Intelligent Fault Diagnosis Method of Rolling Bearings Based on Transfer Residual Swin Transformer with Shifted Windows

Due to their robust learning and expression ability for complex features,the deep learning(DL)model plays a vital role in bearing fault diagnosis.However,since there are fewer labeled samples in fault diagnosis,the depth of DL models in fault diagnosis is generally shallower than that of DL models in other fields,which limits the diagnostic performance.To solve this problem,a novel transfer residual Swin Transformer(RST)is proposed for rolling bearings in this paper.RST has 24 residual self-attention layers,which use the hierarchical design and the shifted window-based residual self-attention.Combined with transfer learning techniques,the transfer RST model uses pre-trained parameters from ImageNet.A new end-to-end method for fault diagnosis based on deep transfer RST is proposed.Firstly,wavelet transform transforms the vibration signal into a wavelet time-frequency diagram.The signal’s time-frequency domain representation can be represented simultaneously.Secondly,the wavelet time-frequency diagram is the input of the RST model to obtain the fault type.Finally,our method is verified on public and self-built datasets.Experimental results show the superior performance of our method by comparing it with a shallow neural network.

Deep Residual Joint Transfer Strategy for Cross-Condition Fault Diagnosis of Rolling Bearings

Rolling bearings are key components of the drivetrain in wind turbines,and their health is critical to wind turbine operation.In practical diagnosis tasks,the vibration signal is usually interspersed with many disturbing components,and the variation of operating conditions leads to unbalanced data distribution among different conditions.Although intelligent diagnosis methods based on deep learning have been intensively studied,it is still challenging to diagnose rolling bearing faults with small amounts of samples.To address the above issue,we introduce the deep residual joint transfer strategy method for the cross-condition fault diagnosis of rolling bearings.One-dimensional vibration signals are pre-processed by overlapping feature extraction techniques to fully extract fault characteristics.The deep residual network is trained in training tasks with sufficient samples,for fault pattern classification.Subsequently,three transfer strategies are used to explore the generalizability and adaptability of the pre-trained models to the data distribution in target tasks.Among them,the feature transferability between different tasks is explored by model transfer,and it is validated that minimizing data differences of tasks through a dual-stream adaptation structure helps to enhance generalization of the models to the target tasks.In the experiments of rolling bearing faults with unbalanced data conditions,localized faults of motor bearings and planet bearings are successfully identified,and good fault classification results are achieved,which provide guidance for the cross-condition fault diagnosis of rolling bearings with small amounts of training data.

Rolling Bearing Fault Diagnosis Based On Convolutional Capsule Network

Fault diagnosis technology has been widely applied and is an important part of ensuring the safe operation of mechanical equipment.In response to the problem of frequent faults in rolling bearings,this paper designs a rolling bearing fault diagnosis method based on convolutional capsule network(CCN).More specifically,the original vibration signal is converted into a two-dimensional time–frequency image using continuous wavelet transform(CWT),and the feature extraction is performed on the two-dimensional time–frequency image using the convolution layer at the front end of the network,and the extracted features are input into the capsule network.The capsule network converts the extracted features into vector neurons,and the dynamic routing algorithm is used to achieve feature transfer and output the results of fault diagnosis.Two different datasets are used to compare with other traditional deep learning models to verify the fault diagnosis capability of the method.The results show that the CCN has good diagnostic capability under different working conditions,even in the presence of noise and insufficient samples,compared to other models.This method contributes to the safe and reliable operation of mechanical equipment and is suitable for other rotating scenarios.

Application of Improved Deep Auto-Encoder Network in Rolling Bearing Fault Diagnosis

Since the effectiveness of extracting fault features is not high under traditional bearing fault diagnosis method, a bearing fault diagnosis method based on Deep Auto-encoder Network (DAEN) optimized by Cloud Adaptive Particle Swarm Optimization (CAPSO) was proposed. On the basis of analyzing CAPSO and DAEN, the CAPSO-DAEN fault diagnosis model is built. The model uses the randomness and stability of CAPSO algorithm to optimize the connection weight of DAEN, to reduce the constraints on the weights and extract fault features adaptively. Finally, efficient and accurate fault diagnosis can be implemented with the Softmax classifier. The results of test show that the proposed method has higher diagnostic accuracy and more stable diagnosis results than those based on the DAEN, Support Vector Machine (SVM) and the Back Propagation algorithm (BP) under appropriate parameters.

