State of Health (SOH) Estimation of Lithium-Ion Batteries Based on ABC-BiGRU

Electronics, Journal Year: 2024, Volume and Issue: 13(9), P. 1675 - 1675

Published: April 26, 2024

As a core component of new energy vehicles, accurate estimation the State Health (SOH) lithium-ion power batteries is essential. Correctly predicting battery SOH plays crucial role in extending lifespan ensuring their safety, and promoting sustainable development. Traditional physical or electrochemical models have low accuracy measuring lithium are not suitable for complex driving conditions real-world vehicles. This study utilized black-box characteristics deep learning to explore intrinsic correlations historical cycling data batteries, thereby eliminating need consider internal chemical reactions batteries. Through Pearson correlation analysis, this selects health indicators (HIs) from that significantly impact as input features. In field paper applies ABC-BiGRU first time prediction. Compared with other recursive neural network models, demonstrates superior predictive performance, maximum root mean square error absolute only 0.016799317 0.012626847, respectively.

Language: Английский

---

State of the Art in Electric Batteries’ State-of-Health (SoH) Estimation with Machine Learning: A Review

Energies, Journal Year: 2025, Volume and Issue: 18(3), P. 746 - 746

Published: Feb. 6, 2025

The sustainable reuse of batteries after their first life in electric vehicles requires accurate state-of-health (SoH) estimation to ensure safe and efficient repurposing. This study applies the systematic ProKnow-C methodology analyze state art SoH using machine learning (ML). A bibliographic portfolio 534 papers (from 2018 onward) was constructed, revealing key research trends. Public datasets are increasingly favored, appearing 60% studies reaching 76% 2023. Among 12 identified sources covering 20 from different lithium battery technologies, NASA’s Prognostics Center Excellence contributes 51% them. Deep (DL) dominates field, comprising 57.5% implementations, with LSTM networks used 22% cases. also explores hybrid models emerging role transfer (TL) improving prediction accuracy. highlights potential applications predictions energy informatics smart systems, such as grids Internet-of-Things (IoT) devices. By integrating estimates into real-time monitoring systems wireless sensor networks, it is possible enhance efficiency, optimize management, promote practices. These reinforce relevance machine-learning-based resilience sustainability systems. Finally, an assessment implemented algorithms performances provides a structured overview identifying opportunities for future advancements.

Language: Английский

---

An improved dung beetle optimizer- hybrid kernel least square support vector regression algorithm for state of health estimation of lithium-ion batteries based on variational model decomposition

Energy, Journal Year: 2024, Volume and Issue: 306, P. 132464 - 132464

Published: July 17, 2024

Language: Английский

---

Intelligent Pattern Recognition Using Equilibrium Optimizer With Deep Learning Model for Android Malware Detection

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 24516 - 24524

Published: Jan. 1, 2024

Android malware recognition is the procedure of mitigating and identifying malicious software (malware) planned to target operating systems (OS) that are extremely utilized in smartphones tablets. As ecosystem endures produce, therefore risk attacks on these devices. Identifying vital for keeping user data, privacy, device integrity. detection utilizing deep learning (DL) signifies a cutting-edge system maintenance mobile DL approaches namely recurrent neural network (RNN) convolutional (CNN) best automatically removing intricate designs behaviors app data. By leveraging features such as application programming interface (API) call sequences, code patterns, permissions, efficiently differentiated between benign apps, even face previous unseen attacks. This study presents an Intelligent Pattern Recognition using Equilibrium Optimizer with Deep Learning (IPR-EODL) Approach Malware Recognition. The purpose IPR-EODL approach properly identify categorize way security can be achieved. In technique, data pre-processing step was applied convert input into compatible setup. addition, technique applies channel attention long short-term memory (CA-LSTM) methodology malware. To enhance solution CA-LSTM algorithm, employs optimization (EO) algorithm hyperparameter tuning method. experimentation evaluation model verified benchmark database. extensive results highlight significant result process.

Language: Английский

---

Evolution of prediction models for road surface irregularity: Trends, methods and future

Construction and Building Materials, Journal Year: 2024, Volume and Issue: 449, P. 138316 - 138316

Published: Sept. 19, 2024

Language: Английский

---

A Novel Approach for Predicting Remaining Useful Life and Capacity Fade in Lithium-Ion Batteries Using Hybrid Machine Learning

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 131950 - 131963

Published: Jan. 1, 2023

Lithium-ion batteries (LIBs) Remaining Useful Life (RUL) prediction is vital for Battery Management Systems (BMS). It crucial providing the optimum performance and longevity of used in different industries. In this study, we propose an innovative approach that combines machine learning techniques hybrid modeling strategies to enhance accuracy robustness battery analysis. By leveraging power k-Nearest Neighbors (kNN), Random Forest (RF), XGBoost algorithms, our proposed model effectively captures complex relationships patterns data. We meticulously curate a comprehensive dataset comprising essential parameters: capacity, voltage, cycle, temperature. Through rigorous experimentation evaluation, method outperforms existing approaches predicting RUL capacity fade. The insights gained from analysis offer valuable guidance optimizing performance, enabling informed maintenance planning, improving energy storage system efficiency.

Language: Английский

---

A collaborative interaction gate-based deep learning model with optimal bandwidth adjustment strategies for lithium-ion battery capacity point-interval forecasting

Applied Energy, Journal Year: 2024, Volume and Issue: 377, P. 124741 - 124741

Published: Oct. 21, 2024

Language: Английский

---

Adaptive Transfer Learning Strategy for Predicting Battery Aging in Electric Vehicles

Batteries, Journal Year: 2025, Volume and Issue: 11(1), P. 21 - 21

Published: Jan. 9, 2025

This work presents an adaptive transfer learning approach for predicting the aging of lithium-ion batteries (LiBs) in electric vehicles using capacity fade as metric battery state health. The proposed includes a similarity-based and strategy which selected data from original dataset are transferred to clean based on combined/weighted similarity contribution feature stress factor similarities times series similarities. Transfer (TL) is then performed by pre-training model with data, frozen weights biases hidden layer. At same time, toward output node recalculated target data. error reduction lies between −0.4% −8.3% 20 computational experiments, attesting effectiveness robustness our TL approach. Considerations structure representation presented, well workflow enhance application LiBs.

Language: Английский

---

An adaptive ensemble learning capacity prediction method with dual-modal data in lithium-ion battery manufacturing

International Journal of Green Energy, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 12

Published: Jan. 20, 2025

Language: Английский

---

Capacity prediction model for lithium-ion batteries based on bi-directional LSTM neural network optimized by adaptive convergence factor gold rush optimizer

Evolutionary Intelligence, Journal Year: 2025, Volume and Issue: 18(2)

Published: Feb. 21, 2025

Language: Английский

---