A new approach for performance degradation feature extraction based on generalized pattern spectrum entropy

2015 ◽  
Vol 231 (10) ◽  
pp. 1932-1945
Author(s):  
Hongbo Gao ◽  
Jie Liu ◽  
Yungong Li
Keyword(s):  
Feature Extraction ◽  
Simulation Analysis ◽  
Rolling Bearing ◽  
Performance Degradation ◽  
Particle Analysis ◽  
New Approach ◽  
Pattern Spectrum ◽  
Remaining Service Life ◽  
Degradation Degree ◽  
Fatigue Life Enhancement

Performance degradation feature extraction is the basis of degradation condition recognition and remaining service life prediction. In this paper, morphological corrosion operator is introduced into mathematical morphological particle analysis (abbreviated as MMP), proposing a new analytical method named generalized mathematical morphological particle analysis (abbreviated as GMMP). On this basis, a new approach for degradation feature extraction based on generalized pattern spectrum entropy (abbreviated as GPSE) is proposed taking GMMP and information entropy as the theoretical foundation. In this approach, GPSE is calculated as degradation feature parameter in describing performance degradation degree of machinery equipment. Simulation analysis is processed, and the result shows that the value of GPSE will increase correspondingly along with the deepening of the degradation degree and the relevance between GPSE and degradation degree is stable. The effectiveness and practicality of the approach is tested through rolling bearing whole lifetime vibrating data. Rolling bearing fatigue life enhancement testing was carried out in Hangzhou Bearing Test & Research Center, getting the whole lifetime data which is able to cover each degradation condition from normal to invalidation. The approach is applied into analysis of rolling bearing data and the results verify its validity and feasibility.

scholarly journals Feature Extraction for Bearing Fault Detection Using Wavelet Packet Energy and Fast Kurtogram Analysis

2020 ◽  
Vol 10 (21) ◽  
pp. 7715
Author(s):  
Xiaojun Zhang ◽  
Jirui Zhu ◽  
Yaqi Wu ◽  
Dong Zhen ◽  
Minglu Zhang
Keyword(s):  
Feature Extraction ◽  
Fault Detection ◽  
Simulation Analysis ◽  
Wavelet Packet ◽  
Signal Reconstruction ◽  
Rolling Bearing ◽  
Band Pass Filter ◽  
Pass Filter ◽  
Integrated Method ◽  
Reconstructed Signal

An integrated method for fault detection of bearing using wavelet packet energy (WPE) and fast kurtogram (FK) is proposed. The method consists of three stages. Firstly, several commonly used wavelet functions were compared to select the appropriate wavelet function for the application of WPE. Then the analyzed signal is decomposed using WPE and the energy of each decomposed signal is calculated and selected for signal reconstruction. Secondly, the reconstructed signal is analyzed by FK to select the best central frequency and bandwidth for the band-pass filter. Finally, the filtered signal is processed using the squared envelope frequency spectrum and compared with the theoretical fault characteristic frequency for fault feature extraction. The procedure and performance of the proposed approach are illustrated and estimated by the simulation analysis, proving that the proposed method can effectively extract the weak transients. Moreover, the analysis results of gearbox bearing and rolling bearing cases show that the proposed method can provide more accurate fault features compared with the individual FK method.

scholarly journals Bispectrum Texture Feature Manifold for Feature Extraction in Rolling Bear Fault Diagnosis

2019 ◽  
Vol 2019 ◽  
pp. 1-11 ◽  
Author(s):  
Fei Wang ◽  
Liqing Fang
Keyword(s):  
Feature Extraction ◽  
Dimensionality Reduction ◽  
Texture Feature ◽  
Texture Features ◽  
Rolling Bearing ◽  
Image Texture ◽  
Support Vector ◽  
Contour Map ◽  
Low Dimensional ◽  
Degradation Degree

