Exploiting Artificial Neural Networks for the State of Charge Estimation in EV/HV Battery Systems: A Review

Batteries, Journal Year: 2025, Volume and Issue: 11(3), P. 107 - 107

Published: March 13, 2025

Artificial Neural Networks (ANNs) improve battery management in electric vehicles (EVs) by enhancing the safety, durability, and reliability of electrochemical batteries, particularly through improvements State Charge (SOC) estimation. EV batteries operate under demanding conditions, which can affect performance and, extreme cases, lead to critical failures such as thermal runaway—an exothermic chain reaction that may result overheating, fires, even explosions. Addressing these risks requires advanced diagnostic strategies, machine learning presents a powerful solution due its ability adapt across multiple facets management. The versatility ML enables application material discovery, model development, quality control, real-time monitoring, charge optimization, fault detection, positioning it an essential technology for modern systems. Specifically, ANN models excel at detecting subtle, complex patterns reflect health performance, crucial accurate SOC effectiveness applications this domain, however, is highly dependent on selection datasets, relevant features, suitable algorithms. Advanced techniques active are being explored enhance improving models’ responsiveness diverse nuanced behavior. This compact survey consolidates recent advances estimation, analyzing current state field highlighting challenges opportunities remain. By structuring insights from extensive literature, paper aims establish ANNs foundational tool next-generation systems, ultimately supporting safer more efficient EVs robust safety protocols. Future research directions include refining dataset quality, optimizing algorithm selection, precision, thereby broadening ANNs’ role ensuring reliable vehicles.

Language: Английский

---

Bearing Lifespan Reliability Prediction Method Based on Multiscale Feature Extraction and Dual Attention Mechanism

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(7), P. 3662 - 3662

Published: March 27, 2025

Accurate prediction of the remaining useful life (RUL) rolling bearings was crucial for ensuring safe operation machinery and reducing maintenance losses. However, due to high nonlinearity complexity mechanical systems, traditional methods failed meet requirements medium- long-term tasks. To address this issue, paper proposed a recurrent neural network with dual attention model. By employing path weight selection methods, Discrete Fourier transform, mechanisms, accuracy generalization ability in complex time series analysis were significantly improved. Evaluation results based on mean absolute error (MAE) root square (RMSE) indicated that mechanism effectively focused key features, optimized feature extraction, improved performance. An end-to-end RUL model established MS-DAN network, effectiveness method validated using IEEE PHM 2012 Data Challenge dataset, providing more accurate decision support equipment engineers.

Language: Английский

---

Operation of EVs in hot climates: Modeling of temperature-driven energy consumption including Li-ion battery energy loss

Energy Reports, Journal Year: 2025, Volume and Issue: 13, P. 4209 - 4222

Published: April 8, 2025

Language: Английский

---

A review of the combined effects of environmental and operational factors on lithium-ion battery performance: temperature, vibration, and charging/discharging cycles

RSC Advances, Journal Year: 2025, Volume and Issue: 15(17), P. 13272 - 13283

Published: Jan. 1, 2025

The performance of lithium-ion batteries (LIBs) is influenced by the coupled effects environmental conditions and operational scenarios, which can impact their electrochemical performance, reliability, safety.

Language: Английский

---

Advances and limitations in machine learning approaches applied to remaining useful life predictions: a critical review

The International Journal of Advanced Manufacturing Technology, Journal Year: 2024, Volume and Issue: 133(9-10), P. 4059 - 4076

Published: June 22, 2024

Language: Английский

---

Enhancing prediction accuracy of Remaining Useful Life in lithium-ion batteries: A deep learning approach with Bat optimizer

Deleted Journal, Journal Year: 2024, Volume and Issue: 2, P. 100003 - 100003

Published: June 1, 2024

Remaining Useful Life (RUL) prediction in lithium-ion batteries is crucial for assessing battery performance. Despite the popularity of deep learning methods RUL prediction, their complex architectures often pose challenges interpretation and resource consumption. We propose a novel approach that combines interpretability convolutional neural network (CNN) with efficiency bat-based optimizer. CNN extracts data features characterizes degradation kinetics, while optimizer refines parameters. Tested on NASA PCoE data, our method achieves exceptional results minimal computational burden fewer It outperforms traditional approaches, yielding an R2-score 0.9987120, MAE 0.004397067 Ah, low RMSE 0.00656 Ah. The proposed model models, as confirmed by comparative analysis.

