A comprehensive review of state of charge estimation in lithium-ion batteries used in electric vehicles

Journal of Energy Storage, Journal Year: 2023, Volume and Issue: 72, P. 108777 - 108777

Published: Aug. 31, 2023

Language: Английский

---

State of charge estimation for LiFePO4 batteries joint by PID observer and improved EKF in various OCV ranges

Applied Energy, Journal Year: 2024, Volume and Issue: 377, P. 124435 - 124435

Published: Sept. 10, 2024

Language: Английский

---

A feedforward deep neural network for predicting the state-of-charge of lithium-ion battery in electric vehicles

Decision Analytics Journal, Journal Year: 2023, Volume and Issue: 8, P. 100255 - 100255

Published: June 1, 2023

This study proposes a feedforward deep neural network to predict the parameters of lithium-ion battery in electric vehicles. Correlation analysis is used select candidate for proposed model with no categorical variable. A direct artificial developed battery's charge state and develop inverse model. The predicted state-of-charge combined four virtual functions form input variables Furthermore, are incorporated enhance predicting capability function multi-output speed, mileage, voltage, velocity, state-of-charge. superior previously literature because its multiple output capabilities. Also, makes decision-making easier when design simulation than single-output networks, which only. mean square error as metric accurate measurement. During by (with functions), accuracy was 44.43 times higher traditional Redefined were verify findings result suggests that incorporating into model's can improve vehicle parameter predictions.

Language: Английский

---

GREENSKY: A fair energy-aware optimization model for UAVs in next-generation wireless networks

Green Energy and Intelligent Transportation, Journal Year: 2023, Volume and Issue: 3(1), P. 100130 - 100130

Published: Oct. 14, 2023

Unmanned Aerial Vehicles (UAVs) offer a strategic solution to address the increasing demand for cellular connectivity in rural, remote, and disaster-hit regions lacking traditional infrastructure. However, UAVs' limited onboard energy storage necessitates optimized, energy-efficient communication strategies intelligent expenditure maximize productivity. This work proposes novel joint optimization model coordinate charging operations across multiple UAVs functioning as aerial base stations. The optimizes station assignments trajectories UAV flight time minimize overall expenditure. By leveraging both static ground stations mobile supercharging opportunistic while considering battery chemistry constraints, mixed integer linear programming approach reduces usage by 9.1% versus conventional greedy heuristics. key results provide insights into separating based on mobility patterns, fully utilizing all available infrastructure through balanced distribution, strategically existing before deploying dedicated assets. Compared myopic localized decisions, globally optimized extends life enhances Overall, this marks significant advance management consolidating improvements within unified coordination framework focused fleets. lays critical foundation network deployments serve needs of future.

Language: Английский

---

State of charge estimation for electric vehicles using random forest

Green Energy and Intelligent Transportation, Journal Year: 2024, Volume and Issue: 3(5), P. 100177 - 100177

Published: Jan. 19, 2024

This paper introduces an innovative approach to addressing a critical challenge in the electric vehicle (EV) industry—the accurate estimation of state charge (SOC) EV batteries under real-world operating conditions. The mobility landscape is rapidly evolving, demanding more precise SOC methods improve range prediction accuracy and battery management. study applies Random Forest (RF) machine learning algorithm estimation. Traditionally, has posed formidable challenge, particularly capturing complex dependencies between various parameters values during dynamic driving Previous methods, including Extreme Learning Machine (ELM), have exhibited limitations providing robustness required for practical applications. In contrast, this research RF model, that excels scenarios. By leveraging decision trees ensemble learning, model forms resilient relationships input parameters, such as voltage, current, ambient temperature, temperatures, values. unique empowers deliver consistent estimates across diverse Comprehensive comparative analyses showcase superiority over ELM. not only outperforms but also demonstrates exceptional reliability, pressing needs industry. results underscore potential advancing suggest promising integration into management system BMW i3. holds key efficient dependable operations, marking significant milestone ongoing evolution technology. Importantly, lower Root Mean Squared Error (RMSE) 5.9028% compared 6.3127% ELM, Absolute (MAE) 4.4321% versus 5.1112% ELM rigorous k-fold cross-validation testing, reaffirming its quantitative

Language: Английский

---

A novel enhanced SOC estimation method for lithium-ion battery cells using cluster-based LSTM models and centroid proximity selection

Journal of Energy Storage, Journal Year: 2024, Volume and Issue: 97, P. 112866 - 112866

Published: July 16, 2024

In line with the global mission in achieving net zero target through deployment of renewable energy technologies and electrifying transportation sector; precise adaptable State Charge (SOC) estimation for Lithium-ion batteries has emerged as a critical need. The paper introduces novel Cluster-Based Learning Model (CBLM) framework that integrates strengths K-Means Fuzzy C-Means clustering predictive power Long Short-Term Memory (LSTM) networks. This approach aims to enhance precision reliability battery SOC estimations, adapting dynamic complex operational conditions characteristic Li-ion batteries. key contributions this study are development validation CBLM framework, which was proven outperform state-of-art standalone deep learning techniques particularly under diverse conditions. Additionally, introduction centroid proximity selection mechanism within dynamically selects most appropriate cluster model real-time based on data centroids. performance proposed is evaluated using Tesla 32,170 dataset. Results demonstrate model's enhanced performance, reductions Root Mean Square Error (RMSE) low 0.65 % Absolute (MAE) 0.51 %, reducing benchmark errors by margins 61.8 68.5 respectively. maximum error lower than benchmark, emphasising worst-case-scenarios. also conducted comprehensive ablation tests further optimize its performance.

Language: Английский

---

Advancing State of Charge Management in Electric Vehicles With Machine Learning: A Technological Review

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 43255 - 43283

Published: Jan. 1, 2024

As the share of electric vehicles increases, are exposed to broader driving conditions (e.g., extreme weather), which reduce performance and ranges below their nameplate rating. To ensure customer confidence support steady growth in vehicle adoption rates, accurate estimation battery state charge maintaining health through optimal charge/discharge decisions critical. Recently, manufacturers have begun employ machine learning techniques improve state-of-charge management better inform drivers about both short-term (state charge) long-term health) vehicles. This comprehensive review article explores intersection Recognizing critical importance optimizing performance, starts by evaluating traditional methods. Subsequently, it delves into transformative impact associated algorithms on management. Through lens various case studies, this demonstrates how learning-based empowers make informed dynamic energy usage decisions, enhancing efficiency extending life. The challenges data availability, model interpretability, real-time processing constraints acknowledged as impediments widespread techniques. Despite these challenges, future outlook for appears promising, with emerging trends such deep reinforcement poised refine accuracy. Moreover, study sheds light potential effectiveness vehicles, offering insights.. Machine emerges a game-changing force paving way intelligent adaptive that environmentally friendly efficient. evolving field invites further research development, making vital exciting area within automotive industry.

Language: Английский

---

State-of-power estimation for lithium-ion batteries based on a frequency-dependent integer-order model

Journal of Power Sources, Journal Year: 2023, Volume and Issue: 594, P. 234000 - 234000

Published: Dec. 30, 2023

Language: Английский

---

Multi-sensor multi-mode fault diagnosis for lithium-ion battery packs with time series and discriminative features

Energy, Journal Year: 2023, Volume and Issue: 290, P. 130151 - 130151

Published: Dec. 29, 2023

Language: Английский

---

State-of-charge estimation by extended sliding mode observer based on lithium-ion battery voltage dynamics

Journal of Power Sources, Journal Year: 2024, Volume and Issue: 611, P. 234718 - 234718

Published: May 24, 2024

Language: Английский

---