A Novel Real-Time Battery State Estimation Using Data-Driven Prognostics and Health Management

This paper presents a novel data-driven framework for real-time State of Charge (SOC) estimation in lithium-ion battery systems using a data-driven Prognostics and Health Management (PHM) approach. The method leverages an optimized bidirectional Long Short-Term Memory (Bi-LSTM) network, trained with...

Full description

Saved in:
Bibliographic Details
Main Authors: Juliano Pimentel, Alistair A. McEwan, Hong Qing Yu
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/15/8538
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849407545673777152
author Juliano Pimentel
Alistair A. McEwan
Hong Qing Yu
author_facet Juliano Pimentel
Alistair A. McEwan
Hong Qing Yu
author_sort Juliano Pimentel
collection DOAJ
description This paper presents a novel data-driven framework for real-time State of Charge (SOC) estimation in lithium-ion battery systems using a data-driven Prognostics and Health Management (PHM) approach. The method leverages an optimized bidirectional Long Short-Term Memory (Bi-LSTM) network, trained with enhanced datasets filtered via exponentially weighted moving averages (EWMAs) and refined through SHAP-based feature attribution. Compared against a Extended Kalman Filter (EKF) and Unscented Kalman Filter (UKF) across ten diverse drive cycles, the proposed model consistently achieved superior performance, with mean absolute errors (MAEs) as low as 0.40%, outperforming EKF (0.66%) and UKF (1.36%). The Bi-LSTM model also demonstrated higher R<sup>2</sup> values (up to 0.9999) and narrower 95% confidence intervals, confirming its precision and robustness. Real-time implementation on embedded platforms yielded inference times of 1.3–2.2 s, validating its deployability for edge applications. The framework’s model-free nature makes it adaptable to other nonlinear, time-dependent systems beyond battery SOC estimation.
format Article
id doaj-art-d73e985b54804786aaae048cc7221ea8
institution Kabale University
issn 2076-3417
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-d73e985b54804786aaae048cc7221ea82025-08-20T03:36:02ZengMDPI AGApplied Sciences2076-34172025-07-011515853810.3390/app15158538A Novel Real-Time Battery State Estimation Using Data-Driven Prognostics and Health ManagementJuliano Pimentel0Alistair A. McEwan1Hong Qing Yu2College of Science and Engineering, University of Derby, Markeaton St., Derby DE22 3AW, UKCollege of Science and Engineering, University of Derby, Markeaton St., Derby DE22 3AW, UKCollege of Science and Engineering, University of Derby, Markeaton St., Derby DE22 3AW, UKThis paper presents a novel data-driven framework for real-time State of Charge (SOC) estimation in lithium-ion battery systems using a data-driven Prognostics and Health Management (PHM) approach. The method leverages an optimized bidirectional Long Short-Term Memory (Bi-LSTM) network, trained with enhanced datasets filtered via exponentially weighted moving averages (EWMAs) and refined through SHAP-based feature attribution. Compared against a Extended Kalman Filter (EKF) and Unscented Kalman Filter (UKF) across ten diverse drive cycles, the proposed model consistently achieved superior performance, with mean absolute errors (MAEs) as low as 0.40%, outperforming EKF (0.66%) and UKF (1.36%). The Bi-LSTM model also demonstrated higher R<sup>2</sup> values (up to 0.9999) and narrower 95% confidence intervals, confirming its precision and robustness. Real-time implementation on embedded platforms yielded inference times of 1.3–2.2 s, validating its deployability for edge applications. The framework’s model-free nature makes it adaptable to other nonlinear, time-dependent systems beyond battery SOC estimation.https://www.mdpi.com/2076-3417/15/15/8538PHMSOC estimationLi-ion batterydata-drivenmachine learningbidirectional LSTM
spellingShingle Juliano Pimentel
Alistair A. McEwan
Hong Qing Yu
A Novel Real-Time Battery State Estimation Using Data-Driven Prognostics and Health Management
Applied Sciences
PHM
SOC estimation
Li-ion battery
data-driven
machine learning
bidirectional LSTM
title A Novel Real-Time Battery State Estimation Using Data-Driven Prognostics and Health Management
title_full A Novel Real-Time Battery State Estimation Using Data-Driven Prognostics and Health Management
title_fullStr A Novel Real-Time Battery State Estimation Using Data-Driven Prognostics and Health Management
title_full_unstemmed A Novel Real-Time Battery State Estimation Using Data-Driven Prognostics and Health Management
title_short A Novel Real-Time Battery State Estimation Using Data-Driven Prognostics and Health Management
title_sort novel real time battery state estimation using data driven prognostics and health management
topic PHM
SOC estimation
Li-ion battery
data-driven
machine learning
bidirectional LSTM
url https://www.mdpi.com/2076-3417/15/15/8538
work_keys_str_mv AT julianopimentel anovelrealtimebatterystateestimationusingdatadrivenprognosticsandhealthmanagement
AT alistairamcewan anovelrealtimebatterystateestimationusingdatadrivenprognosticsandhealthmanagement
AT hongqingyu anovelrealtimebatterystateestimationusingdatadrivenprognosticsandhealthmanagement
AT julianopimentel novelrealtimebatterystateestimationusingdatadrivenprognosticsandhealthmanagement
AT alistairamcewan novelrealtimebatterystateestimationusingdatadrivenprognosticsandhealthmanagement
AT hongqingyu novelrealtimebatterystateestimationusingdatadrivenprognosticsandhealthmanagement