Fault Early Diagnosis of Rolling Element Bearings Combining Wavelet Filtering and Degree of Cyclostationarity Analysis

The vibration signals of rolling element bearing are produced by a combination of periodic and random processes due to the machine’s rotation cycle and interaction with the real world. The combination of such components can give rise to signals, which have periodically time-varying ensemble statistical and are best considered as cyclostationary. When the early fault occurs, the background noise is very heavy, it is difficult to disclose the latent periodic components successfully using cyclostationary analysis alone. In this paper the degree of cyclostationarity is combined with wavelet filtering for detection of rolling element bearing early faults. Using the proposed entropy minimization rule. The parameters of the wavelet filter are optimized. This method is shown to be effective in detecting rolling element bearing early fault when cyclostationary analysis by itself fails.

Application of Xgboost Feature Extraction in Fault Diagnosis of Rolling Bearing

Due to the difficulty that excessive feature dimension in fault diagnosis of rolling bearing will lead to the decrease of classification accuracy,a fault diagnosis method based on Xgboost algorithm feature extraction is proposed.When the Xgboost algorithm classifies features,it generates an order of importance of the input features.The time domain features were extracted from the vibration signal of the rolling bearing,the time-frequency features were formed by the singular value of the modal components that were decomposed by the variational mode decomposition.Firstly,the extracted time domain and time-frequency domain features were input into the support vector machine respectively to observe the fault diagnosis accuracy.Then,Xgboost algorithm was used to rank the importance of features and got the accuracy of fault diagnosis.Finally,important features were extracted and the extracted features were input into the support vector machine to observe the fault diagnosis accuracy.The result shows that the fault diagnosis accuracy of rolling bearing is improved after important feature extraction in time domain and time-frequency domain by Xgboost.

RMA-CNN:A Residual Mixed Domain Attention CNN for Bearings Fault Diagnosis and Its Time-Frequency Domain Interpretability

Early fault diagnosis of bearings is crucial for ensuring safe and reliable operations.Convolutional neural networks(CNNs)have achieved significant breakthroughs in machinery fault diagnosis.However,complex and varying working conditions can lead to inter-class similarity and intra-class variability in datasets,making it more challenging for CNNs to learn discriminative features.Furthermore,CNNs are often considered“black boxes”and lack sufficient interpretability in the fault diagnosis field.To address these issues,this paper introduces a residual mixed domain attention CNN method,referred to as RMA-CNN.This method comprises multiple residual mixed domain attention modules(RMAMs),each employing one attention mechanism to emphasize meaningful features in both time and channel domains.This significantly enhances the network’s ability to learn fault-related features.Moreover,we conduct an in-depth analysis of the inherent feature learning mechanism of the attention module RMAM to improve the interpretability of CNNs in fault diagnosis applications.Experiments conducted on two datasets—a high-speed aeronautical bearing dataset and a motor bearing dataset—demonstrate that the RMA-CNN achieves remarkable results in diagnostic tasks.

Fault Analysis of Wind Power Rolling Bearing Based on EMD Feature Extraction

In a wind turbine,the rolling bearing is the critical component.However,it has a high failure rate.Therefore,the failure analysis and fault diagnosis of wind power rolling bearings are very important to ensure the high reliability and safety of wind power equipment.In this study,the failure form and the corresponding reason for the failure are discussed firstly.Then,the natural frequency and the characteristic frequency are analyzed.The Empirical Mode Decomposition(EMD)algorithm is used to extract the characteristics of the vibration signal of the rolling bearing.Moreover,the eigenmode function is obtained and then filtered by the kurtosis criterion.Consequently,the relationship between the actual fault frequency spectrum and the theoretical fault frequency can be obtained.Then the fault analysis is performed.To enhance the accuracy of fault diagnosis,based on the previous feature extraction and the time-frequency domain feature extraction of the data after EMD decomposition processing,four different classifiers are added to diagnose and classify the fault status of rolling bearings and compare them with four different classifiers.

