scholarly journals Degradation Assessment and Fault Diagnosis for Roller Bearing Based on AR Model and Fuzzy Cluster Analysis

2011 ◽  
Vol 18 (1-2) ◽  
pp. 127-137 ◽  
Author(s):  
Lingli Jiang ◽  
Yilun Liu ◽  
Xuejun Li ◽  
Anhua Chen
Keyword(s):  
Cluster Analysis ◽  
Fault Diagnosis ◽  
Roller Bearing ◽  
Fuzzy Cluster ◽  
Ar Model ◽  
Fuzzy Cluster Analysis ◽  
Bearing Fault Diagnosis ◽  
Stationary Signals ◽  
Gaussian Signal ◽  
Non Gaussian

This paper proposes a new approach combining autoregressive (AR) model and fuzzy cluster analysis for bearing fault diagnosis and degradation assessment. AR model is an effective approach to extract the fault feature, and is generally applied to stationary signals. However, the fault vibration signals of a roller bearing are non-stationary and non-Gaussian. Aiming at this problem, the set of parameters of the AR model is estimated based on higher-order cumulants. Consequently, the AR parameters are taken as the feature vectors, and fuzzy cluster analysis is applied to perform classification and pattern recognition. Experiments analysis results show that the proposed method can be used to identify various types and severities of fault bearings. This study is significant for non-stationary and non-Gaussian signal analysis, fault diagnosis and degradation assessment.

scholarly journals A Roller Bearing Fault Diagnosis Method Based on LCD Energy Entropy and ACROA-SVM

2014 ◽  
Vol 2014 ◽  
pp. 1-12 ◽  
Author(s):  
HungLinh Ao ◽  
Junsheng Cheng ◽  
Kenli Li ◽  
Tung Khac Truong
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Roller Bearing ◽  
Local Characteristic ◽  
Support Vector ◽  
Svm Classifier ◽  
Outer Race ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis ◽  
Energy Entropy

This study investigates a novel method for roller bearing fault diagnosis based on local characteristic-scale decomposition (LCD) energy entropy, together with a support vector machine designed using an Artificial Chemical Reaction Optimisation Algorithm, referred to as an ACROA-SVM. First, the original acceleration vibration signals are decomposed into intrinsic scale components (ISCs). Second, the concept of LCD energy entropy is introduced. Third, the energy features extracted from a number of ISCs that contain the most dominant fault information serve as input vectors for the support vector machine classifier. Finally, the ACROA-SVM classifier is proposed to recognize the faulty roller bearing pattern. The analysis of roller bearing signals with inner-race and outer-race faults shows that the diagnostic approach based on the ACROA-SVM and using LCD to extract the energy levels of the various frequency bands as features can identify roller bearing fault patterns accurately and effectively. The proposed method is superior to approaches based on Empirical Mode Decomposition method and requires less time.

scholarly journals EVALUATING THE DEGREE OF COMPLEXITY OF TIGHT OIL RECOVERY BASED ON THE CLASSIFICATION OF OILS

2020 ◽  
pp. 76-81
Author(s):  
G. Efendiyev ◽  
M. Karazhanova ◽  
D. Akhmetov ◽  
I. Piriverdiyev
Keyword(s):  
Cluster Analysis ◽  
Oil Recovery ◽  
Fuzzy Cluster ◽  
Fuzzy Cluster Analysis ◽  
Recovery Coefficient ◽  
Reservoir Permeability ◽  
Oil Density ◽  
The Relationship ◽  
Degree Of Recovery

The article discusses the results of the use of cluster analysis in assessing the degree of oil recovery complexity and its impact on the performance indicator. For this purpose, clustering was performed using a fuzzy cluster analysis algorithm. It should be noted that along with the deposits of heavy and highly viscous oils, a large share of hard-to-recover reserves is also confined to conditions with very low reservoir permeability values. Data on viscosity, oil density and oil permeability of in-situ conditions from various fields of Kazakhstan are collected. Using the results of this classification, a statistical analysis of indicators of various types of hard-torecover oils was performed. In the process of analysis, a generalized characteristic was determined for each class of oil, including viscosity, oil density and reservoir permeability. The generic characteristic is a linear transformation of the three characteristics. The results were subjected to statistical processing. At the same time, an attempt was made to establish and analyze the relationship between the degree of recovery complexity of hard-to-recover oils and oil recovery coefficient. In the course of the analysis, the average values of the oil recovery coefficient and the index of the degree of recovery complexity of hard-to-recover oil within each cluster were calculated and the relationship between them was plotted. The observed dependence, built on averaged points, is close to a power law, and, as one would expect, with an increase in the degree of oil recovery complexity, the oil recovery coefficient falls. The obtained estimates of the degree of oil recovery complexity allow us to rank different types of oils by their viscosity, density and reservoir permeability, which can be used to compare types of hard-to-recover oils by the value of the quality indicator. Methods to solve the problem of hard-to-remove high-viscosity and heavy oils should be aimed at reducing the viscosity of oil in the reservoir: injection of hot water / steam into the reservoir, the use of electric heaters, etc. Purpose. Assessment of the degree of oil recovery complexity and its impact on the efficiency of field development. The technique. The solution of the tasks set in the work was carried out on the method of mathematical statistics and the theory of fuzzy sets. In this case, the methods of processing the results, the correlation analysis, and the algorithm of fuzzy cluster analysis were used. Results. As a result of studies, 4 classes were obtained, each of which characterizes the degree of oil recovery complexity, a parameter was proposed for quantifying the degree of complexity, including oil density and viscosity, reservoir permeability, a relationship between this parameter and oil recovery coefficient was obtained. Scientific novelty. A classification of hard-to-recover reserves based on a fuzzy cluster analysis has been performed, and a parameter has been proposed for quantifying the degree of oil recovery complexity, a relationship has been obtained that allows judging the oil recovery by the degree of oil recovery complexity. Practical significance. The results obtained make it possible to classify hard-to-recover reserves and make decisions on the choice of methods for influencing the reservoir in various geological conditions.

scholarly journals Improvement of Roller Bearing Diagnosis with Unlabeled Data Using Cut Edge Weight Confidence Based Tritraining

2016 ◽  
Vol 2016 ◽  
pp. 1-9 ◽  
Author(s):  
Wei-Li Qin ◽  
Wen-Jin Zhang ◽  
Zhen-Ya Wang
Keyword(s):  
Fault Diagnosis ◽  
Roller Bearing ◽  
Unlabeled Data ◽  
Edge Weight ◽  
Ring Fault ◽  
Bearing Fault ◽  
Cut Edge ◽  
Bearing Fault Diagnosis ◽  
Roller Bearings ◽  
Diagnosis Method

Roller bearings are one of the most commonly used components in rotational machines. The fault diagnosis of roller bearings thus plays an important role in ensuring the safe functioning of the mechanical systems. However, in most cases of bearing fault diagnosis, there are limited number of labeled data to achieve a proper fault diagnosis. Therefore, exploiting unlabeled data plus few labeled data, this paper proposed a roller bearing fault diagnosis method based on tritraining to improve roller bearing diagnosis performance. To overcome the noise brought by wrong labeling into the classifiers training process, the cut edge weight confidence is introduced into the diagnosis framework. Besides a small trick called suspect principle is adopted to avoid overfitting problem. The proposed method is validated in two independent roller bearing fault experiment vibrational signals that both include three types of faults: inner-ring fault, outer-ring fault, and rolling element fault. The results demonstrate the desirable diagnostic performance improvement by the proposed method in the extreme situation where there is only limited number of labeled data.

Sign in / Sign up

Export Citation Format

Share Document