Fault diagnosis of ball bearings using machine learning methods

Kankar, Pavan Kumar; Sharma, Satish C.; Harsha, S. P.

doi:10.1016/j.eswa.2010.07.119

Cited by 377 publications

(128 citation statements)

References 9 publications

Supporting

Mentioning

123

Contrasting

Unclassified

Order By: Relevance

“…We have conducted a comparative study with another method developed in here [14]. As we said before, pattern recognition problems solving has two steps: feature extraction and classification.…”

Section: Resultsmentioning

confidence: 99%

“…In this paper, we demonstrate the feasibility of a PCA-ANN method, having the principal component analysis as feature extractor and artificial neural network as classifier. In [14] instead, they have used statistical features (for feature extraction) and neural network (for classification). Using the vibration signals of ball bearing components, they have computed for each signal 6 statistical features that have been fed as inputs of the neural network.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Sound Based Machine Fault Diagnosis System Using Pattern Recognition Techniques

Vununu¹,

Moon²,

Lee³

et al. 2017

Journal of Korea Multimedia Society

View full text Add to dashboard Cite

Machine fault diagnosis recovers all the studies that aim to detect automatically faults or damages on machines. Generally, it is very difficult to diagnose a machine fault by conventional methods based on mathematical models because of the complexity of the real world systems and the obvious existence of nonlinear factors. This study develops an automatic machine fault diagnosis system that uses pattern recognition techniques such as principal component analysis (PCA) and artificial neural networks (ANN). The sounds emitted by the operating machine, a drill in this case, are obtained and analyzed for the different operating conditions. The specific machine conditions considered in this research are the undamaged drill and the defected drill with wear. Principal component analysis is first used to reduce the dimensionality of the original sound data. The first principal components are then used as the inputs of a neural network based classifier to separate normal and defected drill sound data. The results show that the proposed PCA-ANN method can be used for the sounds based automated diagnosis system.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Sound Based Machine Fault Diagnosis System Using Pattern Recognition Techniques

Vununu¹,

Moon²,

Lee³

et al. 2017

Journal of Korea Multimedia Society

View full text Add to dashboard Cite

show abstract

“…Furthermore, in engineering field, R. Diao et al have used logistic regression and decision tree method to assess security systems that can result in voltage collapse [13]. Also, Kankar et al used artificial neural network and support vector machine to predict failures in ball bearings [14]. As can be seen, machine learning methods are widely used in a variety of fields for predicting catastrophic events.…”

Section: Fig 1 Number Of Interphase Spacers Installed and Numbermentioning

confidence: 99%

Prediction of Galloping Accidents in Power Transmission Line Using Logistic Regression Analysis

Lee¹,

Jung²,

Koo³

et al. 2017

Journal of Electrical Engineering and Technology

View full text Add to dashboard Cite

-Galloping is one of the most serious vibration problems in transmission lines. Power lines can be extensively damaged owing to aerodynamic instabilities caused by ice accretion. In this study, the accident probability induced by galloping phenomenon was analyzed using logistic regression analysis. As former studies have generally concluded, main factors considered were local weather factors and physical factors of power delivery systems. Since the number of transmission towers outnumbers the number of weather observatories, interpolation of weather factors, Kriging to be more specific, has been conducted in prior to forming galloping accident estimation model. Physical factors have been provided by Korea Electric Power Corporation, however because of the large number of explanatory variables, variable selection has been conducted, leaving total 11 variables. Before forming estimation model, with 84 provided galloping cases, 840 non-galloped cases were chosen out of 13 billion cases. Prediction model for accidents by galloping has been formed with logistic regression model and validated with 4-fold validation method, corresponding AUC value of ROC curve has been used to assess the discrimination level of estimation models. As the result, logistic regression analysis effectively discriminated the power lines that experienced galloping accidents from those that did not.

show abstract

“…Existing applications include bearings (Abbasion et al, 2007;Kankar et al, 2011;Samanta et al, 2006;Sharma et al, 2015;Sugumaran et al, 2007;Widodo et al, 2009) and gearboxes (Chen et al, 2013;Li et al, 2011Li et al, , 2013Staszewski et al, 1997). The combination of CM data, signal processing and data analysis is also known as fault detection or fault diagnosis.…”

Section: Condition Monitoring Using Probabilistic Datamentioning

confidence: 99%

Risk-Based Maintenance Scheduling with application to naval vessels and ships

Cullum

Binns

Lonsdale³

et al. 2018

Ocean Engineering

View full text Add to dashboard Cite

Maintenance scheduling for naval vessels and ships requires ongoing improvement to manage rising maintenance costs within availability constraints. Existing maintenance scheduling approaches are not optimal as maintenance costs continue to rise without an improvement in vessel availability. This paper reviews the Risk-Based Maintenance Scheduling (RBM) framework as applied to ships and naval vessels, and provides a critical analysis of Risk Assessment and Maintenance Scheduling techniques used. Further, objectives and considerations are defined for future applications for ships and naval vessels, and the framework evaluated as an improvement on existing Preventative Maintenance (PM) and Reliability Centered Maintenance (RCM) methods. A probabilistic approach supported by condition monitoring data in combination with Decision Theory is suggested for the Risk Assessment and Maintenance Scheduling elements comprising an RBM Scheduling framework. Implementation of this framework from both periodic PM and RCM is presented. Development of applications from the component level upwards is suggested. Availability and overall maintenance cost are suggested as evaluation metrics against existing methods. The development of an application is formalized within a proposed framework. The development of an application within the RBM Scheduling framework is expected to result in reduced maintenance costs while meeting availability requirements for ship and naval vessel applications.

show abstract

Fault diagnosis of ball bearings using machine learning methods

Cited by 377 publications

References 9 publications

Sound Based Machine Fault Diagnosis System Using Pattern Recognition Techniques

Sound Based Machine Fault Diagnosis System Using Pattern Recognition Techniques

Prediction of Galloping Accidents in Power Transmission Line Using Logistic Regression Analysis

Risk-Based Maintenance Scheduling with application to naval vessels and ships

Contact Info

Product

Resources

About