Generalized real-time state of health estimation for lithium-ion batteries using simulation-augmented multi-objective dual-stream fusion of multi-Bi-LSTM-attention

To maintain the safe and reliable operation of lithium-ion batteries and manage their timely replacement, accurate state of health (SOH) estimation is critically important. This paper presents a novel deep-learning framework based on multi-loss optimized dual stream fusion of attention integrated mu...

Full description

Saved in:
Bibliographic Details
Main Authors: Jarin Tasnim, Md. Azizur Rahman, Md. Shoaib Akhter Rafi, Muhammad Anisuzzaman Talukder, Md. Kamrul Hasan
Format: Article
Language:English
Published: Elsevier 2025-03-01
Series:e-Prime: Advances in Electrical Engineering, Electronics and Energy
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772671124004479
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846124893149593600
author Jarin Tasnim
Md. Azizur Rahman
Md. Shoaib Akhter Rafi
Muhammad Anisuzzaman Talukder
Md. Kamrul Hasan
author_facet Jarin Tasnim
Md. Azizur Rahman
Md. Shoaib Akhter Rafi
Muhammad Anisuzzaman Talukder
Md. Kamrul Hasan
author_sort Jarin Tasnim
collection DOAJ
description To maintain the safe and reliable operation of lithium-ion batteries and manage their timely replacement, accurate state of health (SOH) estimation is critically important. This paper presents a novel deep-learning framework based on multi-loss optimized dual stream fusion of attention integrated multi-Bi-LSTM networks (multi-ABi-LSTM), for generalized real-time SOH estimation of lithium-ion batteries. Battery sensor data is first preprocessed utilizing novel energy discrepancy aware variable cycle length synchronization and grid encoding schemes to achieve generalizability considering battery sets with different discharge profiles and then passed through two parallel networks: overlapped data splitting (ODS)-based attention integrated multi-Bi-LSTM network (ODS-multi-ABi-LSTM) and past cycles’ SOHs (PCSs)-based attention integrated multi-Bi-LSTM (PCS-multi-ABi-LSTM) network. The complementary features extracted from these two networks are effectively combined by a proposed fusion network to achieve high SOH estimation accuracy. Furthermore, a lithium-ion battery simulation model is employed for data augmentation during training, enhancing the generalizability of the proposed data-driven model. The suggested technique outperforms previous methods by a remarkable margin achieving 0.716% MAPE, 0.005 MAE, 0.653% RMSE, and 0.992 R2 on a combined dataset consisting of four different battery sets with varying specifications and discharge profiles, indicating its generalization capability. Appliances using lithium-ion batteries can adopt the proposed SOH prediction framework to predict battery health conditions in real-time, ensuring operational safety and reliability.
format Article
id doaj-art-36619672d66847d08c86a6694f614eab
institution Kabale University
issn 2772-6711
language English
publishDate 2025-03-01
publisher Elsevier
record_format Article
series e-Prime: Advances in Electrical Engineering, Electronics and Energy
spelling doaj-art-36619672d66847d08c86a6694f614eab2024-12-13T11:08:42ZengElseviere-Prime: Advances in Electrical Engineering, Electronics and Energy2772-67112025-03-0111100870Generalized real-time state of health estimation for lithium-ion batteries using simulation-augmented multi-objective dual-stream fusion of multi-Bi-LSTM-attentionJarin Tasnim0Md. Azizur Rahman1Md. Shoaib Akhter Rafi2Muhammad Anisuzzaman Talukder3Md. Kamrul Hasan4Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology (BUET), Dhaka, 1205, BangladeshDepartment of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology (BUET), Dhaka, 1205, BangladeshDepartment of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology (BUET), Dhaka, 1205, BangladeshDepartment of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology (BUET), Dhaka, 1205, BangladeshCorresponding author.; Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology (BUET), Dhaka, 1205, BangladeshTo maintain the safe and reliable operation of lithium-ion batteries and manage their timely replacement, accurate state of health (SOH) estimation is critically important. This paper presents a novel deep-learning