An image-based feature extraction method for fault diagnosis of variable-speed rotating machinery

Park, Jung Ho; Kim, Yunhan; Na, Kyumin; Youn, Byeng D.; Chen, Yuejian; Zuo, Ming J.; Bae, Yong-Chae

doi:10.1016/j.ymssp.2021.108524

Cited by 18 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The 2D Fourier transform can be regarded as an extension of the one-dimensional (1D) Fourier transform, which can transform a 2D spatial signal or image from its spatial domain into the frequency domain, where we can easily extract important feature in frequency domain, such as periodic patterns or edges. This method is widely applied in many fields, including image processing, computer vision, and signal processing, which can be defined as follows 36 :…”

Section: Theoretical Analysismentioning

confidence: 99%

“…We have found a state-of-the-art method which is similar to the proposed method by calculating the root mean squares (RMSs) of spatial frequency components in the central horizontal components. 36 This method is also a feature extraction method for fault diagnosis based on images. We calculated the RMS index of various tools under the same condition, as shown in Table 3.…”

Section: Tool Wear Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Time-frequency analysis-based impulse feature extraction method for quantitative evaluation of milling tool wear

Guo,

Tu,

Abbas

et al. 2023

Structural Health Monitoring

View full text Add to dashboard Cite

Mechanical system condition monitoring is an important procedure in modern industry, which not only reduces maintenance costs but also ensures safe equipment operation. At present, the monitoring method based on signal processing is one of the most common and effective fault diagnosis methods. In this work, the time-frequency distribution (TFD) obtained by generalized horizontal synchrosqueezing transform is used to extract the impulse feature of the non-stationary vibration signal of the tool. By using the TFD result, the two-dimensional (2D) Fourier transform can further detect the periodic pulses. Next, the energy proportion factor of periodic frequency point is proposed to evaluate the different tool wear degrees. Numerical simulations and experimental data analysis demonstrate the effectiveness of the proposed method as well as the potential for condition monitoring.

show abstract

Section: Theoretical Analysismentioning

confidence: 99%

Section: Tool Wear Evaluationmentioning

confidence: 99%

Time-frequency analysis-based impulse feature extraction method for quantitative evaluation of milling tool wear

Guo,

Tu,

Abbas

et al. 2023

Structural Health Monitoring

View full text Add to dashboard Cite

show abstract

“…Various industrial production setups have made substantial use of rotating machinery. Because of the complexity of the operating environment and the influence of various unfavorable factors during operation, faults often occur in the components of rotating mahinery [1][2][3]. These faults not only affect * Author to whom any correspondence should be addressed.…”

Section: Introductionmentioning

confidence: 99%

A feature extraction method for rotating machinery fault diagnosis based on a target detection index and successive variational mode decomposition

Cao,

Zhang,

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Rotating machinery feature extraction is critical for the subsequent fault diagnosis and ensuring safe and stable operation. However, the commonly used methods often have limitations, such as the extracted features being redundant or insufficient and the method parameters generally being set based on experience. Although some feature extraction methods apply optimization algorithms for parameter setting, their objective functions are often too simple to obtain favorable fault diagnosis results. To address these issues, a target detection index (TDI) is constructed which can consider the discrimination among features more comprehensively and make the extracted features more sensitive. Furthermore, a fault feature extraction method is proposed based on TDI and successive variational mode decomposition (SVMD). Taking TDI as the objective function, genetic algorithm (GA) is used for the feature selection process and SVMD parameter optimization. The obtained features are then fused and visualized using t-distributed stochastic neighbor embedding and are classified using support vector machines. The Case Western Reserve University data and hydropower generating unit data are employed for method verification. When compared with other decomposition algorithms, the proposed method exhibits great ability at extracting highly sensitive features.

show abstract

“…For example, the signal is transformed into the SDP image. Then the convolution neural network is used to identify the SDP features under different vibration states [23,24]. The fault diagnosis method based on image has been applied to rolling bearing.…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis of Rolling Bearing Based on Variational Mode Decomposition and Improved Canberra Distance in Symmetrized Dot Pattern Image

Wang,

Sun

2023

JAIMLD

View full text Add to dashboard Cite

The classification of time series is an important work in mechanical fault diagnosis. In recent years, image-based signal processing methods have been widely used in bearing fault diagnosis. However, there are still some problems in the signal classification of multiple fault types and weak fault characteristics. In order to improve the classification accuracy of time series, a diagnosis method based on variable mode decomposition (VMD) and improved Canberra distance is proposed. In this method, the decomposed signal is first converted into a symmetrized dot pattern. Then the image features are extracted using Canberra distance and maximum eigenvalue. Through the obtained features, the accurate diagnosis of bearing vibration signal is realized. The experimental results show that the improved Canberra distance has high classification accuracy.

show abstract

An image-based feature extraction method for fault diagnosis of variable-speed rotating machinery

Cited by 18 publications

References 29 publications

Time-frequency analysis-based impulse feature extraction method for quantitative evaluation of milling tool wear

Time-frequency analysis-based impulse feature extraction method for quantitative evaluation of milling tool wear

A feature extraction method for rotating machinery fault diagnosis based on a target detection index and successive variational mode decomposition

Fault Diagnosis of Rolling Bearing Based on Variational Mode Decomposition and Improved Canberra Distance in Symmetrized Dot Pattern Image

Contact Info

Product

Resources

About