Remaining Useful Life Prediction Method for Bearings Based on LSTM with Uncertainty Quantification

Abstract

To reduce the economic losses caused by bearing failures and prevent safety accidents, it is necessary to develop an effective method to predict the remaining useful life (RUL) of the rolling bearing. However, the degradation inside the bearing is difficult to monitor in real-time. Meanwhile, external uncertainties significantly impact bearing degradation. Therefore, this paper proposes a new bearing RUL prediction method based on long-short term memory (LSTM) with uncertainty quantification. First, a fusion metric related to runtime (or degradation) is proposed to reflect the latent degradation process. Then, an improved dropout method based on nonparametric kernel density is developed to improve estimation accuracy of RUL. The PHM2012 dataset is adopted to verify the proposed method, and comparison results illustrate that the proposed prediction model can accurately obtain the point estimation and probability distribution of the bearing RUL.

Remaining useful life prediction for space bearing with cage friction fault based on data pre-screening and gated recurrent unit

“…This phenomenon is due to the fact that the intermittent impact and wear of the space cage are usually accompanied by strong fluctuation in characteristic parameters, resulting in the inaccurate prediction of RUL. The data pre-screening method based on SAE-K-medoids proposed in 15.49% 0.8670 317.9 1.3662 GRU [45] 35.32% 0.9466 147.9 0.7041 LSTM [46] 29.41% 0.9291 172.9 0.7669 Proposed approach −1.97% 0.9885 21.9 0.1106 this paper can effectively eliminate volatility and significantly improve subsequent prediction accuracy. By comparing the proposed method with cases 2, 4, 6 and 8, it can be observed that changing the type of NN can also improve prediction accuracy under the same pre-processing conditions.…”

“…To further validate the proposed method, it is compared with some RUL prediction models developed in recent five years [23,45,46]. Use different methods to analyze the test data, and the results are shown in table 12.…”

Long Short-Term Memory Neural Network with Transfer Learning and Ensemble Learning for Remaining Useful Life Prediction

“…Lei et al [ 7 ] utilized a multi-scale dense-gate recurrent neural network to identify relevant information at different timescales to improve the performance of model. Yang et al [ 8 ] proposed an improved long-short term memory neural network to estimate bearing performance degradation. In [ 9 ], a hybrid model based on long short-term memory and Elman neural networks predicted RUL for lithium-ion batteries.…”

A Hybrid Prognostic Method for Proton-Exchange-Membrane Fuel Cell with Decomposition Forecasting Framework Based on AEKF and LSTM

“…To extend the fuel-cell lifetime and reduce its maintenance cost, the management and control strategy of the PEMFC has become a hot research topic. The prognostic method provides a potential solution to extending the PEMFC lifespan [ 11 , 12 ]. As the prerequisite for the maintenance of PEMFC, an effective prognostic method can estimate the state of health (SOH) of the fuel cell and predict the system’s future evolution.…”

“…Ma et al [ 25 ] adopted a long short-term memory network (LSTM) to predict the degradation voltage, which identified the superiority of the LSTM network compared with the relevance vector machine (RVM) and the Elman network. Yang et al [ 12 ] proposed an RUL prediction method for the bearing’s degradation process based on LSTM. However, the data-based method suffers from poor generality in practical deployment and there is a shortage of training data because of the costly and time-consuming PEMFC aging test.…”