Long Short-Term Memory Recurrent Neural Network for Remaining Useful Life Prediction of Lithium-Ion Batteries

By Yongzhi Zhang, Rui Xiong, Hongwen He, Michael G. Pecht. IEEE Transactions on Vehicular Technology, 2018

992 citations recorded by the source corpus.

Remaining useful life (RUL) prediction of lithium-ion batteries can assess the battery reliability to determine the advent of failure and mitigate battery risk. The existing RUL prediction techniques for lithium-ion batteries are inefficient for learning the long-term dependencies among the capacity degradations. This paper investigates deep-learning-enabled battery RUL prediction. The long short-term memory (LSTM) recurrent neural network (RNN) is employed to learn the long-term dependencies among the degraded capacities of lithium-ion batteries. The LSTM RNN is adaptively optimized using the resilient mean square back-propagation method, and a dropout technique is used to address the overfitting problem. The developed LSTM RNN is able to capture the underlying long-term dependencies among the degraded capacities and construct an explicitly capacity-oriented RUL predictor, whose long-term learning performance is contrasted to the support vector machine model, the particle filter model, and the simple RNN model. Monte Carlo simulation is combined to generate a probabilistic RUL prediction. Experimental data from multiple lithium-ion cells at two different temperatures is deployed for model construction, verification, and comparison. The developed method is able to predict the battery's RUL independent of offline training data, and when some offline data is available, the RUL can be predicted earlier than in the traditional methods.

Subfields: Automotive Engineering, Electrical and Electronic Engineering, Safety, Risk, Reliability and Quality

View Paper: https://www.semanticscholar.org/paper/648fff9d49c72bddc8271341f9bdea2d153b41c4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

In Electrical and Electronic Engineering

In Safety, Risk, Reliability and Quality

Citations in the corpus

Artificial Intelligence in Advanced Manufacturing: Current Status and Future Outlook (2020, positive): “[123] in which improved RUL estimation for the lithium-ion battery has been achieved using the LSTM-based approach.”
Online State-of-Health Estimation for Li-Ion Battery Using Partial Charging Segment Based on Support Vector Machine (2019, methodology): “Machine learning (ML) provides strong methodology for the establishment of a predictive model, of which the parameters can be built by neural network [32], Gaussian process regression [33], support vector machine (SVM) [34], et al.”
Transfer Learning With Long Short-Term Memory Network for State-of-Health Prediction of Lithium-Ion Batteries (2020, methodology): “Compared with the support vector machine, PF, and simple recurrent neural network, the LSTM could predict RUL more accurately and in advance.”
Transformer Network for Remaining Useful Life Prediction of Lithium-Ion Batteries (2022, positive): “To ensure safety, prediction of RUL in advance provides some key information about the maintenance and replacement of batteries [8]–[10].”