A two-stage method for bearing fault detection using graph similarity evaluation

Sun, Weifang; Zhou, Yuqing; Xiao, Cao; Chen, Binqiang; Feng, Wei; Chen, Leiqing

doi:10.1016/j.measurement.2020.108138

Cited by 22 publications

(7 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For a given test signal y , the corresponding adjacency matrix Y can be established accordingly. Similarity, the adjacency matrix Y can be decomposed as 28 : where the symbol diag [.] represents the diagonal elements of the adjacency matrix, and non–diag [.]…”

Section: Anomalies Identification For Time-seriesmentioning

confidence: 99%

See 1 more Smart Citation

In-situ tool wear condition monitoring during the end milling process based on dynamic mode and abnormal evaluation

Chen,

Mao,

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

Rapid tool wear conditions during the manufacturing process are crucial for the enhancement of product quality. As an extension of our recent works, in this research, a generic in-situ tool wear condition monitoring during the end milling process based on dynamic mode and abnormal evaluation is proposed. With the engagement of dynamic mode decomposition, the real-time response of the sensing physical quantity during the end milling process can be predicted. Besides, by constructing the graph structure of the time series and calculating the difference between the predicted signal and the real-time signal, the anomaly can be acquired. Meanwhile, the tool wear state during the end milling process can be successfully evaluated. The proposed method is validated in milling tool wear experiments and received positive results (the mean relative error is recorded as 0.0507). The research, therefore, paves a new way to realize the in-situ tool wear condition monitoring.

show abstract

Section: Anomalies Identification For Time-seriesmentioning

confidence: 99%

“…For a given test signal y, the corresponding adjacency matrix Y can be established accordingly. Similarity, the adjacency matrix Y can be decomposed as 28 :…”

Section: Anomalies Identificationmentioning

confidence: 99%

In-situ tool wear condition monitoring during the end milling process based on dynamic mode and abnormal evaluation

Chen,

Mao,

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…With this approach, the methods based on spectral graph theory show good performance in terms of early fault detection and generalization with insufficient data owing to the cycleto-cycle strategy. Sun et al (2020) used the spectral graph theory as preprocessing for feature extraction. Specifically, they introduced a method that extracts fault features using maximum correlated kurtosis deconvolution.…”

Section: Introductionmentioning

confidence: 99%

“…To improve the performance of fault feature extraction, they firstly constructed an adjacency matrix by calculating Euclidean distance between time steps and used graph similarity based on eigendecomposition to identify fault states in advance. Lu et al (2018) constructed adjacency matrices for time-series instances in a normal state in the same way as in Sun et al (2020), and derived representative eigenvector and eigenvalue using eigendecomposition for the averaged matrix. Then, with the fixed derived eigenvector, they used a martingale-test based on the Frobenius norm of the difference of non-diagonal component between the derived eigenvalue matrix and that of a time-series instance to be tested.…”

Section: Introductionmentioning

confidence: 99%

Novel Graph-Based Features for Bearing Fault Diagnosis: Two Aspects of Time Series Structure

2022

View full text Add to dashboard Cite

The feature-based methods for bearing fault diagnosis in prognostics and health management have been achieved satisfactory performances because of their robustness to noise and reduced dimension by pre-defined features. However, widely employed time- and frequency-domain features are insufficient to recognize the global pattern that indicates the structure of a time-series instance. In this paper, we propose two novel graph-based features which reflect the connection strength and degree of time series, respectively. First, we construct a graph of which an edge is defined as the Euclidean distance between each pair of time steps to measure the strengths of connections between the nodes. The other graph is constructed by the visibility algorithm, which converts a time series into a complex network to reflect the degrees of connections. Then, we calculate the Frobenius norms of the adjacency matrices of both graphs and use them as features for bearing fault diagnosis. To verify the proposed features, we performed several experiments with both synthetic and real datasets. From the synthetic datasets, it is observed that the changes in amplitudes and frequencies are detected by the features for the connection strength and degree, respectively. In addition, the proposed features also well-separate the distributions of each bearing state, including normal and several fault types, and show significant performance improvement as applied to the fault diagnosis task.

show abstract

“…Due to its manufacturing costs advantage and real-time monitoring, indirect tool wear detection attracts the attention of many scholars. Vibration signal is the most widely used method for machinery condition monitoring and fault detection [8][9][10]. Besides, machine learning techniques also identified a promising option in various engineering application scenarios [11][12][13].…”

Section: Introductionmentioning

confidence: 99%

An Improved Tool Wear Monitoring Method Using Local Image and Fractal Dimension of Workpiece

Yu¹,

Wang

Zhang³

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Tool wear is a key factor that dominates the surface quality and distinctly influences the generated workpiece surface texture. In order to realize accurate evaluation of the tool wear from the generated workpiece surface after machining process, a new tool wear monitoring method is developed by fractal dimension of the acquired workpiece surface digital image. A self-made simple apparatus is employed to capture the local digital images around the region of interest. In addition, a skew correction method based on local fast Fourier transformation energy is also proposed for the surface texture direction adjustment. Furthermore, the tool wear quantitative evaluation was derived based on fractal dimension utilizing its high reliability for inherent irregularity description. The proposed tool wear monitoring method has verified its feasibility as well as its effectiveness in actual milling experiments using the material of AISI 1045 in a vertical machining center. Testing results demonstrate that the proposed method was capable of tool wear condition evaluation.

show abstract

A two-stage method for bearing fault detection using graph similarity evaluation

Cited by 22 publications

References 32 publications

In-situ tool wear condition monitoring during the end milling process based on dynamic mode and abnormal evaluation

In-situ tool wear condition monitoring during the end milling process based on dynamic mode and abnormal evaluation

Novel Graph-Based Features for Bearing Fault Diagnosis: Two Aspects of Time Series Structure

An Improved Tool Wear Monitoring Method Using Local Image and Fractal Dimension of Workpiece

Contact Info

Product

Resources

About