Effectively classify the fault types and the degradation degree of a rolling bearing is an important basis for accurate malfunction detection. A novel feature extract method - bispectrum image texture features manifold (BTM) of the rolling bearing vibration signal is proposed in this paper. The BTM method is realized by three main steps: bispectrum image analysis, texture feature construction and manifold feature dimensionality reduction. In this method, bispectrum analysis is employed to convert the mass vibration signals into bispectrum contour map, the typical texture features were extracted from the contour map by gray level co-occurrence matrix (GLCM), then the manifold dimensionality reduction method liner local tangent space alignment (LLTSA) is used to remove redundant information and reduce the dimension from the extracted texture features and obtain more meaningful low-dimensional information. Furthermore, the low-dimensional texture features were identified by support vector machine (SVM) which was optimized by genetic optimization algorithm (GA). The validity of BTM is confirmed by rolling bear experiments, the result show that the proposed feature extraction method can accurately distinguish different fault types and have a good performance to classify the degradation degree of inner race fault, outer race fault and rolling ball fault.

scholarly journals A Novel Degradation Feature Extraction Technique Based on Improved Base-Scale Entropy

2021 ◽  
Vol 26 (1) ◽  
pp. 41-48
Author(s):  
Zhenyi Chen ◽  
Changzhuan Shao ◽  
Xiong Hu ◽  
Bing Wang ◽  
Daobing Zhang ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Approximate Entropy ◽  
Signal Amplitude ◽  
Amplitude Distribution ◽  
Rolling Bearing ◽  
Performance Degradation ◽  
Entropy Method ◽  
Extraction Technique ◽  
Information Amount ◽  
Feature Extraction Technique

In order to track the performance degradation trend accurately, a novel degradation feature extraction technique is proposed based on improved base-scale entropy. A unified base scale is proposed and a new symbol standard is defined to overcome the disadvantages of the base-scale entropy method, so as to symbolize signal amplitude to characterize information amount under different degradation conditions quantitatively. A lifetime dataset of rolling bearing from the IMS Bearing Experiment Center is introduced. For instance, analysis and some entropy-based techniques including fuzzy entropy, approximate entropy and sample entropy are imported for comparison. The results show that the improved basic-scale technique is able to characterize information amount of the signal amplitude distribution, so that the characterizing performance degradation degree of bearing shows a proportional relationship. When comparing the entropy-based techniques, the improved base-scale entropy technique has a faster calculation speed and better algorithm stability.

scholarly journals Fault Diagnosis of Rolling-Element Bearing Using Multiscale Pattern Gradient Spectrum Entropy Coupled with Laplacian Score

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-29 ◽  
Author(s):  
Xiaoan Yan ◽  
Ying Liu ◽  
Peng Ding ◽  
Minping Jia
Keyword(s):  
Feature Extraction ◽  
Fault Diagnosis ◽  
Multiple Scales ◽  
Rolling Bearing ◽  
Rolling Element Bearing ◽  
Selection Strategy ◽  
Pattern Spectrum ◽  
Bearing Fault ◽  
Laplacian Score ◽  
New Feature

Feature extraction is recognized as a critical stage in bearing fault diagnosis. Pattern spectrum (PS) and pattern spectrum entropy (PSE) in recent years have been smoothly applied in feature extraction, whereas they easily ignore the partial impulse signatures hidden in bearing vibration data. In this paper, the pattern gradient spectrum (PGS) and pattern gradient spectrum entropy (PGSE) are firstly presented to improve the performance of fault feature extraction of two approaches (PS and PSE). Nonetheless, PSE and PGSE are only able to evaluate dynamic behavior of the time series on a single scale, which implies there is no consideration of feature information at other scales. To address this problem, a novel approach entitled multiscale pattern gradient spectrum entropy (MPGSE) is further implemented to extract fault features across multiple scales, where its key parameters are determined adaptively by grey wolf optimization (GWO). Meanwhile, a Laplacian score- (LS-) based feature selection strategy is employed to choose the sensitive features and establish a new feature set. Finally, the selected new feature set is imported into extreme learning machine (ELM) to identify different health conditions of rolling bearing. Performance of our designed algorithm is tested on two experimental cases. Results confirm the availability of our proposed algorithm in feature extraction and show that our method can recognize effectively different bearing fault categories and severities. More importantly, the designed approach can achieve higher recognition accuracies and provide better stability by comparing with other entropy-based methods involved in this paper.

scholarly journals A Fault Diagnosis Method Based on Improved Pattern Spectrum and FOA-SVM

