深度置信网络在齿轮故障诊断中的应用

针对齿轮传动系统中齿轮等零部件易出现故障或失效等问题,提出了一种基于深度学习理论的齿轮传动系统故障诊断方法。首先利用深度置信网络强大的特征自提取能力,对齿轮传动系统的振动信号进行特征提取,然后通过DBNs的复杂映射表征能力对故障信号进行故障判别。诊断实例表明,若不对齿轮振动的原始时域信号进行特征提取,直接利用DBNs对其进行诊断时,故障识别正确率只能达到60%左右;如果对时域信号进行简单的傅里叶变换后,再利用DBNs对处理后的振动信号频谱进行诊断分析,正确率能达到99.7%,从而证明了所提故障诊断方法的简易性和有效性。     

基于流形学习算法的齿轮变速箱故障特征提取

流形学习算法是一种非线性的数据降维方法,可以获得数据的低维几何结构,能很好的体现系统的本质。为了提高齿轮变速箱振动故障信号的可分性,应用流形学习方法对齿轮变速箱振动信号进行故障特征提取。研究结果表明,流形学习方法可以有效地提取齿轮变速箱振动故障的特征信息,并能有效区分不同故障类型的特征信息。运用流形学习方法进行故障特征提取后的诊断结果与时域统计特征提取方法相比,提高了故障诊断的正确率。     

基于深度学习特征提取和粒子群支持向量机状态识别的齿轮智能故障诊断

针对齿轮故障诊断问题,利用数理统计特征提取方法、深度学习神经网络、粒子群算法和支持向量机等技术,提出了一种基于深度学习特征提取和粒子群支持向量机状态识别相结合的智能诊断模型。该模型利用深度学习自适应提取的频谱特征与数理统计方法提取的时域特征相结合组成联合特征向量,然后利用粒子群支持向量机对联合特征向量进行故障诊断。该模型在对多级齿轮传动系统试验台的故障诊断中实现了中速轴大齿轮不同故障类型的可靠识别,获得了满意的诊断结果。应用结果也验证了基于深度学习自适应提取频谱特征的有效性。     

基于多维度模糊熵的齿轮故障诊断方法

针对齿轮的故障诊断问题,引入模糊熵的方法对齿轮振动信号进行分析。通过研究嵌入维数和延迟时间对信号模糊熵的影响,提出多维度模糊熵的齿轮故障特征提取方法。利用多维度模糊熵特征提取方法提取故障特征,并结合支持向量机建立了齿轮故障诊断模型。对实测齿轮故障数据进行分析,证明了多维度模糊熵方法可以有效提取齿轮不同状态的特征信息,与支持向量机结合可以精确地诊断齿轮典型故障,具有一定的优势。     

基于谱熵的齿轮故障诊断方法研究

齿轮故障诊断中,采用何种有效的方法对随机动态信号进行分析和特征提取是关键所在。在实际工程当中所采集到的系统信号不可避免地受到噪声的污染,所以普通的一些处理方法如功率谱分析法等,对噪声的存在很敏感,检测分析结果往往不很理想,且很难准确区分故障。谱熵方法从统计学理论入手,反映了信号的无序性,对噪声具有一定的鲁棒性。本文将谱熵理论引入到机械齿轮传动系统中,对齿轮发生的裂纹、磨损故障进行了特征提取、区分与诊断,并与正常齿轮进行了对比,分析模拟和实验结果表明,效果良好,识别诊断的精度在90%以上,为机械齿轮传动系统的故障识别与诊断提供了一种有效方法。     

基于Morlet小波的时频图在齿轮断齿故障诊断中的应用

齿轮传动系统振动信号带有明显的非平稳性,齿轮断齿故障使非平稳特征更加明显,并伴有明显的脉冲冲击特性。利用小波分析处理非平稳的优势,结合齿轮传动系统的振动特性和Morlet小波能够处理脉冲信号的特点,建立了基于Morlet小波的时频分析方法,通过对某齿轮增速箱齿轮断齿故障的诊断,证明本方法不但能够准确诊断出断齿故障,而且能够评估断齿数量,较好地弥补了传统频谱分析的不足。研究结果对于齿轮断齿等具有脉冲信号特征的故障诊断具有一定的指导意义。     

