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.     

A New Method Based on Time-Varying Filtering Intrinsic Time-Scale Decomposition and General Refined Composite Multiscale Sample Entropy for Rolling-Bearing Feature Extraction

The early fault diagnosis of rolling bearings has always been a difficult problem due to the interference of strong noise. This paper proposes a new method of early fault diagnosis for rolling bearings with entropy participation. First, a new signal decomposition method is proposed in this paper: intrinsic time-scale decomposition based on time-varying filtering. It is introduced into the framework of complete ensemble intrinsic time-scale decomposition with adaptive noise (CEITDAN). Compared with traditional intrinsic time-scale decomposition, intrinsic time-scale decomposition based on time-varying filtering can improve frequency-separation performance. It has strong robustness in the presence of noise interference. However, decomposition parameters (the bandwidth threshold and B-spline order) have significant impacts on the decomposition results of this method, and they need to be artificially set. Aiming to address this problem, this paper proposes rolling-bearing fault diagnosis optimization based on an improved coyote optimization algorithm (COA). First, the minimal generalized refined composite multiscale sample entropy parameter was used as the objective function. Through the improved COA algorithm, optimal intrinsic time-scale decomposition parameters based on time-varying filtering that match the input signal are obtained. By analyzing generalized refined composite multiscale sample entropy (GRCMSE), whether the mode component is dominated by the fault signal is determined. The signal is reconstructed and decomposed again. Finally, the mode component with the highest energy in the central frequency band is selected for envelope spectrum variation for fault diagnosis. Lastly, simulated and experimental signals were used to verify the effectiveness of the proposed method.     

Fusion Domain-Adaptation CNN Driven by Images and Vibration Signals for Fault Diagnosis of Gearbox Cross-Working Conditions

The vibration signal of gearboxes contains abundant fault information, which can be used for condition monitoring. However, vibration signal is ineffective for some non-structural failures. In order to resolve this dilemma, infrared thermal images are introduced to combine with vibration signals via fusion domain-adaptation convolutional neural network (FDACNN), which can diagnose both structural and non-structural failures under various working conditions. First, the measured raw signals are converted into frequency and squared envelope spectrum to characterize the health states of the gearbox. Second, the sequences of the frequency and squared envelope spectrum are arranged into two-dimensional format, which are combined with infrared thermal images to form fusion data. Finally, the adversarial network is introduced to realize the state recognition of structural and non-structural faults in the unlabeled target domain. An experiment of gearbox test rigs was used for effectiveness validation by measuring both vibration and infrared thermal images. The results suggest that the proposed FDACNN method performs best in cross-domain fault diagnosis of gearboxes via multi-source heterogeneous data compared with the other four methods.     

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。     

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。     

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.     

城轨车辆电气柜故障诊断方法研究

城轨车辆电气柜种类繁多,结构复杂,若依靠人工检测的方式进行故障的排除,不仅诊断效率低且可靠性差。通过对多个城轨车辆电气柜的具体分析,提出一种动态提取有向图结构模型并生成测试序列的算法,利用图的最优路径算法进行测试自检,最后使用一种适应性测试诊断树来完成故障的定位与隔离。实验表明,该诊断方法能够有效地对城轨车辆电气柜的故障进行诊断,且对于不同拓扑结构的城轨车辆电气柜具有良好的适应性。     

