。