Detection and Classification of Rolling-Element Bearing Faults using Support Vector Machines

Rojas, Alfonso; Nandi, Asoke K.

doi:10.1109/mlsp.2005.1532891

Cited by 23 publications

(14 citation statements)

References 7 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several effect conditions such as sensor location, signal preprocessing, number of features were presented to show the performance of SVM compared with ANN. Rojas and Nandi (18,19) have improved their previous research on bearing fault diagnosis. They proposed a practical scheme for fast detection and classification of rolling element bearing.…”

Section: Review Svm For Fault Diagnosis 31 Rolling Element Bearingmentioning

confidence: 99%

Support Vector Machine for Machine Fault Diagnosis and Prognosis

Yang

Widodo

2008

JSDD

View full text Add to dashboard Cite

This paper presents a survey of fault diagnosis using support vector machine (SVM). It attempts to summarize and review the recent research and development of SVM in machine fault diagnosis. Numerous methods have been developed based on intelligent system. However, the use of SVM for machine fault diagnosis is still rare. In addition, this paper introduces the feasibility of SVM based on regression (SVR) for machine prognosis system. The proposed method is addressed to predict the upcoming state of machine based on previous condition. The viability of developed system is evaluated by using trending data of low methane compressor acquired from condition monitoring routine. The results show that SVR has potential and promise for reliable and robust forecasting tool in machine prognosis system.

show abstract

Section: Review Svm For Fault Diagnosis 31 Rolling Element Bearingmentioning

confidence: 99%

Support Vector Machine for Machine Fault Diagnosis and Prognosis

Yang

Widodo

2008

JSDD

View full text Add to dashboard Cite

show abstract

“…From numerous existing features, the selection of the most appropriate features for studying the condition of slewing bearings is not a simple task. Two different approaches to feature extraction used in bearing condition monitoring can be identified in the literature [1], [14], [15]. Both approaches extract linear timedomain features, such as root mean square (RMS), variance, skewness, and kurtosis.…”

Section: Introductionmentioning

confidence: 99%

“…The approach used in [1], [15] is not appropriate for this project because in this approach faulty signals are usually acquired from artificial bearing faults or seeded defect on inner race or outer bearing race. In this study, collecting the different kinds of slewing bearing signals from corresponding different fault conditions would be extraordinarily difficult.…”

Section: Introductionmentioning

confidence: 99%

An application of nonlinear feature extraction - A case study for low speed slewing bearing condition monitoring and prognosis

Caesarendra

Kosasih

Tieu

et al. 2013

2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics

View full text Add to dashboard Cite

Moodie, C. (2013). An application of nonlinear feature extraction -a case study for low speed slewing bearing condition monitoring and prognosis. 2013 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM) (pp. 1713-1718). United States: IEEE.An application of nonlinear feature extraction -a case study for low speed slewing bearing condition monitoring and prognosis AbstractThis paper presents the application of four nonlinear methods of feature extraction in slewing bearing condition monitoring and prognosis: these are largest Lyapunov exponent, fractal dimension, correlation dimension, and approximate entropy methods. Although correlation dimension and approximate entropy methods have been used previously, the largest Lyapunov exponent and fractal dimension methods have not been used in vibration condition monitoring to date. The vibration data of the laboratory slewing bearing testrig run at 1 rpm was acquired daily from February to August 2007 (138 days). As time progressed, a more accurate observation of the alteration of bearing condition from normal to faulty was obtained using nonlinear features extraction. These findings suggest that these methods provide superior descriptive information about bearing condition than time-domain features extraction, such as root mean square (RMS), variance, skewness and kurtosis.

show abstract

“…In recent years, many new methods in signal analysis field are constantly used for bearing vibration monitoring and fault diagnosis areas, such as wavelet analysis [2], time-frequency analysis [3], high order spectrum analysis [1,5], etc. Moreover, many research achievements in pattern recognition field (such as support vector machine [4], etc.) are also continuously introduced in intelligent diagnosis field and good results have been achieved.…”

Section: Introductionmentioning

confidence: 99%

Amplitude envelope analysis for feature extraction of direct-driven wind turbine bearing failure

Xin

Liu

et al. 2012

Proceedings of the 10th World Congress on Intelligent Control and Automation

View full text Add to dashboard Cite

Made use of the vibration signals of main shaft which were measured from a normal direct-driven wind turbine and a fault one, the vibration characteristics of main shaft bearing were analyzed and studied. From time domain, frequency domain and cepstrum domain, analyzed and compared the vibration signal characteristics between normal and fault units, then narrowband envelope analysis had been made. The difference of envelope spectrum for vibration signals between normal and fault units was revealed. The results show that narrowband envelope analysis can effectively identify the bearing fault state. Index Terms -direct-driven wind turbine; bearing fault; narrowband filtering; envelope analysis

show abstract

Detection and Classification of Rolling-Element Bearing Faults using Support Vector Machines

Cited by 23 publications

References 7 publications

Support Vector Machine for Machine Fault Diagnosis and Prognosis

Support Vector Machine for Machine Fault Diagnosis and Prognosis

An application of nonlinear feature extraction - A case study for low speed slewing bearing condition monitoring and prognosis

Amplitude envelope analysis for feature extraction of direct-driven wind turbine bearing failure

Contact Info

Product

Resources

About