framework based on multi-loss optimized dual stream fusion of attention integrated multi-Bi-LSTM networks (multi-ABi-LSTM), for generalized real-time SOH estimation of lithium-ion batteries. Battery sensor data is first preprocessed utilizing novel energy discrepancy aware variable cycle length synchronization and grid encoding schemes to achieve generalizability considering battery sets with different discharge profiles and then passed through two parallel networks: overlapped data splitting (ODS)-based attention integrated multi-Bi-LSTM network (ODS-multi-ABi-LSTM) and past cycles’ SOHs (PCSs)-based attention integrated multi-Bi-LSTM (PCS-multi-ABi-LSTM) network. The complementary features extracted from these two networks are effectively combined by a proposed fusion network to achieve high SOH estimation accuracy. Furthermore, a lithium-ion battery simulation model is employed for data augmentation during training, enhancing the generalizability of the proposed data-driven model. The suggested technique outperforms previous methods by a remarkable margin achieving 0.716% MAPE, 0.005 MAE, 0.653% RMSE, and 0.992 R2 on a combined dataset consisting of four different battery sets with varying specifications and discharge profiles, indicating its generalization capability. Appliances using lithium-ion batteries can adopt the proposed SOH prediction framework to predict battery health conditions in real-time, ensuring operational safety and reliability.http://www.sciencedirect.com/science/article/pii/S2772671124004479Lithium-ion batteriesState of healthEnergy discrepancy aware preprocessingOverlapped data splittingSimulation modelAttention guided multi-Bi-LSTM
spellingShingle Jarin Tasnim
Md. Azizur Rahman
Md. Shoaib Akhter Rafi
Muhammad Anisuzzaman Talukder
Md. Kamrul Hasan
Generalized real-time state of health estimation for lithium-ion batteries using simulation-augmented multi-objective dual-stream fusion of multi-Bi-LSTM-attention
e-Prime: Advances in Electrical Engineering, Electronics and Energy
Lithium-ion batteries
State of health
Energy discrepancy aware preprocessing
Overlapped data splitting
Simulation model
Attention guided multi-Bi-LSTM
title Generalized real-time state of health estimation for lithium-ion batteries using simulation-augmented multi-objective dual-stream fusion of multi-Bi-LSTM-attention
title_full Generalized real-time state of health estimation for lithium-ion batteries using simulation-augmented multi-objective dual-stream fusion of multi-Bi-LSTM-attention
title_fullStr Generalized real-time state of health estimation for lithium-ion batteries using simulation-augmented multi-objective dual-stream fusion of multi-Bi-LSTM-attention
title_full_unstemmed Generalized real-time state of health estimation for lithium-ion batteries using simulation-augmented multi-objective dual-stream fusion of multi-Bi-LSTM-attention
title_short Generalized real-time state of health estimation for lithium-ion batteries using simulation-augmented multi-objective dual-stream fusion of multi-Bi-LSTM-attention
title_sort generalized real time state of health estimation for lithium ion batteries using simulation augmented multi objective dual stream fusion of multi bi lstm attention
topic Lithium-ion batteries
State of health
Energy discrepancy aware preprocessing
Overlapped data splitting
Simulation model
Attention guided multi-Bi-LSTM
url http://www.sciencedirect.com/science/article/pii/S2772671124004479
work_keys_str_mv AT jarintasnim generalizedrealtimestateofhealthestimationforlithiumionbatteriesusingsimulationaugmentedmultiobjectivedualstreamfusionofmultibilstmattention
AT mdazizurrahman generalizedrealtimestateofhealthestimationforlithiumionbatteriesusingsimulationaugmentedmultiobjectivedualstreamfusionofmultibilstmattention
AT mdshoaibakhterrafi generalizedrealtimestateofhealthestimationforlithiumionbatteriesusingsimulationaugmentedmultiobjectivedualstreamfusionofmultibilstmattention
AT muhammadanisuzzamantalukder generalizedrealtimestateofhealthestimationforlithiumionbatteriesusingsimulationaugmentedmultiobjectivedualstreamfusionofmultibilstmattention
AT mdkamrulhasan generalizedrealtimestateofhealthestimationforlithiumionbatteriesusingsimulationaugmentedmultiobjectivedualstreamfusionofmultibilstmattention