Language: Английский

---

Early Prediction of Remaining Useful Life for Lithium-Ion Batteries with the State Space Model

Energies, Journal Year: 2024, Volume and Issue: 17(24), P. 6326 - 6326

Published: Dec. 16, 2024

In the realm of lithium-ion batteries (LIBs), issues like material aging and capacity decline contribute to performance degradation or potential safety hazards. Predicting remaining useful life (RUL) serves as a crucial method assessing health batteries, thereby enhancing reliability safety. To reduce complexity improve accuracy applicability early RUL predictions for LIBs, we proposed Mamba-based state space model prediction. Due impacts abnormal data, first use interquartile range (IQR) with sliding window data cleansing. Subsequently, top three highest correlated features are selected, only 300 cycling used training. The has ability make forecasts using these few historical data. Extensive experiments conducted CALCE CS2 datasets. MAE, RMSE, RE less than 0.015, 0.019, 0.0261; meanwhile, R2 is higher 0.99. Compared baseline approaches (CNN, BiLSTM, CNN-BiLSTM), average approach reduced by at least 29%, 21%, 36%, respectively. According experimental results, performs better in terms accuracy, robustness, efficiency.

Language: Английский

---

Advanced battery management system enhancement using IoT and ML for predicting remaining useful life in Li-ion batteries

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Dec. 5, 2024

This study highlights the increasing demand for battery-operated applications, particularly electric vehicles (EVs), necessitating development of more efficient Battery Management Systems (BMS), lithium-ion (Li-ion) batteries used in energy storage systems (ESS). research addresses some key limitations current BMS technologies, with a focus on accurately predicting remaining useful life (RUL) batteries, which is critical factor ensuring operational efficiency and sustainability. Real-time data are collected from sensors via an Internet Things (IoT) device processed using Arduino Nano, extracts values input into Long Short-Term Memory (LSTM) model. model employs National Aeronautics Space Administration (NASA) Li-battery dataset current, voltage temperature, cycle to predict battery RUL. The proposed demonstrates significant forecasting precision, attaining root mean square error (RMSE) 0.01173, outperforming all comparative models. improvement facilitates effective decision-making BMS, resource allocation adaptability transient conditions. However, practical implementation real-time acquisition at scale across diverse environments remains challenging. Future will enhancing generalizability model, expanding its applicability broader datasets, automating ingestion minimize integration challenges. These advancements aimed improving both industrial residential applications accordance Sustainable Development Goals (SDGs) UN.

Language: Английский

---

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

Published: Aug. 30, 2024

In the realm of Lithium-ion batteries, issues like material aging and capacity decline contribute to performance degradation or potential safety hazards. Predicting Remaining Useful Life (RUL) serves as a crucial method assess health thereby enhancing reliability safety. Currently hybrid approaches for batteries RUL estimation are prevalence gained fruitful development. this paper, voting ensembles combining Gradient Boosting, Random Forest K-Nearest Neighbors is proposed predict fade trend knee point. Finally, extensive experiments conducted using CALCE CS2 datasets. According experimental results, approach supersedes single deep learning prediction point predicted accurately. Besides purpose, innovated can be also integrated into real-world application wider usage.

Language: Английский

---

Data-Driven Prognostics with Multi-Layer Perceptron Particle Filter: a Cross-Industry Exploration

PHM Society European Conference, Journal Year: 2024, Volume and Issue: 8(1), P. 8 - 8

Published: June 27, 2024

The integration of particle or Kalman filters with machine learning tools like support vector machines, Gaussian processes, neural networks has seen extensive exploration in the context prognostic and health management, particularly model-based applications. This paper focuses on Multi-Layer Perceptron Particle Filter (MLP-PF), a data-driven approach that harnesses non-linearity MLP to describe degradation trajectories without relying physical model. Bayesian nature filter is utilized update parameters, providing flexibility method accommodating unexpected changes behavior. To showcase versatility MLP-PF, this work demonstrates its seamless into diverse use cases, such as lithium-ion battery analysis, virtual monitoring for turbofans, assessment fatigue crack growth. We illustrate how it effortlessly accommodates various contexts through slight parameter modifications. Adjustment includes variation number neurons layers MLP, threshold adjustments, initial training refinements adaptation process noise. Addressing different processes across these applications, MLP-PF proves adaptability utility contexts. These findings highlight method’s adapting cases potential robust tool industries. offers practical efficient means estimating remaining useful life predicting complex systems, implications advancing

Language: Английский

---