Aug 2026· Eletrônica de Potência· Vol 31, pp. e202626· 0 citations· 37 references
TL;DR
This paper presents a deployment-oriented evaluation of data-driven SoC estimation using large-scale operational data from a battery electric bus, showing that temporal resolution strongly affects the accuracy-efficiency trade-off.
Abstract
Accurate State of Charge (SoC) estimation is essential for safe and efficient lithium-ion battery operation in electric mobility. Although machine learning methods achieve high predictive capability, many studies rely on laboratory cycling data and overlook deployment constraints such as latency and embedded hardware. This paper presents a deployment-oriented evaluation of data-driven SoC estimation using large-scale operational data from a battery electric bus. The dataset includes more than 4.3 million field measurements of current, voltage, temperature, and SoC collected under realistic driving conditions. Five models are compared: Random Forest, LightGBM, XGBoost, Temporal Convolutional Networks (TCN), and Gated Recurrent Unit (GRU) networks. Models are evaluated across sampling intervals from 30 s to 210 s and multiple training-data fractions, considering accuracy, training time, and inference latency. Results show that temporal resolution strongly affects the accuracy-efficiency trade-off. The best configuration, LightGBM at 180 s using 75 % of training data, achieved a test MAE of 6.338, RMSE of 8.495, and median inference latency of 1.10 ms. Compared with the Random Forest baseline at 30 s, it reduced MAE by 34.4 %, RMSE by 35.6 %, and latency by 97.6 %, supporting efficient real-time battery management system deployment.
Accurate estimation of battery State of Charge (SOC) is essential for the reliable and efficient operation of Battery Management Systems (BMS) in electric vehicles, renewable energy storage, and portable electronics. Conventional techniques such as open-circuit voltage measurement and Coulomb counting suffer from limitations including sensitivity to operating conditions, cumulative errors, and reduced accuracy under dynamic loads. This paper presents an integrated hardware–software framework for real-time SOC estimation and intelligent power control using a machine learning approach. An Arduino-based sensing layer acquires voltage, current, temperature, and discharge time, which are processed using a hyperparameter-optimized Random Forest regression model implemented in Python. The predicted SOC is transmitted to an ESP32 microcontroller that executes a threshold-based load management strategy using optocoupler-isolated relay switching. Experimental results demonstrate high prediction accuracy with a Mean Absolute Error of 0.0062% and R² of 99.9997%, outperforming conventional and deep learning-based approaches. The proposed system offers a low-cost, scalable, and IoT-enabled solution for precise battery monitoring and adaptive load control in real-time applications.
P. David, Kalai Vani Solaisamy, S. Suresh Kumar et al.· Engineering Research Express· 0 citations
Accurate estimation of the state of charge (SOC) and state of health (SOH) of lithium-ion batteries is essential for improving the performance, safety, and lifespan of electric vehicles (EVs). Traditional estimation methods often face challenges such as high computational complexity, limited adaptability to battery aging, and reduced accuracy under varying operating conditions. To overcome these limitations, this paper presents a hybrid data-driven framework that combines machine learning and deep learning techniques for SOC and SOH prediction. For SOC estimation, linear regression, recurrent neural networks (RNN), gated recurrent unit (GRU), and stacked long short-term memory (LSTM) models are employed. For SOH prediction, ensemble learning methods, including stacking regressor, tree-based pipeline optimization tool (TPOT) regressor, and hybrid GRU-LSTM models, are utilized. The proposed models are evaluated using publicly available lithium-ion battery datasets under different charge-discharge conditions. Results show that deep learning approaches achieve superior performance, with GRU-LSTM and stacked LSTM models providing highly accurate SOC estimation (R² ≈ 0.993, RMSE ≈ 0.015), while the TPOT-based ensemble model delivers near-perfect SOH prediction (R² ≈ 1.0). A web-based implementation further enables real-time battery monitoring, demonstrating the framework’s practicality for advanced battery management systems (BMS) in EV applications.
N. Keerthi, B. Jyothi, M. Sharanya et al.· International Journal of App...· 0 citations
Lithium-ion batteries fundamentally influence the reliability, safety, and service life of electric vehicles, making accurate State of Health (SOH) estimation essential for advanced battery management systems. To address the nonlinear, multiscale, and usage-dependent degradation patterns found in real-world cycling, this study proposes a hybrid neural network framework that combines convolutional feature extraction with recurrent temporal modeling. The architecture incorporates mathematically defined convolutional modules for localized voltage–capacity pattern recognition, recurrent units for longterm degradation dynamics, and a fusion mechanism supported by multi-metric loss functions. Using publicly available datasets—including National Aeronautics and Space Administration (NASA) cells B0005/B0006 and the Oxford Battery Degradation Dataset—the method is evaluated under diverse degradation trajectories characterized by mid-life plateaus, nonlinear capacity fade, and accelerated end-of-life decline. Results demonstrate that the hybrid model exhibits improved robustness to measurement noise, partial cycling, and operational variability compared with single-path architectures, thereby providing more stable and adaptable SOH predictions. These findings indicate that hybrid neural network frameworks offer a promising technical pathway for next-generation battery management systems, enabling more reliable SOH monitoring, enhanced predictive maintenance strategies, and longer-lasting electric vehicle battery performance.
