Feature frequency extraction algorithm based on the singular value decomposition with changed matrix size and its application in fault diagnosis

Zhao, Xuezhi; Bang-yan, YE

doi:10.1016/j.jsv.2022.116848

Cited by 18 publications

(8 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, ref. [67] outlines a method for diagnosing bearing faults, combining singular value decomposition (SVD) and square envelope spectrum (SES) to determine the type of fault with respect to the traction system of a high-speed vehicle; in [71], the SVD with a modified matrix size for vibration signal analysis is considered; the authors succeed in detecting misalignment faults. In [72], the authors propose a new feature extraction algorithm called Singular Value Decomposition Amplitude Filter (SVD-AF) and confirm the detection of a misalignment fault and a rotor friction fault.…”

Section: Methodsmentioning

confidence: 99%

Induction Motor Bearing Fault Diagnosis Based on Singular Value Decomposition of the Stator Current

2023

View full text Add to dashboard Cite

Among the most widespread systems in industrial plants are automated drive systems, the key and most common element of which is the induction motor. In view of challenging operating conditions of equipment, the task of fault detection based on the analysis of electrical parameters is relevant. The authors propose the identification of patterns characterizing the occurrence and development of the bearing defect by the singular analysis method as applied to the stator current signature. As a result of the decomposition, the time series of the three-phase current are represented by singular triples ordered by decreasing contribution, which are reconstructed into the form of time series for subsequent analysis using a Hankelization of matrices. Experimental studies with bearing damage imitation made it possible to establish the relationship between the changes in the contribution of the reconstructed time series and the presence of different levels of bearing defects. By using the contribution level and tracking the movement of the specific time series, it became possible to observe both the appearance of new components in the current signal and the changes in the contribution of the components corresponding to the defect to the overall structure. The authors verified the clustering results based on a visual assessment of the component matrices’ structure similarity using scattergrams and hierarchical clustering. The reconstruction of the time series from the results of the component grouping allows the use of these components for the subsequent prediction of faults development in electric motors.

show abstract

Section: Methodsmentioning

confidence: 99%

Induction Motor Bearing Fault Diagnosis Based on Singular Value Decomposition of the Stator Current

2023

View full text Add to dashboard Cite

show abstract

“…The search range for the two damping coefficients is set to (0,0.3], the step size is 0.01, the interval of τ is [0, T c ], and T c is the signal time series used for the correlation search [30]. This creates a three-dimensional search domain, and the wavelet is compared to the original pulse signal over the search domain using cross-correlation analysis until a match is found, and the correlation analysis function is shown in equation (7):…”

Section: Constructing the Padmentioning

confidence: 99%

“…Jiang et al [6] integrated the edited cepstrum with a sparse dictionary to address the challenge of identifying modal parameters in fault signals. Based on the feature extraction characteristics of singular value decomposition (SVD), Zhao and Ye [7] proposed a method with a variable matrix size that demonstrated excellent performance in extracting individual signal frequencies. Li et al [8] investigated a modified Laplace wavelet dictionary and embedded a periodic prior for bearing fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

A weighted sparse classification method based on period analysis dictionary

Wang,

Zhang,

Wang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

The periodic transient shocks triggered by damages in rolling bearings are frequently overshadowed by disruptive elements such as noise and harmonics. Therefore, the extraction of fault characteristics from these disturbances to identify the health status of the bearing is crucial for fault diagnosis. This study presents a novel approach, the Period AnalysisDictionary Weighted Sparse Representation Classification (PAD-WSRC) method, designed specifically for rolling bearings. The proposed approach incorporates Bi-damped wavelet (Bi-DW) as the dictionary wavelet atom, while accounting for the pulse characteristics induced by faults and leveraging prior knowledge of periodicity. A weighted sparse representation method was also designed, which calculates the weighted sparse representation coefficients of samples, amplifying the local features of samples while addressing the impact of time-shift bias. In addition, the bearing fault type is identified using a mutual correlation classification criterion based on sparse approximation. Our PAD-WSRC strategy has demonstrated its effectiveness in classifying the health status of bearings across two datasets, achieving recognition accuracies of 99.75% and 99.69%, respectively. Comparisons with several traditional methods further underscore the effectiveness and superiority of our proposed method in classifying rolling bearing faults.

show abstract

“…The singular value decomposition (SVD) algorithm, known for its heightened sensitivity to weak signals amidst noisy backgrounds, is frequently utilized to extract subtle fault information [4,5]. Diverse singular values within the sequence characterize different signal components and serve directly as fault features [6], prompting numerous scholars to employ singular values in depicting equipment fault states. For instance, Yanfeng Li et al [7] utilized the entire sequence of singular values from vibration signals as fault features, employing deep neural networks as classifiers to identify rolling bearing faults.…”

Section: Introductionmentioning

confidence: 99%

Research on a Wind Turbine Gearbox Fault Diagnosis Method Using Singular Value Decomposition and Graph Fourier Transform

Chen,

Zhang,

et al. 2024

Sensors

View full text Add to dashboard Cite

Gearboxes operate in challenging environments, which leads to a heightened incidence of failures, and ambient noise further compromises the accuracy of fault diagnosis. To address this issue, we introduce a fault diagnosis method that employs singular value decomposition (SVD) and graph Fourier transform (GFT). Singular values, commonly employed in feature extraction and fault diagnosis, effectively encapsulate various fault states of mechanical equipment. However, prior methods neglect the inter-relationships among singular values, resulting in the loss of subtle fault information concealed within. To precisely and effectively extract subtle fault information from gear vibration signals, this study incorporates graph signal processing (GSP) technology. Following SVD of the original vibration signal, the method constructs a graph signal using singular values as inputs, enabling the capture of topological relationships among these values and the extraction of concealed fault information. Subsequently, the graph signal undergoes a transformation via GFT, facilitating the extraction of fault features from the graph spectral domain. Ultimately, by assessing the Mahalanobis distance between training and testing samples, distinct defect states are discerned and diagnosed. Experimental results on bearing and gear faults demonstrate that the proposed method exhibits enhanced robustness to noise, enabling accurate and effective diagnosis of gearbox faults in environments with substantial noise.

show abstract

Feature frequency extraction algorithm based on the singular value decomposition with changed matrix size and its application in fault diagnosis

Cited by 18 publications

References 35 publications

Induction Motor Bearing Fault Diagnosis Based on Singular Value Decomposition of the Stator Current

Induction Motor Bearing Fault Diagnosis Based on Singular Value Decomposition of the Stator Current

A weighted sparse classification method based on period analysis dictionary

Research on a Wind Turbine Gearbox Fault Diagnosis Method Using Singular Value Decomposition and Graph Fourier Transform

Contact Info

Product

Resources

About