基于集成卷积神经网络的行星齿轮智能诊断方法

针对行星齿轮箱故障振动特征需要预处理、识别困难以及诊断模型收敛速度较慢的问题,提出基于集成卷积神经网络的行星齿轮箱智能故障诊断方法。首先,采用一维卷积对齿轮的原始时域振动信号提取特征,之后通过采用两个弱分类器,根据弱分类学习错误率的性能更新样本权重,调整权重后根据训练集训练弱分类器。重复此过程,最后通过设置策略整合弱分类器,形成集成卷积神经网络;建立一个稳定用于行星齿轮箱的智能故障诊断的模型。实验结果表明：集成卷积神经网络能很好地对行星齿轮原始振动信号进行快速诊断。相对于传统卷积神经网络对齿轮原始时域振动故障信号的诊断具有更强的辨识能力和更快的收敛速度;所建立的智能诊断模型可以有效地诊断齿轮不同的故障状态。     

基于.NET平台行星齿轮传动故障诊断系统

鉴于三级行星齿轮传动系统故障诊断方法的不足,开发了基于. NET平台的行星齿轮传动故障诊断系统,实现了多路信号实时采集与综合分析功能。首先采集行星齿轮传动系统的振动信号,然后运用基于. NET平台设计开发的行星齿轮传动故障诊断系统对数据进行时频域分析,并利用小波阈值降噪、包络谱分析、频谱细化、窄带解调等方法进行特征提取并对特征信息进行状态识别,最后对行星齿轮传动系统故障信号特征频率进行验证对比。试验结果验证了该行星齿轮传动故障诊断的可行性和有效性。     

基于三相交流异步电机定子电流信号分析的机电传动系统齿轮箱裂纹故障非侵入式诊断

齿轮裂纹故障是机电传动系统的高发故障,及时发现裂纹故障对保证机电传动系统正常工作意义重大。提出了一种基于三相交流异步电机定子电流信号的齿轮裂纹故障非侵入式诊断方法。首先,建立电机-齿轮-负载机电耦合模型,利用势能法计算不同裂纹深度和角度下齿轮变啮合刚度;然后,利用Runge-Kutta法对机电耦合模型进行数值求解,分析时变啮合刚度影响下电机电流动态响应。通过对比健康齿轮和裂纹故障齿轮的定子电流频谱,揭示齿轮裂纹故障对应的电流频谱特征,建立基于电机电流信号分析的传动系统齿轮裂纹故障诊断判据。对存在裂纹故障的齿轮进行电机拖动实验,齿轮裂纹故障影响下的电机电流信号与数值求解结果一致。所提出的基于电机电流信号的齿轮裂纹故障非侵入式诊断方法对于降低传动系统维护成本具有较高价值。     

基于小波包能量谱齿轮振动信号的分析与故障诊断

小波包是继小波分析之后提出的一种新型的多尺度分析方法,解决了小波分析在高频部分分辨率差的缺点,体现了比小波分析更好的处理效果.测试了齿轮传动系统在几种不同故障类型下的振动信号,利用小波包变换的分解和重构算法,有效地提取出齿轮故障特征信号,得到试验结果.通过比较时域分析、频域分析和小波包分析对齿轮振动信号进行的特征提取,...     

局部特征尺度分解结合局部均值解调的齿轮故障诊断

为了准确地进行故障诊断,根据齿轮故障振动信号的多分量调幅-调频特征,提出了一种新的解调方法--局部均值解调法,将之与局部特征尺度分解相结合进行齿轮故障诊断。该诊断方法首先对齿轮振动信号运用局部特征尺度分解,得到若干个内禀尺度分量,然后应用局部均值解调法求取每个分量的调频分量,最后根据瞬时频率的频谱进行故障诊断。采用仿真信号将局部均值解调法与Hilbert解调法、经验调幅调频分解法进行了对比,结果表明,局部均值解调法的精确性更好。通过齿轮故障振动数据的分析,验证了局部特征尺度分解结合局部均值解调的故障诊断方法的有效性。     

基于小波变换-模糊聚类的变速箱齿轮故障诊断

在对车辆变速箱齿轮振动加速度信号进行小波变换的基础上，提出了基于尺度-能量谱的特征提取和模糊聚类相结合的车辆变速箱齿轮故障诊断方法。该方法应用于LC5T81变速箱齿轮的故障诊断中，能够比较准确地识别与诊断出变速箱齿轮的走合运行状态、磨损运行状态和故障运行状态，具有一定的实用价值。     

