Remaining useful life prediction of bearing based on stacked autoencoder and recurrent neural network

Han, Tian; Pang, J. C.; Tan, Andy

doi:10.1016/j.jmsy.2021.10.011

Cited by 68 publications

(32 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is worth noting that, currently, studies on the bogie performance degradation of high-speed trains are starting to receive attention and are relatively scarce. Therefore, in this section, the state-of-the-art methods from other fields are also introduced for comparisons, such as methods TCNN [ 39 ], LSTM-AON [ 30 ], BiGRU [ 33 ], MDDNN [ 40 ], and SAE-LSTM [ 41 ] on bearing performance degradation estimation. The comparison results are shown in Figure 17 and Table 14 .…”

Section: Methodsmentioning

confidence: 99%

Performance Degradation Estimation of High-Speed Train Bogie Based on 1D-ConvLSTM Time-Distributed Convolutional Neural Network

Ren

Jin²,

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

High-speed train bogies are essential for the safety and comfort of train operation. The performance of the bogie usually degrades before it fails, so it is necessary to detect the performance degradation of a high-speed train bogie in advance. In this paper, with two key dampers on the bogie taken as experimental objects (lateral damper and yaw damper), a novel 1D-ConvLSTM time-distributed convolutional neural network (CLTD-CNN) is proposed to estimate the performance degradation of a high-speed train bogie. The proposed CLTD-CNN is an encoder-decoder structure. Specifically, the encoder part of the proposed structure consists of a time-distributed 1D-CNN module and a 1D-ConvLSTM. The decoder part consists of a 1D-ConvLSTM and a simple time-CNN with residual connections. In addition, an auxiliary training part is introduced into the structure to support CLTD-CNN in learning the performance degradation trend characteristic, and a special input format is designed for this structure. The whole structure is end-to-end and does not require expert knowledge or engineering experience. The effectiveness of the proposed CLTD-CNN is tested by the high-speed train CRH380A under different performance states. The experimental results demonstrate the superiority of CLTD-CNN. Compared to other methods, the estimation error of CLTD-CNN is the smallest.

show abstract

Section: Methodsmentioning

confidence: 99%

Performance Degradation Estimation of High-Speed Train Bogie Based on 1D-ConvLSTM Time-Distributed Convolutional Neural Network

Ren

Jin²,

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…The sampling frequency of the acceleration sensor is 25.6 kHz. When the test platform starts to work, the vibration signal is recorded every 10 s, and the sampling time is 0.1 s [43].…”

Section: Dataset Descriptionmentioning

confidence: 99%

“…Zhang et al [42] extracted signal time-domain, frequency-domain, and time-frequency-domain correlation features and defined metrics such as monotonicity for feature selection based on the trend and residuals of the features. Tian et al extracted 10 features of bearing vibration signals and used the monotonicity index to screen good features as input to the neural network [43].…”

Section: Input Selectionmentioning

confidence: 99%

Advances in Bearing Lubrication and Thermal Sciences

2022

View full text Add to dashboard Cite

show abstract

“…Applied to the challenge of RUL prediction, these are approaches to automatically draw conclusions about the RUL from the data measured at the component. Among the machine learning algorithms used for RUL predictions there are different variants of neural networks, such as convolutional neural networks (CNN) [6], recurrent neural networks (RNN) [7], long short-term memory (LSTM) [8], and generative adversarial networks (GAN) [9]. Furthermore, there are contributions to state detection using random forest algorithms [10].…”

Section: Introductionmentioning

confidence: 99%

On the Importance of Temporal Information for Remaining Useful Life Prediction of Rolling Bearings Using a Random Forest Regressor

et al. 2022

View full text Add to dashboard Cite

Rolling bearings are frequently subjected to high stresses within modern machines. To prevent bearing failures, the topics of condition monitoring and predictive maintenance have become increasingly relevant. In order to efficiently and reliably maintain rolling bearings in a predictive manner, an estimate of the remaining useful life (RUL) is of great interest. The RUL prediction quality achieved when using machine learning depends not only on the selection of the sensor data used for condition monitoring, but also on its preprocessing. In particular, the execution of so-called feature engineering has a major impact on prediction quality. Therefore, in this paper, various methods of feature engineering are presented based on rolling–bearing endurance tests and recorded structure-borne sound signals. The performance of these methods is evaluated in the context of a regression-based RUL model. Furthermore, the way in which the quality of RUL prediction can be significantly improved is demonstrated, by adding further processed, time-considering features.

show abstract

Remaining useful life prediction of bearing based on stacked autoencoder and recurrent neural network

Cited by 68 publications

References 22 publications

Performance Degradation Estimation of High-Speed Train Bogie Based on 1D-ConvLSTM Time-Distributed Convolutional Neural Network

Performance Degradation Estimation of High-Speed Train Bogie Based on 1D-ConvLSTM Time-Distributed Convolutional Neural Network

Advances in Bearing Lubrication and Thermal Sciences

On the Importance of Temporal Information for Remaining Useful Life Prediction of Rolling Bearings Using a Random Forest Regressor

Contact Info

Product

Resources

About