Fault Feature Extraction of Rolling Bearing Based on an Improved Cyclical Spectrum Density Method

The traditional cyclical spectrum density（CSD） method is widely used to analyze the fault signals of rolling bearing. All modulation frequencies are demodulated in the cyclic frequency spectrum. Consequently, recognizing bearing fault type is difficult. Therefore, a new CSD method based on kurtosis（CSDK） is proposed. The kurtosis value of each cyclic frequency is used to measure the modulation capability of cyclic frequency. When the kurtosis value is large, the modulation capability is strong. Thus, the kurtosis value is regarded as the weight coefficient to accumulate all cyclic frequencies to extract fault features. Compared with the traditional method, CSDK can reduce the interference of harmonic frequency in fault frequency, which makes fault characteristics distinct from background noise. To validate the effectiveness of the method, experiments are performed on the simulation signal, the fault signal of the bearing outer race in the test bed, and the signal gathered from the bearing of the blast furnace belt cylinder. Experimental results show that the CSDK is better than the resonance demodulation method and the CSD in extracting fault features and recognizing degradation trends. The proposed method provides a new solution to fault diagnosis in bearings.

Long-Range Dependencies Learning Based on Nonlocal 1D-Convolutional Neural Network for Rolling Bearing Fault Diagnosis

In the field of data-driven bearing fault diagnosis,convolutional neural network(CNN)has been widely researched and applied due to its superior feature extraction and classification ability.However,the convolutional operation could only process a local neighborhood at a time and thus lack the ability of capturing long-range dependencies.Therefore,building an efficient learning method for long-range dependencies is crucial to comprehend and express signal features considering that the vibration signals obtained in a real industrial environment always have strong instability,periodicity,and temporal correlation.This paper introduces nonlocal mean to the CNN and presents a 1D nonlocal block(1D-NLB)to extract long-range dependencies.The 1D-NLB computes the response at a position as a weighted average value of the features at all positions.Based on it,we propose a nonlocal 1D convolutional neural network(NL-1DCNN)aiming at rolling bearing fault diagnosis.Furthermore,the 1D-NLB could be simply plugged into most existing deep learning architecture to improve their fault diagnosis ability.Under multiple noise conditions,the 1D-NLB improves the performance of the CNN on the wheelset bearing data set of high-speed train and the Case Western Reserve University bearing data set.The experiment results show that the NL-1DCNN exhibits superior results compared with six state-of-the-art fault diagnosis methods.

PARAMETERS OPTIMIZATION OF CONTINUOUS WAVELET TRANSFORM AND ITS APPLICATION IN ACOUSTIC EMISSION SIGNAL ANALYSIS OF ROLLING BEARING

Morlet wavelet is suitable to extract the impulse components of mechanical fault signals. And thus its continuous wavelet transform （CWT） has been successfully used in the field of fault diagnosis. The principle of scale selection in CWT is discussed. Based on genetic algorithm, an optimization strategy for the waveform parameters of the mother wavelet is proposed with wavelet entropy as the optimization target. Based on the optimized waveform parameters, the wavelet scalogram is used to analyze the simulated acoustic emission （AE） signal and real AE signal of rolling bearing. The results indicate that the proposed method is useful and efficient to improve the quality of CWT.