Virtual prototype and experimental research on gear multi-fault diagnosis using wavelet-autoregressive model and principal component analysis method

Gear systems are an essential element widely used in a variety of industrial applications. Since approximately 80% of the breakdowns in transmission machinery are caused by gear failure, the efficiency of early fault detection and accurate fault diagnosis are therefore critical to normal machinery operations. Reviewed literature indicates that only limited research has considered the gear multi-fault diagnosis, especially for single, coupled distributed and localized faults. Through virtual prototype simulation analysis and experimental study, a novel method for gear multi-fault diagnosis has been presented in this paper. This new method was developed based on the integration of Wavelet transform (WT) technique, Autoregressive (AR) model and Principal Component Analysis (PCA) for fault detection. The WT method was used in the study as the de-noising technique for processing raw vibration signals. Compared with the noise removing method based on the time synchronous average (TSA), the WT technique can be performed directly on the raw vibration signals without the need to calculate any ensemble average of the tested gear vibration signals. More importantly, the WT can deal with coupled faults of a gear pair in one operation while the TSA must be carried out several times for multiple fault detection. The analysis results of the virtual prototype simulation prove that the proposed method is a more time efficient and effective way to detect coupled fault than TSA, and the fault classification rate is superior to the TSA based approaches. In the experimental tests, the proposed method was compared with the Mahalanobis distance approach. However, the latter turns out to be inefficient for the gear multi-fault diagnosis. Its defect detection rate is below 60%, which is much less than that of the proposed method. Furthermore, the ability of the AR model to cope with localized as well as distributed gear faults is verified by both the virtual prototype simulation and experimental studies.     

基于分形理论的机械故障诊断的应用研究

将分形的有关理论与机械故障诊断联系起来,论述了分形维数的基本概念,介绍了网格维数及其求取方法。通过对模拟信号、齿轮振动信号进行分形诊断表明,分形网格维数诊断可以模糊诊断出到底是哪一部分最有可能发生故障,证实了分形网格维数的普遍性和通用性。分形网格维数诊断方法能有效地诊断齿轮局部故障,具有广泛的应用前景。     

A new fault diagnosis algorithm for helical gears rotating at low speed using an optical encoder

Helical gears are widely used in gearboxes due to its low noise and high load carrying capacity, but it is difficult to diagnose their early faults based on the signals produced by condition monitoring systems, particularly when the gears rotate at low speed. In this paper, a new concept of Root Mean Square (RMS) value calculation using angle domain signals within small angular ranges is proposed. With this concept, a new diagnosis algorithm based on the time pulses of an encoder is developed to overcome the difficulty of fault diagnosis for helical gears at low rotational speeds. In this proposed algorithm, both acceleration signals and encoder impulse signal are acquired at the same time. The sampling rate and data length in angular domain are determined based on the rotational speed and size of the gear. The vibration signals in angular domain are obtained by re-sampling the vibration signal of the gear in the time domain according to the encoder pulse signal. The fault features of the helical gear at low rotational speed are then obtained with reference to the RMS values in small angular ranges and the order tracking spectrum following the Angular Domain Synchronous Average processing (ADSA). The new algorithm is not only able to reduce the noise and improves the signal to noise ratio by the ADSA method, but also extracts the features of helical gear fault from the meshing position of the faulty gear teeth, hence overcoming the difficulty of fault diagnosis of helical gears rotating at low speed. The experimental results have shown that the new algorithm is more effective than traditional diagnosis methods. The paper concludes that the proposed helical gear fault diagnosis method based on time pulses of encoder algorithm provides a new means of helical gear fault detection and diagnosis.     

