This paper introduces a novel Lithium-Ion Battery (LIB) State-of-Charge (SOC) estimation approach that integrates Akima–Savitzky–Golay curve reconstruction with a Bayesian-optimized, adaptive Extended Kalman Filter (EKF). The method addresses crucial SOC estimation challenges by means of three foundational advancements: (i) a refined open-circuit voltage (OCV)-SOC curve reconstruction grounded in Akima interpolation coupled with Savitzky–Golay filtering, (ii) an adaptive EKF weighting strategy, and (iii) systematic hyperparameter value optimization executed through Bayesian optimization. Comprehensive performance validation utilizes an extensive dataset collected from LG HG2 18650 cells across temperatures of −20 °C to 40 °C, incorporating multiple standard driving cycles—namely HPPC, UDDS, HWFET, LA92, and US06 cycles. The proposed method achieves an improved estimation accuracy with an average Root Mean Square Error (RMSE) of 2.65% over the different operating conditions and temperature variations. Notably, the method markedly enhances SOC estimation reliability in the critical mid-SOC range (20–80%), while preserving the computational overhead necessary for real-time integration into Battery Management Systems (BMSs). The adaptive weighting successfully compensates for the present physical limitations, thereby delivering a resilient SOC estimation tailored for Electric Vehicle (EV) battery applications.

Batteries are a complex electrochemical device that exhibit non-linearity and stochastic behavior which rely upon the operational conditions and environmental factors, making battery monitoring a vital feature throughout its application. This paper introduces a novel web-based battery monitoring and control system that utilizes Long Range (LoRa) communication technology, an integral part of the Internet of Things (IoT). The system is implemented with the ESP32 microcontroller, with an emphasis on affordability in broader applications. The system provides comprehensive real-time online data by integrating a combination of multiple sensors. The proposed system seeks to address the limitations of existing communication technology by utilizing the benefits of LoRa, a technology that facilitates effective long-range, low-energy communication which makes it particularly well-suited for real-time monitoring applications. In addition, a control operation enables users to regulate crucial aspects of batteries, such as their charging and discharging. The research conducted a meticulous experimental evaluation of the proposed system at different operations, and the results successfully aligned with the main objective and aims of the research. The proposed system successfully enables real-time remote monitoring and user control, long-term data visualization through data logging, and assessment of battery conditions. Data logging was introduced to enhance the utilization of future battery evaluation, such as State-of-Charge (SOC), State-of-Health (SOH) and Remaining Useful Life (RUL). As a result, the developed system makes it suitable for many applications requiring effective energy storage solutions, such as renewable energy and Electric Vehicle (EV) applications.

In today’s modern society, the importance of transportation is undeniable. While Brunei is recognized for its abundant oil and gas reserves and fuel subsidies f

Accurate State-of-Charge (SOC) estimation of batteries remains challenging across aging states, temperature variations, and operating conditions. This paper introduces a novel Aging-Aware Hypernetwork Long Short-Term Memory with Multi-Constraint Physics-Informed Neural Network (AAH-LSTM-PINN) aimed at addressing some of the most pertinent challenges of estimating battery SOC through three key contributions. First, the introduction of a continuous four-component age parameter to quantify the temporal progression, the effects of capacity fade, resistance growth, and thermal stress. Second, the ability of a hypernetwork architecture to generate age-specific adaptation weights for explicit feature transformation. Third, the incorporation of physics-informed constraints based on Coulomb Counting (CC), Equivalent Circuit Model (ECM), and Arrhenius temperature with weights optimized using a three-phase systematic grid search. The effectiveness of the AAH-LSTM-PINN was evaluated on the Lithium-ion Battery (LIB) dataset under three extreme scenarios, which are temperature interpolation with a 0°C holdout, temperature extrapolation with a -20°C holdout, and drive cycle generalization. AAH-LSTM-PINN achieved 0.516% average Root Mean Square Error (RMSE) which gives a 42.8% improvement over age-agnostic LSTM. Age awareness, hypernetwork adaptation, and physics-informed constraints implementation contributed to 27.8%, 15.3%, and 6.5% improvement respectively. The AAH-LSTM-PINN framework has a real-time inference capability of 11.94 μs, which is appropriate for embedded Battery Management Systems (BMS) while also offering robust generalization to unseen situations. This work advanced the battery SOC estimation by showing that accurate state estimation across different aging states and operational conditions is possible when explicit age-aware mechanisms, coupled with deep learning and physics-informed regularization are employed.