Feature Extraction of Rolling Bearing Fault Diagnosis

Mechanical equipment fault diagnosis occupies an important position in the industrial production, and feature extraction plays an important role in fault diagnosis. This paper analyzes various methods of feature extraction in rolling bearing fault diagnosis and classifies them into two big categories, which are methods of depending on empirical rules and experimental trials and using objective methods for screening. The former includes five methods: frequency as the characteristic parameters, multi-sensor information fusion method, rough set attribute reduction method, "zoom" method and vibration signal as the characteristic parameters. The latter includes two methods: sensitivity extraction and data mining methods to select attributes. Currently, selection methods of feature parameters depend heavily on empirical rules and experimental trials, thus extraction results are be subjected to restriction from subjective level, feature extraction in the future will develop toward objective screening direction.

Download Full-text

Feature extraction for rolling bearing fault diagnosis by electrostatic monitoring sensors

Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science ◽

10.1177/0954406214550014 ◽

2014 ◽

Vol 229 (10) ◽

pp. 1887-1903 ◽

Cited By ~ 11

Author(s):

Ying Zhang ◽

Hongfu Zuo ◽

Fang Bai

Keyword(s):

Feature Extraction ◽

Fault Diagnosis ◽

Hankel Matrix ◽

Rolling Bearing ◽

Difference Spectrum ◽

Permutation Entropy ◽

Feature Extraction Method ◽

Bearing Fault ◽

Quantitative Indicator ◽

Bearing Fault Diagnosis

There are mainly two problems with the current feature extraction methods used in the electrostatic monitoring of rolling bearings, which affect their abilities to identify early faults: (1) since noises are mixed in the electrostatic signals, it is difficult to extract weak early fault features; (2) traditional time and frequency domain features have limited ability to provide a quantitative indicator of degradation state. With regard to these two problems, a new feature extraction method for rolling bearing fault diagnosis by electrostatic monitoring sensors is proposed in this paper. First, the spectrum interpolation is adopted to suppress the power-frequency interference in the electrostatic signal. Then the resultant signal is used to construct Hankel matrix, the number of useful components is automatically selected based on the difference spectrum of singular values, after that the signal is reconstructed to remove background noises and random pulses. Finally, the permutation entropy of the denoised signal is calculated and smoothed using the exponential weighted moving average method, which is used to be a quantitative indicator of bearing performance state. The simulation and experimental results show that the proposed method can effectively remove noises and significantly bring forward the time when early faults are detected.

Download Full-text

Deep Transfer Learning Method Based on 1D-CNN for Bearing Fault Diagnosis

Shock and Vibration ◽

10.1155/2021/6687331 ◽

2021 ◽

Vol 2021 ◽

pp. 1-16

Author(s):

Jun He ◽

Xiang Li ◽

Yong Chen ◽

Danfeng Chen ◽

Jing Guo ◽

...

Keyword(s):

Fault Diagnosis ◽

Transfer Learning ◽

Vibration Signal ◽

Rolling Bearing ◽

Learning Method ◽

Target Domain ◽

Source Domain ◽

Second Order Statistics ◽

Bearing Fault ◽

Bearing Fault Diagnosis

In mechanical fault diagnosis, it is impossible to collect massive labeled samples with the same distribution in real industry. Transfer learning, a promising method, is usually used to address the critical problem. However, as the number of samples increases, the interdomain distribution discrepancy measurement of the existing method has a higher computational complexity, which may make the generalization ability of the method worse. To solve the problem, we propose a deep transfer learning method based on 1D-CNN for rolling bearing fault diagnosis. First, 1-dimension convolutional neural network (1D-CNN), as the basic framework, is used to extract features from vibration signal. The CORrelation ALignment (CORAL) is employed to minimize marginal distribution discrepancy between the source domain and target domain. Then, the cross-entropy loss function and Adam optimizer are used to minimize the classification errors and the second-order statistics of feature distance between the source domain and target domain, respectively. Finally, based on the bearing datasets of Case Western Reserve University and Jiangnan University, seven transfer fault diagnosis comparison experiments are carried out. The results show that our method has better performance.

Download Full-text

Research on rolling bearing fault diagnosis based on multi-dimensional feature extraction and evidence fusion theory

Royal Society Open Science ◽

10.1098/rsos.181488 ◽

2019 ◽

Vol 6 (2) ◽

pp. 181488 ◽

Cited By ~ 4

Author(s):

Jingchao Li ◽

Yulong Ying ◽

Yuan Ren ◽

Siyu Xu ◽

Dongyuan Bi ◽

...