Blind vibration component separation and nonlinear feature extraction applied to the nonstationary vibration signals for the gearbox multi-fault diagnosis

Fault diagnosis of gearboxes, especially the gears and bearings, is of great importance to the long-term safe operation. An unexpected damage on the gearbox may break the whole transmission line down. It is therefore crucial for engineers and researchers to monitor the health condition of the gearbox in a timely manner to eliminate the impending faults. However, useful fault detection information is often submerged in heavy background noise. Thereby, a new fault detection method for gearboxes using the blind source separation (BSS) and nonlinear feature extraction techniques is presented in this paper. The nonstationary vibration signals were analyzed to reveal the operation state of the gearbox. The kernel independent component analysis (KICA) algorithm was used hereby as the BSS approach for the mixed observation signals of the gearbox vibration to discover the characteristic vibration source associated with the gearbox faults. Then the wavelet packet transform (WPT) and empirical mode decomposition (EMD) nonlinear analysis methods were employed to deal with the nonstationary vibrations to extract the original fault feature vector. Moreover, the locally linear embedding (LLE) algorithm was performed as the nonlinear feature reduction technique to attain distinct features from the feature vector. Lastly, the fuzzy k-nearest neighbor (FKNN) was applied to the fault pattern identification of the gearbox. Two case studies were carried out to evaluate the effectiveness of the proposed diagnostic approach. One is for the gear fault diagnosis, and the other is to diagnose the rolling bearing faults of the gearbox. The nonstationary vibration data was acquired from the gear and rolling bearing fault test-beds, respectively. The experimental test results show that sensitive fault features can be extracted after the KICA processing, and the proposed diagnostic system is effective for the multi-fault diagnosis of the gears and rolling bearings. In addition, the proposed method can achieve higher performance than that without KICA processing with respect to the classification rate.     

基于最大重加权峭度盲解卷积的风电故障诊断

受噪声以及复杂传递路径等影响,风电机组齿轮故障特征信号通常比较微弱。为有效诊断齿轮故障,提出一种新的盲解卷积方法——最大重加权峭度盲解卷积方法。重加权峭度对故障信号中单个或少量强冲击干扰具有很好的鲁棒性,且无需待恢复故障冲击序列先验知识。最大重加权峭度盲解卷积方法能有效地解决经典的基于峭度最大化方法倾向于恢复单个主导冲击而非齿轮故障冲击序列的问题,同时相较于常见非全“盲”(依赖故障特征频率先验)方法在工业装备齿轮故障诊断方面具有更强的适用性。仿真信号分析结果表明所提方法在恢复故障冲击序列方面效果显著,在风电机组故障诊断中的应用案例证实了所提方法对齿轮故障诊断的有效性。     

多通道多分量分解方法在变转速工况齿轮故障特征提取中的应用

齿轮故障振动信号在非稳态工况下,其分量可能存在跨时间尺度或不同分量重叠的复杂时频特征,传统的以局部时间尺度特征为依据的分解方法无法分解,为此,引入一种新的多通道多分量分解(MMD)方法。MMD方法创新性地将单分量信号看成具有不同权重系数的特征向量线性组合,通过迭代优化出权重系数,便可获得相应的分量信号。解决了MMD分析高采样率的实际振动信号时大数据量会导致其分解效率降低的问题,并将MMD方法应用于变转速工况下齿轮故障振动信号的分析,结果表明,该方法可以有效分解出在时频域发生重叠的故障分量信号,较传统的以时间尺度特征为依据的分解方法具有明显优势,结合阶次分析可以清晰准确地提取出齿轮故障特征信息。     

基于MCKD和改进HHT多尺度模糊熵的齿轮故障诊断方法

针对齿轮故障信号常伴有大量噪声,故障特征难以提取的问题,提出一种基于最大相关峭度解卷积(MCKD)和改进希尔伯特-黄变换(HHT)多尺度模糊熵的故障诊断方法。首先采用MCKD算法对采集到的齿轮振动信号进行降噪处理,以提高信号的信噪比;然后利用自适应白噪声完备经验模态分解(CEEMDAN)对降噪后信号进行分解,获得一系列不同尺度的固有模态函数(IMF),并通过相关系数-能量的虚假IMF评价方法选取对故障敏感的模态分量;最后计算敏感IMF分量的模糊熵,将获得的原信号多尺度的模糊熵作为状态特征参数输入最小二乘支持向量机(LS-SVM)中,对齿轮的故障类型进行诊断。实测信号的诊断结果表明,该方法可实现齿轮故障的有效诊断。     

增压鼓风机增速箱振动故障的频谱分析

根据离线采集的振动信号,应用状态监测与故障诊断的频谱分析技术,诊断增压鼓风机增速箱振动增大的原因,并通过检查验证了诊断结论.