2019 ◽  
Vol 24 (2) ◽  
pp. 312-319
Author(s):  
Dejian Sun ◽  
Bing Wang ◽  
Xiong Hu ◽  
Wei Wang
Keyword(s):  
Feature Extraction ◽  
Fault Diagnosis ◽  
Simulation Analysis ◽  
Roller Bearing ◽  
Data Set ◽  
Pattern Spectrum ◽  
Vibration Data ◽  
Recognition Result ◽  
Diagnosis Method ◽  
Fault Information

A fault diagnosis method using improved pattern spectrum (IP S) and F OA−SV M is proposed. Improved pattern spectrum is introduced for feature extraction by employing morphological erosion operator, and this feature is able to present fault information for roller bearing on different scales. Simulation analysis is processed and shows that, the value of IP S has a steady distinction among different fault types and the calculating amount is less than traditional method. After feature extraction, SV M with F OA, which can help with seeking optimal parameters, is employed for pattern recognition. Experiments were conducted, and the proposed method is verified by roller bearing vibration data including different fault types. The classification accuracy of the proposed approach on training is 87.5% ( 21 24 ) and reaches 91.7% ( 44 48 ) in a testing data set. The analysis shows that the method has a good diagnosis effect and an acceptable recognition result.

Rolling bearing degradation condition clustering using multidimensional degradation feature and Gath–Geva fuzzy clustering algorithm

2020 ◽  
pp. 107754632095495
Author(s):  
Bing Wang ◽  
Xiong Hu ◽  
Tao X Mei ◽  
Sun D Jian ◽  
Wang Wei
Keyword(s):  
Fuzzy Clustering ◽  
Clustering Algorithm ◽  
Chaotic Map ◽  
Vibration Signal ◽  
Degradation Process ◽  
Rolling Bearing ◽  
Performance Degradation ◽  
Time Parameter ◽  
Mechanical Equipment ◽  
Time Dimension

In allusion to the issue of rolling bearing degradation feature extraction and degradation condition clustering, a logistic chaotic map is introduced to analyze the advantages of C0 complexity and a technique based on a multidimensional degradation feature and Gath–Geva fuzzy clustering algorithmic is proposed. The multidimensional degradation feature includes C0 complexity, root mean square, and curved time parameter which is more in line with the performance degradation process. Gath–Geva fuzzy clustering is introduced to divide different conditions during the degradation process. A rolling bearing lifetime vibration signal from intelligent maintenance system bearing test center was introduced for instance analysis. The results show that C0 complexity is able to describe the degradation process and has advantages in sensitivity and calculation speed. The introduced degradation indicator curved time parameter can reflect the agglomeration character of the degradation condition at time dimension, which is more in line with the performance degradation pattern of mechanical equipment. The Gath–Geva fuzzy clustering algorithmic is able to cluster degradation condition of mechanical equipment such as bearings accurately.

Hot Strip Tail Flick Recognition Based on Morphological Pattern Spectrum

2012 ◽  
Vol 572 ◽  
pp. 25-30
Author(s):  
Li Jing Han ◽  
Jian Hong Yang ◽  
Min Lin ◽  
Jin Wu Xu
Keyword(s):  
Feature Extraction ◽  
Extraction Method ◽  
Steel Strip ◽  
Wavelet Packet ◽  
Support Vector ◽  
Tail Flick ◽  
Morphological Pattern ◽  
Feature Extraction Method ◽  
Pattern Spectrum ◽  
Hot Strip

Hot strip tail flick is an abnormal production phenomenon, which brings many damages. To recognize the tail flick signals from all throwing steel strip signals, a feature extraction method based on morphological pattern spectrum is proposed in this paper. The area between signal curves after multiscale opening operation and the horizontal axis is computed as the pattern spectrum value and it reflects the geometric information differences. Then, support vector machine is used as the classifier. Experimental results show that the total correct rate based on pattern spectrum feature reached 96.5%. Compared with wavelet packet energy feature, the total correct rate is 92.1%. So, the feasibility and availability of this new feature extraction method are verified.

Sign in / Sign up

Export Citation Format

Share Document