Cover Image

Gravitational Search Algorithm based Long Short-term Memory Deep Neural Network for Battery Capacity and Remaining Useful Life Prediction with Uncertainty

This paper presents a hybrid approach for predicting the remaining useful life (RUL) and future capacity of lithium-ion batteries (LIBs) using an improved long short-term memory (LSTM) deep neural network with a gravitational search algorithm (GSA). The proposed method address the challenges of nonl...

Full description

Saved in:
Bibliographic Details
Main Authors: Reza M.S., Hannan M.A., Mansor M., Ker P.J., Tiong S.K., Hossain M.J.
Other Authors: 59055914200
Format: Conference Paper
Published: Institute of Electrical and Electronics Engineers Inc. 2024
Subjects:
capacity prediction
deep neural network
gravitational search algorithm
lithium-ion batteries
long short-term memory
remaining useful life
Brain
Digital storage
Forecasting
Learning algorithms
Lithium-ion batteries
Long short-term memory
NASA
Uncertainty analysis
Battery capacity
Capacity prediction
Dynamic battery
Gravitational search algorithm
Hybrid approach
Hyper-parameter
Remaining useful life predictions
Remaining useful lives
Search Algorithms
Uncertainty
Deep neural networks
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uniten.dspace-34430
record_format dspace
spelling my.uniten.dspace-344302024-10-14T11:19:44Z Gravitational Search Algorithm based Long Short-term Memory Deep Neural Network for Battery Capacity and Remaining Useful Life Prediction with Uncertainty Reza M.S. Hannan M.A. Mansor M. Ker P.J. Tiong S.K. Hossain M.J. 59055914200 7103014445 6701749037 37461740800 15128307800 57209871691 capacity prediction deep neural network gravitational search algorithm lithium-ion batteries long short-term memory remaining useful life Brain Digital storage Forecasting Learning algorithms Lithium-ion batteries Long short-term memory NASA Uncertainty analysis Battery capacity Capacity prediction Dynamic battery Gravitational search algorithm Hybrid approach Hyper-parameter Remaining useful life predictions Remaining useful lives Search Algorithms Uncertainty Deep neural networks This paper presents a hybrid approach for predicting the remaining useful life (RUL) and future capacity of lithium-ion batteries (LIBs) using an improved long short-term memory (LSTM) deep neural network with a gravitational search algorithm (GSA). The proposed method address the challenges of nonlinear and dynamic battery behavior, battery aging uncertainty, the requirement for optimal hyperparameters tuning, and the importance of maintaining safe and efficient battery operation. The RUL prediction uncertainty with a 95% confidence interval (CI) is also analyzed. The GSA algorithm optimizes the hyperparameters of the LSTM network to construct an optimal model. The method proposed in this work is evaluated based on the aging data from the NASA battery dataset, and its effectiveness is compared with that of BiLSTM, baseline gated recurrent unit (GRU), and baseline LSTM using various error metrics. The results demonstrate that the LSTM-GSA model outperforms other methods in the context of prediction accuracy, achieving a minimum RMSE of 1.04% and 1.15% for both battery cases. Overall, this research provides a promising solution for predicting RUL and the future capacity of LIBs with uncertainty, which is essential for ensuring the safe and efficient operation of energy storage systems. � 2023 IEEE. Final 2024-10-14T03:19:44Z 2024-10-14T03:19:44Z 2023 Conference Paper 10.1109/ETFG55873.2023.10407732 2-s2.0-85185784877 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85185784877&doi=10.1109%2fETFG55873.2023.10407732&partnerID=40&md5=1358008c9b46f5df44c2ee65a675b4c2 https://irepository.uniten.edu.my/handle/123456789/34430 Institute of Electrical and Electronics Engineers Inc. Scopus
institution Universiti Tenaga Nasional
building UNITEN Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Tenaga Nasional
