Multiple failure behaviors identification and remaining useful life prediction of ball bearings

Kundu, Pradeep; Chopra, S.; Lad, Bhupesh Kumar

doi:10.1007/s10845-017-1357-8

Cited by 48 publications

(22 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, if all these features have been taken as input parameters to the model, then it may result into model over-fitting. Thus, before using these features as input parameters to the model, it is desirable to select the most sensitive features from the feature set and remove the less indicative features to improve the model accuracy [44].…”

Section: Construction Of Bearing Degradation Indicator Setmentioning

confidence: 99%

An Ensemble Learning and RUL Prediction Method Based on Bearings Degradation Indicator Construction

Tian

Wang

2020

Applied Sciences

View full text Add to dashboard Cite

The prediction of the remaining life of a bearing plays a vital role in reducing the accident-related maintenance costs of machinery and in improving the reliability of machinery and equipment. To predict bearing remaining useful life (RUL), the abilities of statistical characteristics to reflect the bearing degradation state differ, and the single prediction model has low generalization ability and a poor prediction effect. An ensemble robust prediction method is proposed here to predict bearing RUL based on the construction of a bearing degradation indicator set: the initial bearing degradation indicator subsets were constructed using the Fast Correlation-Based Filter with Approximate Markov Blankets (FCBF-AMB) and Maximal Information Coefficient (MIC) selection methods. Through the cross-operation of the obtained subsets, we obtained a set of robust degradation indicators. These selected degradation indicators were fed into the long short-term memory (LSTM) neural network prediction model enhanced by the AdaBoost algorithm. We found through calculation that the average prediction accuracy of the proposed method is 91.40%, 92.04%, and 93.25% at 2100, 2250, and 2400 rpm, respectively. Compared with other methods, the proposed method improves the prediction accuracy by 1.8% to 14.87% at most. Therefore, the method proposed in this paper is more accurate than the other methods in terms of RUL prediction.

show abstract

Section: Construction Of Bearing Degradation Indicator Setmentioning

confidence: 99%

An Ensemble Learning and RUL Prediction Method Based on Bearings Degradation Indicator Construction

Tian

Wang

2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Time-domain analysis is based directly on the temporal waveform itself. The characteristics usually extracted from these signals are mean square root (RMS), peak value (PV), kurtosis (KT), and crest factor (CF) [ 32 , 33 ]. These statistical characteristics reveal the signal’s energy intensity, which may reveal a change of friction in CDFW.…”

Section: Vibration Signal Analysismentioning

confidence: 99%

Vibrations in CDFW

Alcântara

Balestrassi

Gomes

et al. 2020

Entropy

View full text Add to dashboard Cite

Continuous drive friction welding is a solid-state welding process that has been experimentally proven to be a fast and reliable method. This is a complex process; deformations in the viscosity of a material alter the friction between the surfaces of the pieces. All these dynamics cause changes in the vibration signals; the interpretation of these signals can reveal important information. The vibration signals generated during the friction and forging stages are measured on the stationary part of the structure to determine the influence of the manipulated variables on the time domain statistical characteristics (root mean square, peak value, crest factor, and kurtosis). In the frequency domain, empirical mode decomposition is used to characterize frequencies. It was observed that it is possible to identify the effects of the manipulated variables on the calculated statistical characteristics. The results also indicate that the effect of manipulated variables is stronger on low-frequency signals.

show abstract

“…These methods built the mapping from condition monitoring data to RUL values directly without prior knowledge. Some experiments show that the degradation process consists of gradual and sudden changes (Son et al, 2014;Kundu et al, 2019). The RUL prediction has to consider the degradation process of equipment in response to the uncertain influence of sudden changes, such as Zhang et al (2017).…”

Section: Introductionmentioning

confidence: 99%

A method for degradation prediction based on Hidden semi-Markov models with mixture of Kernels

Yang

Zheng

2020

Computers in Industry

View full text Add to dashboard Cite

Multiple failure behaviors identification and remaining useful life prediction of ball bearings

Cited by 48 publications

References 15 publications

An Ensemble Learning and RUL Prediction Method Based on Bearings Degradation Indicator Construction

An Ensemble Learning and RUL Prediction Method Based on Bearings Degradation Indicator Construction

Vibrations in CDFW

A method for degradation prediction based on Hidden semi-Markov models with mixture of Kernels

Contact Info

Product

Resources

About