An enhanced encoder–decoder framework for bearing remaining useful life prediction

Liu, Lu; Song, Xiao; Chen, Kai; Hou, Baocun; Chai, Xudong; Ning, Huansheng

doi:10.1016/j.measurement.2020.108753

Cited by 38 publications

(21 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The termination criterion was only created by the acceleration signal exceeding the threshold. Similarly, the same criterion was defined as the end of bearing life in many other representative studies [7][8][9][10]. However, it was found in our experiments that under the same operating conditions, even if the same acceleration threshold is used as the test termination condition, the final damage degree, namely the crack length in the spall area, can be remarkably different.…”

Section: Introductionmentioning

confidence: 66%

“…To further reduce the error caused by feature fluctuations and to lower the influence of noise, exponential curve fitting is performed on the data before training the mathematical model for bearing RUL prediction [7,9]. The theoretical model is expressed as…”

Section: Feature Smoothingmentioning

confidence: 99%

“…Kundu [6] predicted the bearing RUL by establishing a Weibull proportional regression model based on the monitored signals of the PRONOSTIA platform. By combining the respective advantages of long-and short-term memory (LSTM) and statistical process analysis, Liu [7] proposed a new network to predict the bearing RUL using the datasets released by NASA and FEMTO-ST. Huang [8] introduced the transfer learning method and constructed a transfer depth-wise separable convolution recurrent network to predict the bearing RUL from the same public datasets considering different work conditions.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Bearing Remaining Useful Life Prediction Based on a Scaled Health Indicator and a LSTM Model with Attention Mechanism

et al. 2021

View full text Add to dashboard Cite

Rotor systems are of considerable importance in most modern industrial machinery, and the evaluation of the working conditions and longevity of their core component—the rolling bearing—has gained considerable research interest. In this study, a scale-normalized bearing health indicator based on the improved phase space warping (PSW) and hidden Markov model regression was established. This indicator was then used as the input for the encoder–decoder LSTM neural network with an attention mechanism to predict the rolling bearing RUL. Experiments show that compared with traditional health indicators such as kurtosis and root mean square (RMS), this scale-normalized bearing health indicator directly indicates the actual damage degree of the bearing, thereby enabling the LSTM model to predict RUL of the bearing more accurately.

show abstract

Section: Introductionmentioning

confidence: 66%

Section: Feature Smoothingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Bearing Remaining Useful Life Prediction Based on a Scaled Health Indicator and a LSTM Model with Attention Mechanism

et al. 2021

View full text Add to dashboard Cite

show abstract

“… Encoder-Decoder LSTM : Sequence-to-sequence prediction issues (seq2seq) are a more difficult form of problem in which a sequence is given as input and a sequence prediction is required as output. The Encoder-Decoder is made up of two sub-models: one that reads the input sequence and encodes it into a fixed-length vector, and the other that decodes the fixed-length vector and predicts the sequence ( Liu et al, 2021 ). The encoder is often a Vanilla LSTM model, although alternative encoder models such as Stacked, Bidirectional, and CNN models can also be utilized.…”

Section: Methodsmentioning

confidence: 99%

Deep learning-based anomaly-onset aware remaining useful life estimation of bearings

Kamat

Sugandhi

Kumar

2021

PeerJ Computer Science

View full text Add to dashboard Cite

Remaining Useful Life (RUL) estimation of rotating machinery based on their degradation data is vital for machine supervisors. Deep learning models are effective and popular methods for forecasting when rotating machinery such as bearings may malfunction and ultimately break down. During healthy functioning of the machinery, however, RUL is ill-defined. To address this issue, this study recommends using anomaly monitoring during both RUL estimator training and operation. Essential time-domain data is extracted from the raw bearing vibration data, and deep learning models are used to detect the onset of the anomaly. This further acts as a trigger for data-driven RUL estimation. The study employs an unsupervised clustering approach for anomaly trend analysis and a semi-supervised method for anomaly detection and RUL estimation. The novel combined deep learning-based anomaly-onset aware RUL estimation framework showed enhanced results on the benchmarked PRONOSTIA bearings dataset under non-varying operating conditions. The framework consisting of Autoencoder and Long Short Term Memory variants achieved an accuracy of over 90% in anomaly detection and RUL prediction. In the future, the framework can be deployed under varying operational situations using the transfer learning approach.

show abstract

“…However, in most cases, it is challenging to develop an accurate mathematical model for a specific bearing under different operating conditions. If the operating conditions of a bearing change, the prediction result of these approaches tends to be less accurate due to their poor adaptability [5].…”

Section: Introductionmentioning

confidence: 99%

GAN-LSTM Predictor for Failure Prognostics of Rolling Element Bearings

Lü

Barzegar

Nemani

et al. 2021

2021 IEEE International Conference on Prognostics and Health Management (ICPHM)

View full text Add to dashboard Cite

Failure prognostics is the process of predicting the remaining useful life (RUL) of machine components, which is vital for the predictive maintenance of industrial machinery. This paper presents a new deep learning approach for failure prognostics of rolling element bearings based on a Long Short-Term Memory (LSTM) predictor trained simultaneously within a Generative Adversarial Network (GAN) architecture. The LSTM predictor takes the current and past observations of a well-defined health index as an input, uses those to forecast the future degradation trajectory, and then derives the RUL. Our proposed approach has three unique features: (1) Defining the bearing failure threshold by adopting an International Organization of Standardization (ISO) standard, making the approach industryrelevant; (2) Employing a GAN-based data augmentation technique to improve the accuracy and robustness of RUL prediction in cases where the deep learning model has access to only a small amount of training data; (3) Integrating the training process of the LSTM predictor within the GAN architecture. A joint training approach is utilized to ensure that the LSTM predictor model learns both the original and artificially generated data to capture the degradation trajectories. We utilize a publicly available accelerated run-to-failure dataset of rolling element bearings to assess the performance of the proposed approach. Results of a five-fold cross-validation study show that the integration of the LSTM predictor with GAN helps to decrease the average RUL prediction error by 29% over a simple LSTM model without GAN implementation.

show abstract

An enhanced encoder–decoder framework for bearing remaining useful life prediction

Cited by 38 publications

References 31 publications

Bearing Remaining Useful Life Prediction Based on a Scaled Health Indicator and a LSTM Model with Attention Mechanism

Bearing Remaining Useful Life Prediction Based on a Scaled Health Indicator and a LSTM Model with Attention Mechanism

Deep learning-based anomaly-onset aware remaining useful life estimation of bearings

GAN-LSTM Predictor for Failure Prognostics of Rolling Element Bearings

Contact Info

Product

Resources

About