Battery Health Monitoring and Remaining Useful Life Prediction Techniques: A Review of Technologies

Batteries, Journal Year: 2025, Volume and Issue: 11(1), P. 31 - 31

Published: Jan. 17, 2025

Lithium-ion (Li-ion) batteries have become essential in modern industries and domestic applications due to their high energy density efficiency. However, they experience gradual degradation over time, which presents significant challenges maintaining optimal battery performance increases the risk of unexpected system failures. To ensure reliability longevity Li-ion applications, various methods been proposed for health monitoring remaining useful life (RUL) prediction. This paper provides a comprehensive review analysis primary approaches employed RUL estimation under categories model-based, data-driven, hybrid methods. Generally speaking, model-based use physical or electrochemical models simulate behaviour, offers valuable insights into principles that govern degradation. Data-driven techniques leverage historical data, AI, machine learning algorithms identify trends predict RUL, can provide flexible adaptive solutions. Hybrid integrate multiple enhance predictive accuracy by combining with statistical analytical strengths data-driven techniques. thoroughly evaluates these methodologies, focusing on recent advancements along respective limitations. By consolidating current findings highlighting potential pathways advancement, this serves as foundational resource researchers practitioners working advance prediction across both academic industrial fields.

Language: Английский

---

Experimental investigation on hydrated salt phase change material for lithium-ion battery thermal management and thermal runaway mitigation

Energy, Journal Year: 2024, Volume and Issue: 307, P. 132685 - 132685

Published: Aug. 3, 2024

Language: Английский

---

Multiscale-multidomain model order reduction of Lithium-ion batteries for automobile application: A review

Journal of Energy Storage, Journal Year: 2024, Volume and Issue: 99, P. 113390 - 113390

Published: Aug. 24, 2024

Language: Английский

---

A review of Bayesian-filtering-based techniques in RUL prediction for Lithium-Ion batteries

Journal of Energy Storage, Journal Year: 2025, Volume and Issue: 111, P. 115371 - 115371

Published: Jan. 18, 2025

Language: Английский

---

Thermal characterization of pouch cell using infrared thermography and electrochemical modelling for the Design of Effective Battery Thermal Management System

Applied Energy, Journal Year: 2024, Volume and Issue: 376, P. 124301 - 124301

Published: Aug. 30, 2024

Language: Английский

---

Evaluation of Advances in Battery Health Prediction for Electric Vehicles from Traditional Linear Filters to Latest Machine Learning Approaches

Batteries, Journal Year: 2024, Volume and Issue: 10(10), P. 356 - 356

Published: Oct. 11, 2024

In recent years, there has been growing interest in Li-ion battery State-of-Health (SOH) estimation due to its critical role ensuring the safe and reliable operation of Electric Vehicles (EVs). Effective energy management accurate SOH prediction are essential for reliability sustainability EVs. This paper presents an in-depth review techniques, starting with overview seminal methods that lay theoretical groundwork modeling prediction. The then evaluates advancements Machine Learning (ML) Artificial Intelligence (AI) emphasizing their contributions improving estimation. Through a rigorous screening process, systematically assesses evolution these advanced methods, addressing specific research questions evaluate effectiveness practical implications. Key findings highlight potential hybrid models integrate Equivalent Circuit Models (ECMs) Deep approaches, offering enhanced accuracy real-time performance. Additionally, discusses limitations current such as challenges translating laboratory-based real-world conditions computational complexity some prospective methods. conclusion, this identifies promising future directions aimed at optimizing overcoming existing constraints advance Vehicles.

Language: Английский

---

Experimental investigation for the influence mechanism of air intake method and humidity level on performance of proton exchange membrane fuel cells

International Journal of Hydrogen Energy, Journal Year: 2024, Volume and Issue: 86, P. 823 - 834

Published: Sept. 2, 2024

Language: Английский

---

A Novel Method for Estimating the State of Health of Lithium-Ion Batteries Based on Physics-Informed Neural Network

Batteries, Journal Year: 2025, Volume and Issue: 11(2), P. 49 - 49

Published: Jan. 26, 2025

An accurate state of health (SOH) assessment lithium-ion batteries is essential for ensuring the reliability and safety electric vehicles (EVs). Data-driven SOH estimation methods have shown promise but face challenges in generalizing across diverse battery types variable operating conditions. To address this, this study integrates physical information into data-driven approaches, enabling physically consistent inferences a rapid adaptation to different chemistries usage scenarios. Specifically, features correlated with degradation, such as link between incremental capacity (IC) peaks SOH, are used constraints guide model learning. A fully connected layer within back-propagation neural network (BPNN) employed capture aging dynamics effectively. Experimental results on two datasets show that proposed outperforms traditional networks, reducing RMSE by at least 1.1% demonstrating strong generalizability both single-dataset transfer learning tasks.

Language: Английский

---

Remaining Useful Life Prediction for Lithium-Ion Batteries Based on Hybrid Ensembles Allied with Data-Driven Approach

Energies, Journal Year: 2025, Volume and Issue: 18(5), P. 1114 - 1114

Published: Feb. 25, 2025

Capacity fade in lithium-ion batteries (LIBs) poses challenges for various industries. Predicting and preventing this is crucial, hybrid methods estimating remaining useful life (RUL) have become prevalent achieved significant advancements. In paper, we introduce a voting ensemble that combines Gradient Boosting, Random Forest, K-Nearest Neighbors to forecast the fading capacity trend knee point. We conducted extensive experiments using CALCE CS2 datasets. The results indicate our proposed approach outperforms single deep learning RUL prediction accurately identifies Beyond prediction, innovative method can potentially be integrated into real-world applications broader use.

Language: Английский

---

Fuzzy Particle Filtering Based Approach for Battery RUL Prediction With Uncertainty Reduction Strategies

Expert Systems, Journal Year: 2025, Volume and Issue: 42(4)

Published: March 6, 2025

ABSTRACT This paper proposes a two‐stage framework that combines uncertainty reduction and predictive modelling to enhance the accuracy of battery Remaining Useful Life (RUL) prediction. In first stage, simplified fuzzy optimization learning model is introduced mitigate caused by abnormal capacity fluctuations in data. The proposed reconstructs degradation data into consistent downward trend based on mid‐ short‐term tendencies battery, alleviating variability improving suitability for modelling. second arising during recursive prediction process standalone Transformer was mitigated through integration particle filter. approach dynamically manages errors using particles, effectively controlling cumulative enhancing stability reliability long‐term predictions. methodology can lead extended life increased operational accurate RUL validated experiments NASA CALCE datasets, demonstrating superior compared conventional approaches systematically reducing uncertainties.

Language: Английский

---