Incipient rolling element bearing weak fault feature extraction based on adaptive second-order stochastic resonance incorporated by mode decomposition

He, Chunlin; Niu, Pei; Yang, Rui; Wang, Chaoge; Li, Zhixiong; Li, Hongkun

doi:10.1016/j.measurement.2019.05.052

Cited by 45 publications

(12 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, these methods can identify the health status of the machine and the operating state of the rolling bearing by comparing the feature frequency of each bearing fault state and the characteristic spectrum of the vibration signal [9]. These kinds of methods perform well, and the characteristic frequency can be found in the complex signal, but more manual experience is needed [10,11]. It is also difficult to diagnose the degree or the type of fault.…”

Section: Introductionmentioning

confidence: 99%

The Method of Rolling Bearing Fault Diagnosis Based on Multi-Domain Supervised Learning of Convolution Neural Network

Liu

Sun

et al. 2022

Energies

Self Cite

View full text Add to dashboard Cite

The rolling bearing is a critical part of rotating machinery and its condition determines the performance of industrial equipment; it is necessary to detect rolling bearing faults as early as possible. The traditional methods of fault diagnosis are not efficient and are time-consuming. With the help of deep learning, the convolution neural network (CNN) plays a huge role in the data-driven methods of bearing fault diagnosis. However, the vibration signal is non-stationary, contains high noise, and is one-dimensional, which is difficult to analyze directly by the CNN model. Considering the multi-domain learning as an advantage of deep learning, this paper proposes a novel rolling bearing fault diagnosis approach using an improved one-dimensional (1D) and two-dimensional (2D) convolution neural network (CNN) of two-domain information learning. The constructed fault diagnosis model combining 1D and 2D CNN extracts the fault features from the two-domain information of bearing fault samples. The padding and dropout technology are utilized to fully extract features from the raw data and reduce over-fitting. To prove the validity of the proposed method, this paper performs two tests with two bearing datasets, the Case Western Reserve University (CWRU) bearing dataset and the Dalian University of Technology (DUT) vibration laboratory dataset. The experimental results show that our proposed method achieves high recognition accuracy of rolling bearing fault states via two-domain learning of monitoring data, and there is no manual experience necessary. Vibration data under strong noise were also used to test the method, and the results show the superiority and robustness of the proposed method.

show abstract

Section: Introductionmentioning

confidence: 99%

The Method of Rolling Bearing Fault Diagnosis Based on Multi-Domain Supervised Learning of Convolution Neural Network

Liu

Sun

et al. 2022

Energies

Self Cite

View full text Add to dashboard Cite

show abstract

“…AE technology has high sensitivity but fast attenuation, susceptible to noise interference [10]. The CEEMDAN method has been applied to feature extraction [11] and signal denoising [12] of early weak faults of rolling bearings. As such, the method combing CEEMDAN and auto regressive (AR) spectrum is adopted in this paper.…”

Section: Introductionmentioning

confidence: 99%

Leakage Detection Based on CEEMDAN Analysis for Hydraulic Cylinder Using Acoustic Emission Technique

Zhang

Chen

Cheng

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The early internal leakage fault characteristics in hydraulic cylinder are very weak and vulnerable to environmental noise, which makes the early internal leakage fault detection very difficult. In comparison with internal leakage detection by the pressure signal, internal leakage by Acoustic emission (AE) signal has higher sensitivity and accuracy. So this paper adapts the algorithms combining complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and auto regressive (AR) spectrum. Comparing with the mean value of first intrinsic mode function (IMF1) instantaneous amplitude based on EEMD, The experimental results verify the proposed algorithms based on CEEMDAN distinguish different internal leakage levels obviously and has better performance.

show abstract

“…In recent years, the SR method has been widely applied in fault feature extraction and recognition of bearings [22,23]. Li and Shi [24] introduced a new piecewise nonlinear SR to enhance early fault features of machinery.…”

Section: Introductionmentioning

confidence: 99%

Weak Fault Detection for Rolling Bearings in Varying Working Conditions through the Second‐Order Stochastic Resonance Method with Barrier Height Optimization

Shi

Zhou

et al. 2021

Shock and Vibration

View full text Add to dashboard Cite

The stochastic resonance (SR) method is widely applied to fault feature extraction of rotary machines, which is capable of improving the weak fault detection performance by energy transformation through the potential well function. The potential well functions are mostly set fixed to reduce computational complexity, and the SR methods with fixed potential well parameters have better performances in stable working conditions. When the fault frequency changes in variable working conditions, the signal processing effect becomes different with fixed parameters, leading to errors in fault detection. In this paper, an underdamped second-order adaptive general variable-scale stochastic resonance (USAGVSR) method with potential well parameters’ optimization is put forward. For input signals with different fault frequencies, the potential well parameters related to the barrier height are figured out and optimized through the ant colony algorithm. On this basis, further optimization is carried out on undamped factor and step size for better fault detection performance. Cases with diverse fault types and in different working conditions are studied, and the performance of the proposed method is validated through experiments. The results testify that this method has better performances of weak fault feature extraction and can accurately identify different fault types in the input signals. The method proves to be effective in the weak fault extraction and classification and has a good application prospect in rolling bearings’ fault feature recognition.

show abstract

Incipient rolling element bearing weak fault feature extraction based on adaptive second-order stochastic resonance incorporated by mode decomposition

Cited by 45 publications

References 37 publications

The Method of Rolling Bearing Fault Diagnosis Based on Multi-Domain Supervised Learning of Convolution Neural Network

The Method of Rolling Bearing Fault Diagnosis Based on Multi-Domain Supervised Learning of Convolution Neural Network

Leakage Detection Based on CEEMDAN Analysis for Hydraulic Cylinder Using Acoustic Emission Technique

Weak Fault Detection for Rolling Bearings in Varying Working Conditions through the Second‐Order Stochastic Resonance Method with Barrier Height Optimization

Contact Info

Product

Resources

About