Adaptive k-Sparsity-Based Weighted Lasso for Bearing Fault Detection

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.

Section: Inputmentioning

confidence: 99%

Section: Inputmentioning

confidence: 99%

A weighted sparse classification method based on period analysis dictionary

Wang,

Zhang,

Wang

et al. 2024

“…To overcome the drawbacks caused by dictionary construction, Sun and Yu [15] proposed an adaptive weighted adjacent difference sparse representation. Due to the difficult sparsity regularization parameter setup, Sun and Yu [16] proposed an adaptive k-sparsity-based weighted lasso. CS resamples signals at a frequency significantly below twice the signal frequency, simplifying the acquisition process and saving system storage space.…”

Section: Introductionmentioning

confidence: 99%

Core consistency blind source separation based on compressive sensing trilinear decomposition

Huang,

Li,

Wang

et al. 2024

In the traditional fault diagnosis method based on blind source separation, the mechanical signals are required to meet some additional conditions in the process of estimation of mixed matrix and separation of source signals, which may cause many problems in practice application because the mechanical signals do not suffer to these additional conditions. Additionally, the trilinear model has complex construction, high computational complexity, and large storage capacity in the fault source blind separation model with trilinear parallel factors. Based on the above deficiencies, a core consistency blind source separation method is proposed based on Compressive Sensing Trilinear Decomposition. In the proposed method, the core consistency diagnostic (CORCONDIA) is used to fit the tensor model, and determine the number of fault sources. The mixed matrix of the observed signal is estimated by the load matrices. Then, the minimum norm method is used to solve the underdetermined blind separation of fault sources. The simulation and experiment results show that the proposed method is superior the traditional core consistency blind separation method based on trilinear parallel factor analysis in the underdetermined blind separation. the proposed method can effectively solve the problem that the number of sources is unknown and the number of observed signals is less than the number of source signals.

“…The use of vibration signals for fault diagnosis is a common and effective method [4]. Time-frequency Analysis (TFA) methods transform signals for fault diagnosis in timefrequency domain.…”

Section: Introductionmentioning

confidence: 99%

Bearing fault diagnosis under variable speed conditions on adaptive time frequency extraction mode decomposition

Huo,

Yang,

Yao

et al. 2024

Fault diagnosis of rolling bearings is crucial for their operation in variable working conditions in mechanical systems. Time-frequency distribution (TFD) methods are widely used in variable-speed rolling bearing fault diagnosis due to their ability to capture the time-frequency characteristics of signals. However, they suffer from weak robustness, poor resolution, and lack of feature information concentration. To address these issues, we construct a method: adaptive time frequency extraction mode decomposition (ATFEMD) by utilizing the characteristic of instantaneous frequency (IF) energy concentration in TFD. The method first enhances the adaptive time-frequency distribution (ADTFD) via an iterative algorithm, applying random sample consensus (RANSAC) algorithm enables ridges extraction from the TFD. The harmonics of the extracted ridges are then verified by passing the proxy data method, followed by a noise test to determine if the harmonics are true. From the above steps, ATFEMD decomposing the signal into physically meaningful adaptive mode (AM). This article analyzes the simulated bearing vibration and test bench bearing vibration signals to demonstrate the performance of ATFEMD. Results indicated that the proposed method is characterized by strong robustness, and good feature extraction results compared to other methods.