Guan-Ze Li· European Conference on Elect...· 0 citations
Accurate state of charge (SOC) estimation is essential for the safe and efficient operation of lithium-ion battery systems, while deploying deep learning-based estimators in embedded battery management systems remains challenging due to limited memory, computational capability, and real-time constraints. To address this issue, this study comparatively investigates four deep learning models, namely CNN, LSTM, CNN–LSTM, and lightweight TinyCNN, for embedded-oriented SOC estimation. A unified framework integrating data preprocessing, model training, post-training INT8 quantization, and TensorFlow Lite Micro deployment on an ESP32 microcontroller is established. Results under the US06 driving condition show that all models can track the SOC trajectory, although their relative performance differs between FP32 and INT8 inference. CNN–LSTM achieves the lowest FP32 error, with an MAE of 1.31%, while LSTM achieves the lowest INT8 error, with an MAE of 1.70%. Although TinyCNN has a higher INT8 MAE of 2.55%, it contains only 2913 parameters, occupies 8.51 KiB in INT8 form, and achieves the lowest measured ESP32 mean inference latency of 41.992 ms. These results demonstrate the feasibility of the evaluated INT8 models on the ESP32 under the US06 condition and indicate that model selection should depend on application-specific trade-offs among estimation accuracy, model size, runtime memory, and inference latency.
Yi-Yun Liang, Xun Lin, Xin Tang et al.· World Electric Vehicle Journ...· 1 citation
With the increasing integration of renewable energy sources, energy storage systems have become essential, making the accurate estimation of their State of Health (SOH) and degradation behavior critical. In this work, we propose a physics-informed deep learning approach for lithium-ion battery SOH prediction using incomplete discharge curves extracted from arbitrary voltage ranges, thereby reflecting realistic and heterogeneous operating conditions. The proposed method combines data-driven learning with physically motivated degradation dynamics to ensure consistent and reliable SOH estimation from partial discharge information, achieving a MAPE below 4$\%$. In addition, a real-time degradation trend estimation strategy is introduced to detect key aging transitions without requiring prior knowledge or historical data, making it applicable to a wide range of batteries. Overall, our approach enables SOH estimation from arbitrary discharge segments and a real-time degradation forecast that continuously integrates all usage, overcoming previous methods that rely on fixed protocols or early, non-adaptive predictions.
Begoña Ispizua, S. Gil-Lopez, Leire Arrizabalaga et al.· 0 citations
State of charge (SoC) represents the remaining capacity of a battery relative to its fully charged state and is a critical indicator of electric vehicle (EV) performance and driving range. Accurate SoC estimation is essential for effective battery management systems. Conventional methods such as Coulomb counting, open-circuit voltage, and Kalman filtering often suffer from reduced accuracy under varying operating conditions. long short-term memory (LSTM) networks effectively capture the nonlinear and temporal characteristics of battery behavior; however, the impact of activation function parameters within LSTM cells has not been thoroughly investigated. In this work, the impact of parameterized activation functions on the performance of LSTM models for SoC estimation in lithium-ion electric vehicle batteries is investigated. By introducing a scaling factor λ to the standard log sigmoid and tan sigmoid activation functions, the gradient profiles during training are modified. The empirical results demonstrate that modulating the scaling parameter λ directly reshapes the internal gradient landscape of the recurrent cells, fundamentally enhancing sequence tracking precision. The proposed approach achieves its peak SoC estimation performance at an optimal scaling value of λ= 0.5, yielding a maximum coefficient of determination (R2) of 0.9103 and a significantly reduced tracking error compared to baseline unscaled configurations. Furthermore, the parameterized gating architecture accelerates training convergence velocity by up to 45% while maintaining strict stability boundaries within a range of. These key numerical findings prove the structural effectiveness and universality of the proposed framework, establishing it as a highly accurate, computationally efficient solution suitable for online deployment in real-time electric vehicle battery management systems.
S. Bhavana, Vellure Rahul, V. Arunachalam et al.· Engineering Research Express· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
