A SVR-Based Remaining Life Prediction for Rolling Element Bearings

Wang, Xiaolin; Gu, Haoran; Xu, Liyun; Chen, Hu; Guo, Hui

doi:10.1007/s11668-015-9976-x

Cited by 13 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It establishes ML models by learning from past experimental data and existing knowledge for prediction [19]. ML-based methods achieved satisfactory results in RUL prediction, including support vector regression model (SVR) [20], multi-layer perceptron (MLP) [21], convolutional neural network (CNN) [22,23], recurrent neural network (RNN) [24,25], etc. In terms of input, the ML-based method can take the original output data and state information of PVS as input, preventing the error from the sensitivity calculation process and ignoring the assumptions in the statistical data-driven method.…”

Section: Introductionmentioning

confidence: 99%

RUL Prediction for Piezoelectric Vibration Sensors Based on Digital-Twin and LSTM Network

Fu,

Gao,

Zhang

2024

Mathematics

View full text Add to dashboard Cite

Piezoelectric vibration sensors (PVSs) are widely used in high-temperature environments, such as vibration measurements in aero-engines, because of their high accuracy, small size, and high temperature resistance. Accurate prediction of its RUL (Remaining Useful Life) is essential for applying and maintaining PVSs. Based on PVSs’ characteristics and main failure modes, this work combines the Digital-Twin (DT) and Long Short-Term Memory (LSTM) networks to predict the RUL of PVSs. In this framework, DT can provide rich data collection, analysis, and simulation capabilities, which have advantages in RUL prediction, and LSTM network has good results in predicting time sequence data. The proposed method exploits the advantages of those techniques in feature data collection, sample optimization, and RUL multiclassification. To verify the prediction of this method, a DT platform is established to conduct PVS degradation tests, which generates sample datasets, then the LSTM network is trained and validated. It has been proved that prediction accuracy is more than 99.7%, and training time is within 94 s. Based on this network, the RUL of PVSs is predicted using different test samples. The results show that the method performed well in prediction accuracy, sample data utilization, and compatibility.

show abstract

Section: Introductionmentioning

confidence: 99%

RUL Prediction for Piezoelectric Vibration Sensors Based on Digital-Twin and LSTM Network

Fu,

Gao,

Zhang

2024

Mathematics

View full text Add to dashboard Cite

show abstract

“…Wang et al used two novel mixed effects models to predict the performance of rolling element bearings [19]. Zhang et al used SVR to achieve bearing remaining life prediction [20]. Ling et al used Improved Empirical Wavelet Transform-Least Square Support Vector Machine (IEWT-LSSVM) and bird swarm algorithm to predict wind speed [21].…”

Section: Introductionmentioning

confidence: 99%

HKF-SVR Optimized by Krill Herd Algorithm for Coaxial Bearings Performance Degradation Prediction

Liu

et al. 2020

Sensors

View full text Add to dashboard Cite

In real industrial applications, bearings in pairs or even more are often mounted on the same shaft. So the collected vibration signal is actually a mixed signal from multiple bearings. In this study, a method based on Hybrid Kernel Function-Support Vector Regression (HKF–SVR) whose parameters are optimized by Krill Herd (KH) algorithm was introduced for bearing performance degradation prediction in this situation. First, multi-domain statistical features are extracted from the bearing vibration signals and then fused into sensitive features using Kernel Joint Approximate Diagonalization of Eigen-matrices (KJADE) algorithm which is developed recently by our group. Due to the nonlinear mapping capability of the kernel method and the blind source separation ability of the JADE algorithm, the KJADE could extract latent source features that accurately reflecting the performance degradation from the mixed vibration signal. Then, the between-class and within-class scatters (SS) of the health-stage data sample and the current monitored data sample is calculated as the performance degradation index. Second, the parameters of the HKF–SVR are optimized by the KH (Krill Herd) algorithm to obtain the optimal performance degradation prediction model. Finally, the performance degradation trend of the bearing is predicted using the optimized HKF–SVR. Compared with the traditional methods of Back Propagation Neural Network (BPNN), Extreme Learning Machine (ELM) and traditional SVR, the results show that the proposed method has a better performance. The proposed method has a good application prospect in life prediction of coaxial bearings.

show abstract

“…Caesarendra et al (2017) applied multivariate state estimation technique (MSET), sequential probability ratio test (SPRT) and kernel regression to condition monitoring and prognosis of low speed bearing. Support vector regression (SVR) algorithm and specific indicator are linked (Wang et al, 2015) to construct adaptive prediction model, improving predicted results of rolling bearings. Lu et al (2016) utilized a novel prediction method based on least squares support vector machine (LSSVM) to estimate the slewing bearing’s degradation trend with small sample data and improved the prediction accuracy of slewing bearing.…”

Section: Introductionmentioning

confidence: 99%

Life prediction of slewing bearing based on isometric mapping and fuzzy support vector regression

Bao

Wang

Chen

et al. 2019

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

The monitoring data of slewing bearing is massive. In order to establish accurate life prediction model from complex vibration signal of slewing bearing, a life prediction method based on manifold learning and fuzzy support vector regression (SVR) is proposed. Firstly, the multiple features are extracted from time domain and time-frequency domain. Then isometric mapping (ISOMAP) is used to reduce high-dimensional features to low-dimensional features that can reflect degeneration of slewing bearing well. Finally, the fuzzy SVR is used to predict the life degradation trend of slewing bearing. The results show that: (1) Multi-feature fusion after ISOMAP can obtain more comprehensive degradation indicator. (2) The complexity of the life prediction model is simplified and the real-time life degradation trend of slewing bearing can be well predicted by fuzzy SVR, so it is very suitable to predict life degradation trend of slewing bearing based on massive data well. The time of prediction on average is reduced by 72.7%. The mean absolute error (MAE) and root mean square error (RMSE) of prediction are reduced by 73% and 59% respectively compared with traditional methods. The accuracy of prediction is greatly improved.

show abstract

A SVR-Based Remaining Life Prediction for Rolling Element Bearings

Cited by 13 publications

References 10 publications

RUL Prediction for Piezoelectric Vibration Sensors Based on Digital-Twin and LSTM Network

RUL Prediction for Piezoelectric Vibration Sensors Based on Digital-Twin and LSTM Network

HKF-SVR Optimized by Krill Herd Algorithm for Coaxial Bearings Performance Degradation Prediction

Life prediction of slewing bearing based on isometric mapping and fuzzy support vector regression

Contact Info

Product

Resources

About