Improved Multi-Bandwidth Mode Manifold for Enhanced Bearing Fault Diagnosis

Variational mode decomposition(VMD) has been proved to be useful for extraction of fault-induced transients of rolling bearings. Multi-bandwidth mode manifold(Triple M, TM) is one variation of the VMD, which units multiple fault-related modes with different bandwidths by a nonlinear manifold learning algorithm named local tangent space alignment(LTSA). The merit of the TM method is that the bearing fault-induced transients extracted contain low level of in-band noise without optimization of the VMD parameters. However, the determination of the neighborhood size of the LTSA is time-consuming, and the extracted fault-induced transients may have the problem of asymmetry in the up-and-down direction. This paper aims to improve the efficiency and waveform symmetry of the TM method.Specifically, the multi-bandwidth modes consisting of the fault-related modes with different bandwidths are first obtained by repeating the recycling VMD(RVMD) method with different bandwidth balance parameters. Then, the LTSA algorithm is performed on the multi-bandwidth modes to extract their inherent manifold structure, in which the natural nearest neighbor(Triple N, TN) algorithm is adopted to efficiently and reasonably select the neighbors of each data point in the multi-bandwidth modes. Finally, a weight-based feature compensation strategy is designed to synthesize the low-dimensional manifold features to alleviate the asymmetry problem, resulting in a symmetric TM feature that can represent the real fault transient components. The major contribution of the improved TM method for bearing fault diagnosis is that the pure fault-induced transients are extracted efficiently and are symmetrical as the real. One simulation analysis and two experimental applications in bearing fault diagnosis validate the enhanced performance of the improved TM method over the traditional methods. This research proposes a bearing fault diagnosis method which has the advantages of high efficiency, good waveform symmetry and enhanced in-band noise removal capability.

Diagnosis of multiple faults using a double parallel two-hidden-layer extreme learning machine

Multiple faults are easily confused with single faults.In order to identify multiple faults more accurately,a highly efficient learning method is proposed based on a double parallel two-hidden-layer extreme learning machine,called DPTELM.The DPT-ELM method is a variant of an extreme learning machine(ELM).There are some issues with ELM.First,achieving a high accuracy requires too many hidden nodes;second,the direct connection between the input layer and the output layer is ignored.Accordingly,to deal with the above-mentioned problems,DPT-ELM extends the single-hidden-layer ELM to a two-hidden-layer ELM,which can achieve a desired performance with fewer hidden nodes.In addition,a direct connection is built between the input layer and the output layer.Since the input layer weights and the thresholds of the two hidden layers are determined randomly,this simplifies the improved model and shortens the calculation time.Additionally,to improve the signal to noise ratio(SNR),an adaptive waveform decomposition(AWD)algorithm is used to denoise the vibration signal.Then,the denoised signal is used to extract the eigenvalues by the time-domain and frequency-domain methods.Finally,the eigenvalues are input to the DPT-ELM classifier.In this paper,two groups of rolling bearing data at different speeds,which were collected from a real experimental platform,are used to test the method.Each set of data includes three single fault states,two complex fault states and a healthy state.The experimental results demonstrate that the DPT-ELM method achieves fast learning speed and a high accuracy.Moreover,based on 10-fold cross-validation,it proves to be an effective method to improve the accuracy with fewer hidden nodes.

联合收割机裂纹转子与滚动轴承故障诊断系统研究--基于卷积神经网络

首先,介绍了传统神经网络,在其基础上引出了改进的卷积神经网络;然后,搭建了转子和滚动轴承的动力学模型,对转子和轴承的裂纹模型进行分析研究;最后,实现了联合收割机裂纹转子与滚动轴承故障诊断系统。实验结果表明:基于卷积神经网络的诊断模型达到稳定识别精度的迭代次数更少,且识别精度更高,效果更好,证明了系统的可行性和可靠性。

基于EMDPWVD时频图像和改进ViT网络的滚动轴承智能故障诊断

滚动轴承是机械设备的关键零部件之一,其故障诊断对设备安全稳定运行至关重要。针对滚动轴承振动信号的非平稳特点,提出经验模态分解联合伪魏格纳分布(empirical mode decomposition&pseudo-Wigner-Ville distribution, EMDPWVD)时频图像联合改进Vision Transformer(ViT)网络模型的智能故障诊断新方法。首先针对实际信号研究短时傅里叶变换(short-time Fourier transform, STFT)、连续小波变换(continuous wavelet transform, CWT)和EMDPWVD三种时频分析方法,考虑STFT和CWT无法同时获得高的时间分辨率和频率分辨率,优选EMDPWVD作为智能故障诊断网络的时频图像构造方法。其次,以经典ViT作为故障诊断基础模型,将时频图像按照预定尺寸分块并线性映射为输入序列,通过自注意力机制整合图像全局信息,借助堆叠Transformer编码器完成网络传输,进而实现故障诊断。为进一步提高故障诊断准确率,将池化层作为ViT的预处理网络,获得改进的Pooling ViT(PiT)模型,实现时频图像的空间特征延展,提升模型对输入图像敏感度。结果表明,所提方法对滚动轴承不同故障类型均有高的诊断准确率,PiT较ViT的准确率提高4.40%,证明对ViT加入池化层能够实现滚动轴承故障诊断效果提升。