Keyword(s):

Pattern Recognition ◽

Feature Extraction ◽

Fault Diagnosis ◽

Real Time ◽

Rolling Bearing ◽

Diagnostic Methods ◽

Bearing Fault ◽

Feature Vectors ◽

Bearing Fault Diagnosis ◽

Fusion Theory

Rolling bearing failure is the main cause of failure of rotating machinery, and leads to huge economic losses. The demand of the technique on rolling bearing fault diagnosis in industrial applications is increasing. With the development of artificial intelligence, the procedure of rolling bearing fault diagnosis is more and more treated as a procedure of pattern recognition, and its effectiveness and reliability mainly depend on the selection of dominant characteristic vector of the fault features. In this paper, a novel diagnostic framework for rolling bearing faults based on multi-dimensional feature extraction and evidence fusion theory is proposed to fulfil the requirements for effective assessment of different fault types and severities with real-time computational performance. Firstly, a multi-dimensional feature extraction strategy on the basis of entropy characteristics, Holder coefficient characteristics and improved generalized box-counting dimension characteristics is executed for extracting health status feature vectors from vibration signals. And, secondly, a grey relation algorithm is used to calculate the basic belief assignments (BBAs) using the extracted feature vectors, and lastly, the BBAs are fused through the Yager algorithm for achieving bearing fault pattern recognition. The related experimental study has illustrated the proposed method can effectively and efficiently recognize various fault types and severities in comparison with the existing intelligent diagnostic methods based on a small number of training samples with good real-time performance, and may be used for online assessment.

Download Full-text

High Resonance Component of Resonance-Based Sparse Decomposition Application in Extraction of Rolling Bearing Fault Information

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.753-755.2290 ◽

2013 ◽

Vol 753-755 ◽

pp. 2290-2296 ◽

Cited By ~ 2

Author(s):

Wen Tao Huang ◽

Yin Feng Liu ◽

Pei Lu Niu ◽

Wei Jie Wang

Keyword(s):

Fault Diagnosis ◽

Vibration Signal ◽

Rolling Bearing ◽

Frequency Resolution ◽

Sparse Decomposition ◽

High Resonance ◽

Bearing Fault ◽

Bearing Fault Diagnosis ◽

Information Frequency ◽

Fault Information

In the early fault diagnosis of rolling bearing, the vibration signal is mixed with a lot of noise, resulting in the difficulties in analysis of early weak fault signal. This article introduces resonance-based signal sparse decomposition (RSSD) into rolling bearing fault diagnosis, and studies the fault information contained in high resonance component and low resonance component. This article compares the effect of the two resonance components to extract rolling bearing fault information in four aspects: the amount of fault information, frequency resolution of subbands, sensitivity to noise and immunity to autocorrelation processing. We find that the high resonance component has greater advantage in extraction of rolling bearing fault information, and it is able to indicate rolling bearing failure accurately.

Download Full-text

Adaptive feature extraction for low speed rolling bearing fault diagnosis based on improved Teager energy operator, Auto-encoder and PCA

The Proceedings of the Symposium on Evaluation and Diagnosis ◽

10.1299/jsmesed.2019.18.203 ◽

2019 ◽

Vol 2019.18 (0) ◽

pp. 203

Author(s):

Duan Tangshao ◽

Liao Zhiqiang ◽

Tang Haihong ◽

Fang Ziye ◽

Jinyama Ho

Keyword(s):

Feature Extraction ◽

Fault Diagnosis ◽

Energy Operator ◽

Rolling Bearing ◽

Low Speed ◽

Bearing Fault ◽

Bearing Fault Diagnosis ◽

Teager Energy Operator ◽

Adaptive Feature Extraction ◽

Teager Energy

Download Full-text

A cross domain feature extraction method based on transfer component analysis for rolling bearing fault diagnosis

2017 29th Chinese Control And Decision Conference (CCDC) ◽

10.1109/ccdc.2017.7978168 ◽

2017 ◽

Cited By ~ 4

Author(s):

Chen Chen ◽

Zhiheng Li ◽

Jun Yang ◽

Bin Liang

Keyword(s):

Feature Extraction ◽

Fault Diagnosis ◽

Extraction Method ◽

Rolling Bearing ◽

Component Analysis ◽

Feature Extraction Method ◽

Bearing Fault ◽

Bearing Fault Diagnosis ◽

Cross Domain

Download Full-text

Bearing Fault Diagnosis Based on Deep Belief Network and Multisensor Information Fusion

