A Review on Rolling Bearing Fault Signal Detection Methods Based on Different Sensors

Wu, Guoguo; Yan, Tianyi; Yang, Guolai; Chai, Hongqiang; Chen, Cao

doi:10.3390/s22218330

Cited by 42 publications

(22 citation statements)

References 132 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, acoustic emission sensors—typically used to perform an analysis of load torque, rotational speed signal, magnetic field frequency, etc.—could allow for the detection of a two-dimensional (2D) signal system. Nonetheless, complex mathematical calculations, a numerical model, or even a neural network would need to be carried out to transform signals detected by the sensors into 2D images that could then be analyzed and diagnosed [ 19 ]. In order to enhance productivity and reduce maintenance cost, an online monitoring system is essential to check the status of bearings.…”

Section: Introductionmentioning

confidence: 99%

Design Rules of Bidirectional Smart Sensor Coating for Condition Monitoring of Bearings

Nguyen

Bernadet

et al. 2023

Polymers

View full text Add to dashboard Cite

This paper reports a novel monitoring technique of bearings’ bidirectional load (axial and radial) based on a smart sensor coating, which is screen printed onto the surface of a cross-shaped steel substrate. To ensure the accuracy and stability of measurement as well as the durability of the printed coating, the developed prototype is built according to design rules commonly used in electronic circuits. The finite element model (FEM) is used to predict the mechanical property of the tested substrate under either unidirectional or bidirectional loads. Regarding the output voltage of the piezoelectric sensor, experimental results are revealed to be well-corelated to the numerical simulation. It is pointed out that the output signal generated from the sensor (electrode) could be particularly affected due to the capacitive parasite coming from the conductive tracks (CTs). Such a phenomenon might be reduced by printing them on the dielectric layer rather than on the piezocomposite layer. The study also investigates a highly anisotropic shape of electrodes (rectangular instead of circle), indicating that the orientation of such electrodes (axial or radial) does affect the output measurement. To sum up, the high performance of a sensor network coating depends not only on the ultimate characteristics of its own materials, but also on its structural design. Such an issue has been rarely reported on in the literature, but is nonetheless crucial to achieving reliable condition monitoring of bearings, especially for multidirectional loads—a key signature of early failure detection.

show abstract

Section: Introductionmentioning

confidence: 99%

Design Rules of Bidirectional Smart Sensor Coating for Condition Monitoring of Bearings

Nguyen

Bernadet

et al. 2023

Polymers

View full text Add to dashboard Cite

show abstract

“…Rolling bearing faults are the leading cause of the failure of rotating machinery, bringing economic losses and even unplanned downtime. The fault diagnosis of rolling bearings before catastrophic failure is one of the main concerns of these industries [ 1 ] and is essential for the availability and reliability of mechanical systems [ 2 ].…”

Section: Introductionmentioning

confidence: 99%

A Sound and Vibration Fusion Method for Fault Diagnosis of Rolling Bearings under Speed-Varying Conditions

Wan

Yang

et al. 2023

Sensors

View full text Add to dashboard Cite

The fault diagnosis of rolling bearings is critical for the reliability assurance of mechanical systems. The operating speeds of the rolling bearings in industrial applications are usually time-varying, and the monitoring data available are difficult to cover all the speeds. Though deep learning techniques have been well developed, the generalization capacity under different working speeds is still challenging. In this paper, a sound and vibration fusion method, named the fusion multiscale convolutional neural network (F-MSCNN), was developed with strong adaptation performance under speed-varying conditions. The F-MSCNN works directly on raw sound and vibration signals. A fusion layer and a multiscale convolutional layer were added at the beginning of the model. With comprehensive information, such as the input, multiscale features are learned for subsequent classification. An experiment on the rolling bearing test bed was carried out, and six datasets under various working speeds were constructed. The results show that the proposed F-MSCNN can achieve high accuracy with stable performance when the speeds of the testing set are the same as or different from the training set. A comparison with other methods on the same datasets also proves the superiority of F-MSCNN in speed generalization. The diagnosis accuracy improves by sound and vibration fusion and multiscale feature learning.

show abstract

“…In recent decades, many bearing fault diagnosis techniques have been developed based on acoustic emission (AE). AE-based analysis enables detection of very low-energy signals caused by bearing failures at an early stage or during low-speed operation [ 5 , 6 , 7 ]. However, because the sampling rate used for AE signal collection is usually greater than 1 MHz, analysis of AE signals is difficult because of the tremendous amount of data in the collected time series and the computational time required for analysis [ 8 ].…”

Section: Introductionmentioning

confidence: 99%

Extreme-Low-Speed Heavy Load Bearing Fault Diagnosis by Using Improved RepVGG and Acoustic Emission Signals

Jiang

Sun

et al. 2023

Sensors

View full text Add to dashboard Cite

With the worldwide carbon neutralization boom, low-speed heavy load bearings have been widely used in the field of wind power. Bearing failure generates impulses when the rolling element passes the cracked surface of the bearing. Over the past decade, acoustic emission (AE) techniques have been used to detect failure signals. However, the high sampling rates of AE signals make it difficult to design and extract fault features; thus, deep neural network-based approaches have been proposed. In this paper, we proposed an improved RepVGG bearing fault diagnosis technique. The normalized and noise-reduced bearing signals were first converted into Mel frequency cepstrum coefficients (MFCCs) and then inputted into the model. In addition, the exponential moving average method was used to optimize the model and improve its accuracy. Data were extracted from the test bench and wind turbine main shaft bearing. Four damage classes were studied experimentally. The experimental results demonstrated that the improved RepVGG model could be employed for classifying low-speed heavy load bearing states by using MFCCs. Furthermore, the effectiveness of the proposed model was assessed by performing comparisons with existing models.

show abstract

A Review on Rolling Bearing Fault Signal Detection Methods Based on Different Sensors

Cited by 42 publications

References 132 publications

Design Rules of Bidirectional Smart Sensor Coating for Condition Monitoring of Bearings

Design Rules of Bidirectional Smart Sensor Coating for Condition Monitoring of Bearings

A Sound and Vibration Fusion Method for Fault Diagnosis of Rolling Bearings under Speed-Varying Conditions

Extreme-Low-Speed Heavy Load Bearing Fault Diagnosis by Using Improved RepVGG and Acoustic Emission Signals

Contact Info

Product

Resources

About