PatchFormer: A novel patch-based transformer for accurate remaining useful life prediction of lithium-ion batteries

Journal of Power Sources, Год журнала: 2025, Номер 631, С. 236187 - 236187

Опубликована: Янв. 17, 2025

Язык: Английский

---

State-of-Health Prediction of Lithium-Ion Batteries Using Feature Fusion and a Hybrid Neural Network Model

Energy, Год журнала: 2025, Номер unknown, С. 135163 - 135163

Опубликована: Фев. 1, 2025

Язык: Английский

---

Lithium-ion battery health state and remaining useful life prediction based on hybrid model MFE-GRU-TCA

Journal of Energy Storage, Год журнала: 2024, Номер 95, С. 112442 - 112442

Опубликована: Июнь 15, 2024

Язык: Английский

---

A novel hybrid neural network-based SOH and RUL estimation method for lithium-ion batteries

Journal of Energy Storage, Год журнала: 2024, Номер 98, С. 113074 - 113074

Опубликована: Июль 28, 2024

Язык: Английский

---

A Deep Learning Multi-Feature Based Fusion Model for Predicting the State of Health of Lithium-Ion Batteries

Energy, Год журнала: 2025, Номер unknown, С. 134569 - 134569

Опубликована: Янв. 1, 2025

Язык: Английский

---

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

Energies, Год журнала: 2025, Номер 18(3), С. 746 - 746

Опубликована: Фев. 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.

Язык: Английский

---

Transfer learning from synthetic data for open-circuit voltage curve reconstruction and state of health estimation of lithium-ion batteries from partial charging segments

Energy and AI, Год журнала: 2024, Номер 17, С. 100382 - 100382

Опубликована: Июнь 7, 2024

Data-driven models for battery state estimation require extensive experimental training data, which may not be available or suitable specific tasks like open-circuit voltage (OCV) reconstruction and subsequent of health (SOH) estimation. This study addresses this issue by developing a transfer-learning-based OCV model using temporal convolutional long short-term memory (TCN-LSTM) network trained on synthetic data from an automotive nickel cobalt aluminium oxide (NCA) cell generated through mechanistic approach. The consists curves at constant temperature, C-rates between C/30 to 1C, SOH-range 70 % 100 %. is refined via Bayesian optimization then applied four use cases with reduced manganese (NMC) higher cases. TL models' performances are compared solely focusing different windows. results demonstrate that the mean absolute error (MAE) within average electric vehicle (BEV) home charging window (30 85 charge (SOC)) less than 22 mV first three across all C-rates. SOH estimated reconstructed exhibits percentage (MAPE) below 2.2 these further investigates impact source domain incorporating two additional datasets, lithium iron phosphate (LFP) entirely artificial, non-existing, cell, showing shifting scaling gradient changes in curve suffice transfer knowledge, even chemistries. A key limitation respect extrapolation capability identified evidenced our fourth case, where absence such comprehensive hindered process.

Язык: Английский

---

State of health estimation joint improved grey wolf optimization algorithm and LSTM using partial discharging health features for lithium-ion batteries

Energy, Год журнала: 2024, Номер unknown, С. 134293 - 134293

Опубликована: Дек. 1, 2024

Язык: Английский

---

Research on topology technology of integrated battery energy storage system with reconfigurable battery and converter

Journal of Energy Storage, Год журнала: 2024, Номер 96, С. 112688 - 112688

Опубликована: Июнь 24, 2024

Язык: Английский

---

Predicting the RUL of Li-Ion Batteries in UAVs Using Machine Learning Techniques

Computers, Год журнала: 2024, Номер 13(3), С. 64 - 64

Опубликована: Фев. 29, 2024

Over the past decade, Unmanned Aerial Vehicles (UAVs) have begun to be increasingly used due their untapped potential. Li-ion batteries are most power electrically operated UAVs for advantages, such as high energy density and number of operating cycles. Therefore, it is necessary estimate Remaining Useful Life (RUL) prediction batteries’ capacity prevent UAVs’ loss autonomy, which can cause accidents or material losses. In this paper, authors propose a method RUL using data-driven approach. To maximize performance process, three machine learning models, Support Vector Machine Regression (SVMR), Multiple Linear (MLR), Random Forest (RF), were compared batteries. The implemented within Predictive Maintenance (PdM) systems.

Язык: Английский

---