Fast nonlinear blind deconvolution for rotating machinery fault diagnosis

Zhang, Zongzhen; Wang, Jinrui; Li, Shunming; Han, Baokun; Jiang, Xingxing

doi:10.1016/j.ymssp.2022.109918

Cited by 63 publications

(25 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The parameter combination [K, α] in VMD is first optimized using WOA, which exhibits the tendency to become more stable with increasing iterations. The optimal set of parameters for [K, α] in accordance with WOA optimization is [6,3190]. The optimal solution number K and the penalty factor α are add to the VMD method and the INVL algorithm to break down the signal after optimizing VMD by using WOA.…”

Section: Comparison Analysismentioning

confidence: 99%

See 1 more Smart Citation

Improvement of VMD for anomalous collision disturbance based on nonlinear l _1/2 norm

Han

Yao

Zhang

et al. 2023

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Variational mode decomposition (VMD) is widely used in the fault diagnosis of rotating equipment. The kurtosis index is typically utilized as the objective function to determine the optimal decomposition mode in conventional VMD. However, kurtosis is easily interfered with by abnormal impact signals, seriously affecting the accuracy of VMD in the fault extraction process. Therefore, the instability of the kurtosis index for anomalous disturbances should be addressed. In addition, the number of modal decompositions K and the penalty factor α are not wisely selected, exerting a significant influence on the decomposition effect of VMD. In this study, an improved VMD method based on nonlinear VMD with l1/2 norm (INVL) is proposed for the fault diagnosis of rotating machineries under abnormal impact interference. First, the whale optimization algorithm is used to optimize the combination of parameters [Κ,α] to obtain the best decomposition results. Second, the decomposed modes are preprocessed with the nonlinear tanh function to weaken the impact of amplitude shocks. Third, the sparse l1/2 norm is used to select the fault feature components for assessing the sparse distribution of modes. The modes with the smallest l1/2-norm values are selected for information reconstruction and envelope analysis. Simulation and experimental verification are employed to demonstrate the performance of the method. Results show that abnormal shocks are suppressed by the proposed INVL method and bearing fault features under anomalous collision disturbances are effectively extracted.

show abstract

Section: Comparison Analysismentioning

confidence: 99%

“…To a large extent, the operating condition of a machine depends on the condition of the bearings. Consequently, the analysis and identification of early faults in rolling bearings have been popular topics of studies in recent decades [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Improvement of VMD for anomalous collision disturbance based on nonlinear l _1/2 norm

Han

Yao

Zhang

et al. 2023

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning algorithm-based fault diagnosis has attracted more and more attention [1]. Different from traditional fault diagnosis approaches [2], deep learning algorithms can usually fit more complex and non-linear mapping functions due to the stack of layers [3]. There exist some basic neural networks, such as restricted Boltzmann machine [4], convolutional neural network (CNN) [5], recurrent neural networks (RNNs) [6] and generative adversarial networks (GANs) [7].…”

Section: Introductionmentioning

confidence: 99%

A two-stage multi-scale domain adversarial transfer learning method and its application in fault diagnosis

Zhang,

Huang,

Wang

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Domain adaptation (DA) based intelligent fault diagnosis (IFD) methods have attracted great attention in recent years. The key motivation of DA methods is to extract the domain-invariant features. In most cases, the one-dimensional convolutional neural networks (CNN) are adopted as the feature extractor, in which the kernels are usually single and fixed. However, the monitoring data for IFD usually involves various scale information, the feature representation extracted by above models may be incomprehensive. Moreover, the target domain data is only used for narrowing distribution discrepancy in an unsupervised way, which may lead to the ignorance of class information of target domain. To address these issues, in this paper, a two-stage multi-scale domain adversarial fault diagnosis method is proposed. A multi-scale feature extractor with different kernel sizes is designed to acquire more discriminative domain-invariant features. Meanwhile, the pseudo label learning is adopted for providing transfer learning process with the pseudo labels of target domain, which are generated by a pre-train network in the first stage and then are optimised through iterations in the second stage. The maximum mean discrepancy (MMD) is also adopted to enhance the ability of model for marginal distribution alignment, which can make the model more robust. Thirty-eight transfer tasks from two different datasets were conducted to evaluate the effectiveness of the proposed method. The experimental results demonstrated that the proposed method achieved higher average diagnosis accuracy compared with several popular methods. The superiority of our proposed method was further explained by visualization of learned features.

show abstract

“…The last four transforms are time–frequency spectrograms, and this type of data is notably used as input data during classification. Recently, there has been work to enhance the impulsive signature in signals from rotating machinery, such as the kurtogram [ 19 ] and fast nonlinear blind decomposition [ 20 ].…”

Section: Introductionmentioning

confidence: 99%

Multi–Output Classification Based on Convolutional Neural Network Model for Untrained Compound Fault Diagnosis of Rotor Systems with Non–Contact Sensors

Son

Hong

Kim

2023

Sensors

View full text Add to dashboard Cite

Fault diagnosis is important in rotor systems because severe damage can occur during the operation of systems under harsh conditions. The advancements in machine learning and deep learning have led to enhanced performance of classification. Two important elements of fault diagnosis using machine learning are data preprocessing and model structure. Multi–class classification is used to classify faults into different single types, whereas multi–label classification classifies faults into compound types. It is valuable to focus on the capability of detecting compound faults because multiple faults can exist simultaneously. Diagnosis of untrained compound faults is also a merit. In this study, input data were first preprocessed with short–time Fourier transform. Then, a model was built for classification of the state of the system based on multi–output classification. Finally, the proposed model was evaluated based on its performance and robustness for classification of compound faults. This study proposes an effective model based on multi–output classification, which can be trained using only single fault data for the classification of compound faults and confirms the robustness of the model to changes in unbalance.

show abstract

Fast nonlinear blind deconvolution for rotating machinery fault diagnosis

Cited by 63 publications

References 33 publications

Improvement of VMD for anomalous collision disturbance based on nonlinear l _1/2 norm

Improvement of VMD for anomalous collision disturbance based on nonlinear l _1/2 norm

A two-stage multi-scale domain adversarial transfer learning method and its application in fault diagnosis

Multi–Output Classification Based on Convolutional Neural Network Model for Untrained Compound Fault Diagnosis of Rotor Systems with Non–Contact Sensors

Contact Info

Product

Resources

About

Fast nonlinear blind deconvolution for rotating machinery fault diagnosis

Cited by 63 publications

References 33 publications

Improvement of VMD for anomalous collision disturbance based on nonlinear l 1/2 norm

Improvement of VMD for anomalous collision disturbance based on nonlinear l 1/2 norm

A two-stage multi-scale domain adversarial transfer learning method and its application in fault diagnosis

Multi–Output Classification Based on Convolutional Neural Network Model for Untrained Compound Fault Diagnosis of Rotor Systems with Non–Contact Sensors

Contact Info

Product

Resources

About

Improvement of VMD for anomalous collision disturbance based on nonlinear l _1/2 norm

Improvement of VMD for anomalous collision disturbance based on nonlinear l _1/2 norm