Matching pursuit of an adaptive impulse dictionary for bearing fault diagnosis

The sparse decomposition based on matching pursuit is an adaptive sparse expression of the signals. An adaptive matching pursuit algorithm that uses an impulse dictionary is introduced in this article for rolling bearing vibration signal processing and fault diagnosis. First, a new dictionary model is established according to the characteristics and mechanism of rolling bearing faults. The new model incorporates the rotational speed of the bearing, the dimensions of the bearing and the bearing fault status, among other parameters. The model can simulate the impulse experienced by the bearing at different bearing fault levels. A simulation experiment suggests that a new impulse dictionary used in a matching pursuit algorithm combined with a genetic algorithm has a more accurate effect on bearing fault diagnosis than using a traditional impulse dictionary. However, those two methods have some weak points, namely, poor stability, rapidity and controllability. Each key parameter in the dictionary model and its influence on the analysis results are systematically studied, and the impulse location is determined as the primary model parameter. The adaptive impulse dictionary is established by changing characteristic parameters progressively. The dictionary built by this method has a lower redundancy and a higher relevance between each dictionary atom and the analyzed vibration signal. The matching pursuit algorithm of an adaptive impulse dictionary is adopted to analyze the simulated signals. The results indicate that the characteristic fault components could be accurately extracted from the noisy simulation fault signals by this algorithm, and the result exhibited a higher efficiency in addition to an improved stability, rapidity and controllability when compared with a matching pursuit approach that was based on a genetic algorithm. We experimentally analyze the early-stage fault signals and composite fault signals of the bearing. The results further demonstrate the effectiveness and superiority of the matching pursuit algorithm that uses the adaptive impulse dictionary. Finally, this algorithm is applied to the analysis of engineering data, and good results are achieved.     

Rolling Bearing Fault Monitoring for Sparse Time-Frequency Representation and Feature Detection Strategy

Data-driven fault diagnosis methods for rotating machinery have developed rapidly with the help of deep learning methods. However, traditional intelligent fault diagnosis methods still have some limitations in fault feature extraction and the latest object detection theory has not been applied in fault diagnosis. To this end, a fault diagnosis method based on a sparse short-term Fourier transform (SSTFT) and object detection theory is developed in this paper. First, a sparse constraint is introduced in time-frequency analysis to improve the time-frequency resolution of the model without cross-term interference and proximal gradient descent (PGD) is adopted to quickly and effectively optimize the model to obtain a high-quality time-frequency representation (TFR). Second, a fault diagnosis model based on a region-based convolutional neural network (RCNN) is built; the model can extract multiple regions that can characterize fault features from the TFR. This process avoids the interference of irrelevant vibration components and improves the interpretability of the fault diagnosis model. Finally, multicategory rolling bearing fault identification is realized. The effectiveness of the proposed method is validated by simulation signals and bearing experiments. The results indicate that the proposed method is more effective than existing methods.     

Gear Fault Diagnosis Method Based on Multi-Sensor Information Fusion and VGG

The gearbox is an important component in the mechanical transmission system and plays a key role in aerospace, wind power and other fields. Gear failure is one of the main causes of gearbox failure, and therefore it is very important to accurately diagnose the type of gear failure under different operating conditions. Aiming at the problem that it is difficult to effectively identify the fault types of gears using traditional methods under complex and changeable working conditions, a fault diagnosis method based on multi-sensor information fusion and Visual Geometry Group (VGG) is proposed. First, the power spectral density is calculated with the raw frequency domain signal collected by multiple sensors before being transformed into a power spectral density energy map after information fusion. Second, the obtained energy map is combined with VGG to obtain the fault diagnosis model of the gear. Finally, two datasets are used to verify the effectiveness and generalization ability of the method. The experimental results show that the accuracy of the method can reach 100% at most on both datasets.     

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。     

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.     

Feature separation using ICA for a one-dimensional time series and its application in fault detection

Principal component analysis (PCA) is a method that transforms multiple data series into uncorrelated data series. Independent component analysis (ICA) is a method that separates multiple data series into independent data series. Both methods have been used in fault detection. However, both require signals from at least two separate sensors. To overcome this requirement and utilize the fault detection capability of ICA and PCA, we propose to use wavelet transform to pre-process the data collected from a single sensor and then use the coefficients of the wavelet transforms at different scales as input to ICA and PCA. The effectiveness of this method is demonstrated by applying it to both a simulated signal series and a vibration signal series collected from a gearbox. The results show that the method of combining wavelet transform and ICA works better than the method of combining wavelet transform and PCA for impulse detection based on a one-dimensional vibration data series.     

A Novel Feature Extraction Method for Power Transformer Vibration Signal Based on CEEMDAN and Multi-Scale Dispersion Entropy

Effective diagnosis of vibration fault is of practical significance to ensure the safe and stable operation of power transformers. Aiming at the traditional problems of transformer vibration fault diagnosis, a novel feature extraction method based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and multi-scale dispersion entropy (MDE) was proposed. In this paper, CEEMDAN method is used to decompose the original transformer vibration signal. Additionally, then MDE is used to capture multi-scale fault features in the decomposed intrinsic mode functions (IMFs). Next, the principal component analysis (PCA) method is employed to reduce the feature dimension and extract the effective information in vibration signals. Finally, the simplified features are sent into density peak clustering (DPC) to get the fault diagnosis results. The experimental data analysis shows that CEEMDAN-MDE can effectively extract the information of the original vibration signals and DPC can accurately diagnose the types of transformer faults. By comparing different algorithms, the practicability and superiority of this proposed method are verified.     

