Validating Prognostic Algorithms: A Case Study Using Comprehensive Bearing Fault Data

Lybeck, Nancy J.; Marble, S.; Morton, Brogan

doi:10.1109/aero.2007.352842

Search citation statements

Order By: Relevance

Paper Sections

Select...

Introduction2

Original Feature Set1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2009

2016

Publication Types

Select...

Article7

Book1

Relationship

Self Cite0

Independent8

Authors

Journals

Cited by 25 publications

(22 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So these feature's stability is not good. Lybeck et al [14] studied some statistic features' correlation with spall length. These features' behavior is disappointing.…”

mentioning

confidence: 99%

Robust bearing performance degradation assessment method based on improved wavelet packet–support vector data description

Pan

Chen

Guo

2009

Mechanical Systems and Signal Processing

181

View full text Add to dashboard Cite

“…So these feature's stability is not good. Lybeck et al [14] studied some statistic features' correlation with spall length. These features' behavior is disappointing.…”

mentioning

confidence: 99%

Robust bearing performance degradation assessment method based on improved wavelet packet–support vector data description

Pan

Chen

Guo

2009

Mechanical Systems and Signal Processing

181

View full text Add to dashboard Cite

“…But these statistic parameters reflect the operation condition in different ways [3]. In this study, ten time domain features are selected, i.e., peak-to-peak value, mean value, peak value, root mean square (RMS), impulse factor, crest factor, waveform factor, clearance factor, skewness factor and kurtosis factor.…”

Section: Original Feature Setmentioning

confidence: 99%

Bearing fault recognition method based on neighbourhood component analysis and coupled hidden Markov model

Zhou

Chen

Dong

et al. 2016

Mechanical Systems and Signal Processing

View full text Add to dashboard Cite

“…[3][4][5]. Usually these values are calculated from the generated vibrations filtered on specific frequency bands.…”

Section: Introductionmentioning

confidence: 99%

Signal Complexity and Gaussian Process Models Approach for Bearing Remaining Useful Life Estimation

Boškoski

Gašperin

Petelin

2013

Lecture Notes in Mechanical Engineering

View full text Add to dashboard Cite

Standard bearing fault detection features are shown to be ineffective for estimating bearings remaining useful life (RUL). In this paper we propose a new approach estimating bearing RUL based on features describing the statistical complexity of the envelope of the generated vibrations and a set of Gaussian process (GP) models. The proposed approach is shown to be sensitive to incipient condition deterioration which allows timely and sufficiently accurate estimates of the RUL. The proposed approach was evaluated on the data set comprising of 17 bearing runs with natural fault evolution.

show abstract

Validating Prognostic Algorithms: A Case Study Using Comprehensive Bearing Fault Data

Cited by 25 publications

References 4 publications

Robust bearing performance degradation assessment method based on improved wavelet packet–support vector data description

Robust bearing performance degradation assessment method based on improved wavelet packet–support vector data description

Bearing fault recognition method based on neighbourhood component analysis and coupled hidden Markov model

Signal Complexity and Gaussian Process Models Approach for Bearing Remaining Useful Life Estimation

Contact Info

Product

Resources

About