A Joint Estimation Method for the SOC and SOH of Lithium-Ion Batteries Based on AR-ECM and Data-Driven Model Fusion

Electronics, Journal Year: 2025, Volume and Issue: 14(7), P. 1290 - 1290

Published: March 25, 2025

Accurate estimations of State-of-Charge (SOC) and State-of-Health (SOH) are crucial for ensuring the safe efficient operation lithium-ion batteries in Battery Management Systems (BMSs). This paper proposes a novel joint estimation method integrating an Autoregressive Equivalent Circuit Model (AR-ECM) with data-driven model to address strong coupling between SOC SOH. First, multi-strategy improved Ivy algorithm (MSIVY) is utilized optimize hyperparameters Hybrid Kernel Extreme Learning Machine (HKELM). Key voltage interval features, including split voltage, differential capacity, current–voltage product, extracted filtered using sliding window approach enhance SOH prediction accuracy. The estimated subsequently incorporated into AR-ECM state-space equations, where enhanced particle swarm optimization optimizes parameters. Finally, Extended Kalman Filter (EKF) applied achieve collaborative SOC–SOH estimation. Experimental results demonstrate that proposed achieves errors below 1% under 2% on public datasets, showcasing its robust generalization capability real-time performance.

Language: Английский

Artificial intelligence-driven cybersecurity system for internet of things using self-attention deep learning and metaheuristic algorithms

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 16, 2025

Language: Английский

SOH Estimation Model Based on an Ensemble Hierarchical Extreme Learning Machine

Electronics, Journal Year: 2025, Volume and Issue: 14(9), P. 1832 - 1832

Published: April 29, 2025

This paper addresses the challenges of accurately estimating state health (SOH) retired batteries, where factors such as limited historical data, non-linear degradation, and unstable parameters complicate process. We propose a novel SOH estimation model based on an Integrated Hierarchical Extreme Learning Machine (I-HELM). The minimizes reliance data reduces computational complexity by introducing indicators derived from constant charging time current area. hierarchical structure (HELM) effectively captures relationship between battery capacity, improving accuracy learning efficiency. Additionally, integrating multiple HELM models enhances stability robustness results, making approach more reliable across varying operational conditions. proposed is validated experimental datasets collected two Samsung packs, four single cells, Panasonic batteries under both constant-current dynamic Experimental results demonstrate superior performance model: maximum error for cells packs does not exceed 2.2% 2.6%, respectively, with root mean square errors (RMSEs) below 1%. For remains 3%.

Language: Английский