Shock and Vibration ◽

10.1155/2016/9306205 ◽

2016 ◽

Vol 2016 ◽

pp. 1-9 ◽

Cited By ~ 27

Author(s):

Jie Tao ◽

Yilun Liu ◽

Dalian Yang

Keyword(s):

Fault Diagnosis ◽

Vibration Signal ◽

Rolling Bearing ◽

Deep Belief Network ◽

Identification Accuracy ◽

Learning Ability ◽

Belief Network ◽

Bearing Fault ◽

Bearing Fault Diagnosis ◽

The Individual

In the rolling bearing fault diagnosis, the vibration signal of single sensor is usually nonstationary and noisy, which contains very little useful information, and impacts the accuracy of fault diagnosis. In order to solve the problem, this paper presents a novel fault diagnosis method using multivibration signals and deep belief network (DBN). By utilizing the DBN’s learning ability, the proposed method can adaptively fuse multifeature data and identify various bearing faults. Firstly, multiple vibration signals are acquainted from various fault bearings. Secondly, some time-domain characteristics are extracted from original signals of each individual sensor. Finally, the features data of all sensors are put into the DBN and generate an appropriate classifier to complete fault diagnosis. In order to demonstrate the effectiveness of multivibration signals, experiments are carried out on the individual sensor with the same conditions and procedure. At the same time, the method is compared with SVM, KNN, and BPNN methods. The results show that the DBN-based method is able to not only adaptively fuse multisensor data, but also obtain higher identification accuracy than other methods.

Download Full-text

Rolling Bearing Fault Diagnosis Based on Second Generation Wavelet Denoising and Improved EEMD

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.556-562.2677 ◽

2014 ◽

Vol 556-562 ◽

pp. 2677-2680 ◽

Cited By ~ 2

Author(s):

Ling Jie Meng ◽

Jia Wei Xiang

Keyword(s):

Fault Diagnosis ◽

Second Generation ◽

Selection Criterion ◽

Vibration Signal ◽

Rolling Bearing ◽

Wavelet Denoising ◽

Intrinsic Mode Functions ◽

Bearing Fault ◽

Bearing Fault Diagnosis ◽

Second Generation Wavelet

A new rolling bearing fault diagnosis approach is proposed. The original vibration signal is purified using the second generation wavelet denoising. The purified signal is further decomposed by an improved ensemble empirical mode decomposition (EEMD) method. A new selection criterion, including correlation analysis and the first two intrinsic mode functions (IMFs) with the maximum energy, is put forward to eliminate the pseudo low-frequency components. Experimental investigation show that the rolling bearing fault features can be effectively extracted.

Download Full-text

Application of Balanced Multi-Wavelet in the Fault Diagnosis of Rolling Bearing

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.226-228.210 ◽

2012 ◽

Vol 226-228 ◽

pp. 210-215

Author(s):

Sui Zheng Zhang ◽

Jian Yu Zhang ◽

Yang Yang

Keyword(s):

Fault Diagnosis ◽

Vibration Signal ◽

Rolling Bearing ◽

Vanishing Moments ◽

One Dimensional ◽

Bearing Fault ◽

Bearing Fault Diagnosis ◽

Band Index ◽

Different Characteristics ◽

Better Than

Multi-wavelet has many excellent properties that single wavelet cannot satisfy simultaneously, such as symmetry, orthogonality, compact support and high vanishing moments etc. It contains several scaling functions and wavelet functions, which can make it match different characteristics of analyzed signal. Therefore, it is always used in bearing fault diagnosis. However, multi-wavelet is multi-dimensional and vibration signal is one-dimensional, so the 1-D vibration signal should be preprocessed before being decomposed with multi-wavelet. It means that the initial data need to be converted to r-dimensional data, and then is input to a tower algorithm. If preprocessing is done, multi-wavelet properties will be destroyed. Due to balanced multi-wavelet has unique properties, the preprocessing can be omitted. In this paper, a balanced multi-wavelet called CL4BAL is designed through balancing original CL4 multi-wavelet and is applied in the vibration signal processing. Comparing the frequency band index after decomposition and reconstruction of CL4BAL and CL4 multi-wavelet, it can be proved that CL4BAL is much better than that of CL4 multi-wavelet in bearing fault diagnosis.

Download Full-text