GhostConv轻量级网络设计及故障诊断研究

提出一种GhostConv轻量级网络模型并将其用于故障诊断。GhostConv利用常规卷积生成一小部分特征图,然后在生成的特征图上进行多次特征提取来生成其余特征图,最大程度地节约了常规卷积中生成冗余特征图的成本,减少了模型参数,保证了模型的性能。采用连续小波变换对振动信号进行时频变换生成二维时频图,之后利用设计的GhostConv搭建轻量级网络模型进行故障诊断。采用凯斯西储大学轴承数据集进行验证,并与其他卷积结构网络模型进行参数量、计算量以及识别准确率的对比。实验结果表明,与其他模型相比,所使用的网络模型在参数量和计算量较少的条件下依旧有较高的识别精度,且具有较好的鲁棒性和泛化能力,具有一定的工程应用价值。

基于AESL-GA的BN球磨机滚动轴承故障诊断方法

针对基于知识的贝叶斯网络(BN)构建方法存在不完全和不精确的缺点,提出一种基于知识引导和数据挖掘的BN结构构建方法。针对单一信号故障诊断结果不精确的问题和故障信息中存在的不确定性问题,将电流信号与振动信号融合建立BN的特征节点,分别提取2种信号的故障特征参数,利用区分度指标法进行特征筛选,将其作为BN结构特征层的节点。将专家知识构建的初始BN结构结合自适应精英结构遗传算法(AESL-GA)进行结构优化,通过自适应限制进化过程中的搜索空间,减少自由参数的数量,提高其全局搜索能力,得到最优BN结构。通过MQY5585溢流型球磨机滚动轴承实测数据和Paderborn University轴承数据集对所提方法进行验证,结果证明了所提方法的有效性。

基于混合域残差注意力网络的滚动轴承智能故障诊断方法

机械设备正朝着大型化、精密化和自动化的方向发展,机械系统也因此变得越来越复杂。考虑到机械系统可能会发生无特征的灾难性故障,因此机械故障的自动检测是一个巨大的挑战。然而,现有的故障检测方法在对高度复杂的工业系统进行故障类型识别时,误诊率较高,无法给出准确的故障诊断结果。针对这一问题,本文以滚动轴承这一机械设备关键部件作为研究对象,提出一种基于混合域残差注意力网络的故障诊断方法,旨在结合深度卷积神经网络自动学习表示的优点,并配合通道注意力机制和空间注意力机制的关键特征提取能力,提高故障检测性能。实验结果表明,所提出的方法能够准确地检测轴承故障类型,在准确度指标方面优于其他方法。

基于全矢CEEMDAN能量矩和AMHSSA-SVM的滚动轴承故障诊断

为充分利用滚动轴承的故障特征信息,提高故障诊断的准确性和可靠性,文中提出了一种基于全矢自适应噪声完全集成经验模态分解(Complementary Ensemble Empirical Mode Decomposition with Adaptive Noise,CEEMDAN)能量矩和自适应多种群混合麻雀搜索算法(Adaptive Multi-population Hybrid Sparrow Search Algorithm,AMHSSA)优化支持向量机(Support Vector Machine,SVM)的故障诊断方法。首先,采用全矢谱技术融合同源双通道信号;其次,采用CEEMDAN算法处理融合信号,选择相关系数较大的前5阶IMF分量,并计算其能量矩作为支持向量机模型的特征输入;最后,提出AMHSSA算法并优化支持向量机模型的参数,建立AMHSSA-SVM故障诊断模型。对该模型进行测试,结果表明:此模型有效提高了识别准确性,与类似模型对比,进一步证明了其在分类精度和优化时间方面的优越性。