content_source UNITEN Institutional Repository
url_provider http://dspace.uniten.edu.my/
topic capacity prediction
deep neural network
gravitational search algorithm
lithium-ion batteries
long short-term memory
remaining useful life
Brain
Digital storage
Forecasting
Learning algorithms
Lithium-ion batteries
Long short-term memory
NASA
Uncertainty analysis
Battery capacity
Capacity prediction
Dynamic battery
Gravitational search algorithm
Hybrid approach
Hyper-parameter
Remaining useful life predictions
Remaining useful lives
Search Algorithms
Uncertainty
Deep neural networks
spellingShingle capacity prediction
deep neural network
gravitational search algorithm
lithium-ion batteries
long short-term memory
remaining useful life
Brain
Digital storage
Forecasting
Learning algorithms
Lithium-ion batteries
Long short-term memory
NASA
Uncertainty analysis
Battery capacity
Capacity prediction
Dynamic battery
Gravitational search algorithm
Hybrid approach
Hyper-parameter
Remaining useful life predictions
Remaining useful lives
Search Algorithms
Uncertainty
Deep neural networks
Reza M.S.
Hannan M.A.
Mansor M.
Ker P.J.
Tiong S.K.
Hossain M.J.
Gravitational Search Algorithm based Long Short-term Memory Deep Neural Network for Battery Capacity and Remaining Useful Life Prediction with Uncertainty
description This paper presents a hybrid approach for predicting the remaining useful life (RUL) and future capacity of lithium-ion batteries (LIBs) using an improved long short-term memory (LSTM) deep neural network with a gravitational search algorithm (GSA). The proposed method address the challenges of nonlinear and dynamic battery behavior, battery aging uncertainty, the requirement for optimal hyperparameters tuning, and the importance of maintaining safe and efficient battery operation. The RUL prediction uncertainty with a 95% confidence interval (CI) is also analyzed. The GSA algorithm optimizes the hyperparameters of the LSTM network to construct an optimal model. The method proposed in this work is evaluated based on the aging data from the NASA battery dataset, and its effectiveness is compared with that of BiLSTM, baseline gated recurrent unit (GRU), and baseline LSTM using various error metrics. The results demonstrate that the LSTM-GSA model outperforms other methods in the context of prediction accuracy, achieving a minimum RMSE of 1.04% and 1.15% for both battery cases. Overall, this research provides a promising solution for predicting RUL and the future capacity of LIBs with uncertainty, which is essential for ensuring the safe and efficient operation of energy storage systems. � 2023 IEEE.
author2 59055914200
author_facet 59055914200
Reza M.S.
Hannan M.A.
Mansor M.
Ker P.J.
Tiong S.K.
Hossain M.J.
format Conference Paper
author Reza M.S.
Hannan M.A.
Mansor M.
Ker P.J.
Tiong S.K.
Hossain M.J.
author_sort Reza M.S.
title Gravitational Search Algorithm based Long Short-term Memory Deep Neural Network for Battery Capacity and Remaining Useful Life Prediction with Uncertainty
title_short Gravitational Search Algorithm based Long Short-term Memory Deep Neural Network for Battery Capacity and Remaining Useful Life Prediction with Uncertainty
title_full Gravitational Search Algorithm based Long Short-term Memory Deep Neural Network for Battery Capacity and Remaining Useful Life Prediction with Uncertainty
title_fullStr Gravitational Search Algorithm based Long Short-term Memory Deep Neural Network for Battery Capacity and Remaining Useful Life Prediction with Uncertainty
title_full_unstemmed Gravitational Search Algorithm based Long Short-term Memory Deep Neural Network for Battery Capacity and Remaining Useful Life Prediction with Uncertainty
title_sort gravitational search algorithm based long short-term memory deep neural network for battery capacity and remaining useful life prediction with uncertainty
publisher Institute of Electrical and Electronics Engineers Inc.
publishDate 2024
_version_ 1814060095174082560
score 13.209306

Similar Items