Gearbox Failure Diagnosis Using a Multisensor Data-Fusion Machine-Learning-Based Approach

Failure detection and diagnosis are of crucial importance for the reliable and safe operation of industrial equipment and systems, while gearbox failures are one of the main factors leading to long-term downtime. Condition-based maintenance addresses this issue using several expert systems for early failure diagnosis to avoid unplanned shutdowns. In this context, this paper provides a comparative study of two machine-learning-based approaches for gearbox failure diagnosis. The first uses linear predictive coefficients for signal processing and long short-term memory for learning, while the second is based on mel-frequency cepstral coefficients for signal processing, a convolutional neural network for feature extraction, and long short-term memory for classification. This comparative study proposes an improved predictive method using the early fusion technique of multisource sensing data. Using an experimental dataset, the proposals were tested, and their effectiveness was evaluated considering predictions based on statistical metrics.     

Identification of multiple transient faults based on the adaptive spectral kurtosis method

This paper proposes a multi-fault detection method based on the adaptive spectral kurtosis (ASK) analysis of the vibration signal from single sensor. A theoretical model of multiple bearing faults is established in this paper. Compared with the kurtogram and protrugram techniques, the proposed method can more effectively extract signatures of multiple bearing faults even in the presence of strong background noise. The performance of the proposed method in fault detection of the rolling element bearings is validated using simulation data and experimental signals from a bearing with multiple faults and two faulty bearings.     

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。     

基于Polytec激光测振仪和第二代小波的齿轮箱故障诊断

齿轮箱是机械设备中一种必不可少的通用零部件,也是故障多发部件,而齿轮失效又是诱发其故障的重要因素。因此发展新型齿轮箱故障诊断技术具有重要意义。搭建了基于Polytec激光测振仪的光学测量系统,拾取齿轮箱振动信号,采用第二代小波提取故障特征,达到了故障诊断的目的,可用于齿轮箱故障预知和智能维修。     

Experimental Investigation and Fault Diagnosis for Buckled Wet Clutch Based on Multi-Speed Hilbert Spectrum Entropy

The multi-disc wet clutch is widely used in transmission systems as it transfers the torque and power between the gearbox and the driving engine. During service, the buckling of the friction components in the wet clutch is inevitable, which can shorten the lifetime of the wet clutch and decrease the vehicle performance. Therefore, fault diagnosis and online monitoring are required to identify the buckling state of the friction components. However, unlike in other rotating machinery, the time-domain features of the vibration signal lack efficiency in fault diagnosis for the wet clutch. This paper aims to present a new fault diagnosis method based on multi-speed Hilbert spectrum entropy to classify the buckling state of the wet clutch. Firstly, the wet clutch is classified depending on the buckling degree of the disks, and then a bench test is conducted to obtain vibration signals of each class at varying speeds. By comparing the accuracy of different classifiers with and without entropy, Hilbert spectrum entropy shows higher efficiency than time-domain features for the wet clutch diagnosis. Thus, the classification results based on multi-speed entropy achieve even better accuracy.     

Vibration signal models for fault diagnosis of planetary gearboxes

A thorough understanding of the spectral structure of planetary gear system vibration signals is helpful to fault diagnosis of planetary gearboxes. Considering both the amplitude modulation and the frequency modulation effects due to gear damage and periodically time variant working condition, as well as the effect of vibration transfer path, signal models of gear damage for fault diagnosis of planetary gearboxes are given and the spectral characteristics are summarized in closed form. Meanwhile, explicit equations for calculating the characteristic frequency of local and distributed gear fault are deduced. The theoretical derivations are validated using both experimental and industrial signals. According to the theoretical basis derived, manually created local gear damage of different levels and naturally developed gear damage in a planetary gearbox can be detected and located.