Enhanced transformer encoder long short-term memory hybrid neural network for multiple temperature state of charge estimation of lithium-ion batteries

Journal of Power Sources, Journal Year: 2025, Volume and Issue: 632, P. 236411 - 236411

Published: Feb. 3, 2025

Language: Английский

---

Systematic overview of equalization methods for battery energy storage systems

Journal of Power Sources, Journal Year: 2025, Volume and Issue: 640, P. 236766 - 236766

Published: March 13, 2025

Language: Английский

---

Battery SOC estimation with physics-constrained BiLSTM under different external pressures and temperatures

Journal of Energy Storage, Journal Year: 2025, Volume and Issue: 117, P. 116205 - 116205

Published: March 14, 2025

Language: Английский

---

Research Progress on State of Charge Estimation Methods for Power Batteries in New Energy Intelligent Connected Vehicles

Energies, Journal Year: 2025, Volume and Issue: 18(9), P. 2144 - 2144

Published: April 22, 2025

Accurately estimating the State of Charge (SOC) power batteries is crucial for Battery Management Systems (BMS) in new energy intelligent connected vehicles. It directly influences vehicle range, management efficiency, and safety lifespan battery. However, SOC cannot be measured with instruments; it needs to estimated using external parameters such as current, voltage, internal resistance. Moreover, represent complex nonlinear time-varying systems, various uncertainties—like battery aging, fluctuations ambient temperature, self-discharge effects—complicate accuracy these estimations. This significantly increases complexity estimation process limits industrial applications. To address challenges, this study systematically classifies existing algorithms, performs comparative analyses their computational accuracy, identifies inherent limitations within each category. Additionally, a comprehensive review technologies utilized BMS by automotive OEMs globally conducted. The analysis concludes that advancing multi-fusion frameworks, which offer enhanced universality, robustness, hard real-time capabilities, represents primary research trajectory field.

Language: Английский

---

Application of state of health estimation and remaining useful life prediction for lithium-ion batteries based on AT-CNN-BiLSTM

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

Published: Nov. 23, 2024

Ensuring the long-term safe usage of lithium-ion batteries hinges on accurately estimating State Health $$(\textrm{SOH})$$ and predicting Remaining Useful Life (RUL). This study proposes a novel prediction method based AT-CNN-BiLSTM architecture. Initially, key parameters such as voltage, current, temperature, SOH are extracted averaged for each cycle to ensure uniformity reliability input data. The CNN is utilized extract deep features from data, followed by BiLSTM analyze temporal dependencies in data sequences. Since multidimensional parameter used predict trend batteries, an attention mechanism employed enhance weight highly relevant vectors, improving model's analytical capabilities. Experimental results demonstrate that CNN-BiLSTM-Attention model achieves absolute error 0 RUL prediction, $$R^{2}$$ value greater than 0.9910 , MAPE less 0.9003 . Comparative analysis with hybrid neural network algorithms LSTM, BiLSTM, CNN-LSTM confirms proposed high accuracy stability estimation prediction.

Language: Английский

---

Enhancing combustion and emission characteristics of CI engines through atomization and fuel-air mixing using non-circular orifices: A path towards sustainable biodiesel utilization

Green Technologies and Sustainability, Journal Year: 2024, Volume and Issue: unknown, P. 100161 - 100161

Published: Dec. 1, 2024

Language: Английский

---