A novel methodology for online detection of bearing health status for naturally progressing defect

Shakya, Piyush; Kulkarni, Makarand S.; Darpe, Ashish K.

doi:10.1016/j.jsv.2014.04.058

Cited by 54 publications

(34 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, investigations related to naturally induced and naturally progressed defects of REBs are relatively scarce. In fact, online detection of REB degradation for naturally progressing defect in damage stages is not available in the literature (Shakya et al, 2014). Recently, some approaches have been proposed for the online bearing health monitoring.…”

Section: Several Efforts Based On Vibration Signals Have Been Recentlmentioning

confidence: 99%

“…In (Pan et al, 2014), the authors have proposed a new approach based on dynamic fuzzy neural networks where only consequent parameters were updated online. In (Shakya et al, 2014), various damage stages for naturally progressing REB defect were given online. For this, time domain, frequency domain and time-frequency domain were together under study.…”

Section: Several Efforts Based On Vibration Signals Have Been Recentlmentioning

confidence: 99%

See 1 more Smart Citation

Linear feature selection and classification using PNN and SFAM neural networks for a nearly online diagnosis of bearing naturally progressing degradations

Ali

Saïdi

Mouelhi

et al. 2015

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

In this work, an effort is made to characterize seven bearing states depending on the energy entropy of Intrinsic Mode Functions (IMFs) resulted from the Empirical Modes Decomposition (EMD). Three run-to-failure bearing vibration signals representing different defects either degraded or different failing components (roller, inner race and outer race) with healthy state lead to seven bearing states under study. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) are used for feature reduction. Then, six classification scenarios are processed via a Probabilistic Neural Network (PNN) and a Simplified Fuzzy Adaptive resonance theory Map (SFAM) neural network. In other words, the three extracted feature data bases (EMD, PCA and LDA features) are processed firstly with SFAM and secondly with a combination of PNN-SFAM. The computation of classification accuracy and scattering criterion for each scenario shows that the EMD-LDA-PNN-SFAM combination is the suitable strategy for online bearing fault diagnosis. The proposed methodology reveals better generalization capability compared to previous works and it's validated by an online bearing fault diagnosis. The proposed strategy can be applied for the decision making of several assets.

show abstract

Section: Several Efforts Based On Vibration Signals Have Been Recentlmentioning

confidence: 99%

Section: Several Efforts Based On Vibration Signals Have Been Recentlmentioning

confidence: 99%

Linear feature selection and classification using PNN and SFAM neural networks for a nearly online diagnosis of bearing naturally progressing degradations

Ali

Saïdi

Mouelhi

et al. 2015

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Recently Mahalanobis distance was successfully applied in damage evolution: e.g. crack in concrete [15], naturally progressing defect in bearing [16]. In this paper the relationships between the THz measurement results for different stages of composite samples will be presented using those two distances.…”

Section: Mahalanobis Distancementioning

confidence: 99%

Heat induced damage detection in composite materials by terahertz radiation

et al. 2015

View full text Add to dashboard Cite

In recent years electromagnetic Terahertz (THz) radiation or T-ray has been increasingly used for nondestructive evaluation of various materials such as polymer composites and porous foam tiles in which ultrasonic waves cannot penetrate but T-ray can. Most of these investigations have been limited to mechanical damage detection like inclusions, cracks, delaminations etc. So far only a few investigations have been reported on heat induced damage detection. Unlike mechanical damage the heat induced damage does not have a clear interface between the damaged part and the surrounding intact material from which electromagnetic waves can be reflected back. Difficulties associated with the heat induced damage detection in composite materials using T-ray are discussed in detail in this paper. T-ray measurements are compared for different levels of heat exposure of composite specimens.

show abstract

“…Different methods have been proposed to determine the FPT, such as the engineering norm ISO 10816 based approach [16] and the system's longest time constant based approach [22]. The 3σ approach has been widely used in FPT selection [10], [23], [24], one advantage is that the alarm, which is used to determine the FPT, can be set adaptively according to the HI behavior of bearings. Therefore, the 3σ approach is adopted here to select the FPT based on the new developed HI, i.e., RMS-MAVE.…”

Section: Introductionmentioning

confidence: 99%

Remaining Useful Life Prediction of Rolling Bearings Based on RMS-MAVE and Dynamic Exponential Regression Model

Kong

Yang

2019

IEEE Access

View full text Add to dashboard Cite

The remaining useful life (RUL) prediction of rolling bearings has recently gained increasing interest. Many models have been established to catch the degradation performance of bearings. However, there are two shortcomings existing in those models: (1) the health indicator (HI) that used for the first predicting time (FPT) selection is insensitive to incipient faults; (2) the parameter estimation must be based on the historical data, which are not available for some applications due to expensive experiment cost. To overcome the first shortcoming, this paper firstly adopts the mean absolute value of extremums (MAVE) of signals to feature signal energy. Then, the root mean square of the MAVE values (RMS-MAVE) is developed as a new HI to embody signal changes. After that, based on RMS-MAVE values, an adaptive FPT selection approach is proposed by the 3σ approach. For the second shortcoming, through coupling acquired measurement data with the exponential model, a dynamic exponential regression (DER) model based on RMS-MAVE values is proposed to predict the RUL of bearings. The comparison study indicates that RMS-MAVE is superior to the existed ones in FPT selection for distinguishing different health state of bearings, and the DER model performs better than the existed ones in RUL prediction. INDEX TERMS Remaining useful life, rolling bearings, first predicting time, root mean square, the mean absolute value of extremums, dynamic exponential regression model.

show abstract

A novel methodology for online detection of bearing health status for naturally progressing defect

Cited by 54 publications

References 19 publications

Linear feature selection and classification using PNN and SFAM neural networks for a nearly online diagnosis of bearing naturally progressing degradations

Linear feature selection and classification using PNN and SFAM neural networks for a nearly online diagnosis of bearing naturally progressing degradations

Heat induced damage detection in composite materials by terahertz radiation

Remaining Useful Life Prediction of Rolling Bearings Based on RMS-MAVE and Dynamic Exponential Regression Model

Contact Info

Product

Resources

About