Battery State Of Charge Research Articles

A Deep Learning Dependent Controller for Advanced Ultracapacitor SoC Concept to Increase Battery Life Span of Electric Vehicles

ABSTRACTOn a global scale, significant progress is being made in the field of battery technology for Electric Vehicle (EV) applications, driven by the need to combat carbon emissions and mitigate the effects of global warming. Accurately determining critical parameters, making sure battery storage system diagnosis, and functioning are correct are critical to the feasibility of EVs. However, insufficient supervision and safety measures for these storage systems may lead to serious problems like a thermal runaway, overcharging, overheating, cell imbalances, and fire hazards. To tackle these challenges, the presence of an efficient battery management system becomes paramount. By facilitating accurate monitoring, managing heat dissipation, regulating charging‐discharging procedures, guaranteeing battery safety, and offering protection measures, this system is essential to maximizing battery performance. The key intention of this innovative approach is to improve the longevity of EV batteries during extended periods of operation. By assessing vehicle velocity, remaining battery energy, and State of Charge (SoC), the proposed method effectively manages SoC in both the battery and ultracapacitor. This control is accomplished through a two‐stage convolutional neural network‐based system known as the Charge Sustain‐CNN Controller and the Charge Deplete‐CNN Controller. These controllers are fine‐tuned using the Fractional Latrans‐Hunt optimization (FLHO) algorithm to optimize the performance. The evaluation criteria encompass the battery and ultracapacitor's energy efficiency, as well as vehicle velocity. This novel approach significantly improves the energy storage system in EVs, leading to enhanced energy efficiency and prolonged battery life. Ultimately, experimental results validate the practicality and effectiveness of this developed method. Specifically, the proposed approach attained the Battery's SoC of 72.47%, 91.99%, and 82.88% for the different drive cycles including the FTP75, J1015, and UDDS, respectively.

Lithium battery SOC estimation based on improved sparrow search algorithm and backpropagation neural network

Accurate state-of-charge (SOC) estimation is crucial for optimal battery management. This paper proposes a novel method, the Improved Sparrow Search Algorithm-Backpropagation (ISSA-BP) neural network, to address the issue of low estimation accuracy encountered with a single BP neural network. ISSA is used to optimize the initial weights and thresholds of the BP neural network, effectively overcoming its tendency to get stuck in local minima. Compared to the single BP neural network, ISSA-BP demonstrates significantly improved accuracy under two conditions (DST and BJDST), with reductions in root mean square error by 64.0% and 50.9% and mean absolute error by 69.8% and 51.1%, respectively. These results highlight the superior robustness and accuracy of the ISSA-BP algorithm for SOC estimation in lithium batteries.

An Adaptive Combined Method for Lithium‐Ion Battery State of Charge Estimation Using Long Short‐Term Memory Network and Unscented Kalman Filter Considering Battery Aging

AbstractThe accurate estimation of battery state of charge (SOC) enables the reliable and safe operation of lithium‐ion batteries. Data‐driven SOC estimation is considered an emerging and effective solution. However, existing data‐driven SOC estimation methods typically involve direct estimation and lack effective feedback correction. Moreover, battery degradation poses additional challenges to accurate SOC estimation. Therefore, this study proposes an adaptive combined method for battery SOC estimation based on a long short‐term memory (LSTM) network and unscented Kalman filter (UKF) algorithm considering battery aging status. First, an LSTM model is constructed to characterize the battery's dynamic performance instead of traditional battery models. Then, the UKF algorithm is employed to perform SOC estimation through the feedback of terminal voltage prediction. To enhance estimation accuracy under different aging statuses, a proportional‐integral‐derivative controller is employed to correct the capacity fading during the SOC estimation process. Validation results indicate that the terminal voltage prediction model demonstrates exceptional robustness against interference from current and voltage noise. Compared to the traditional estimation method combining the deep learning model and Kalman filter algorithm, the proposed method demonstrates superior estimation accuracy under various complex operating conditions. Furthermore, the proposed method outperforms the traditional method in estimation performance during battery aging.

Estimation of Lithium-Ion Battery SOC Based on IFFRLS-IMMUKF

The state of charge (SOC) is a characteristic parameter that indicates the remaining capacity of electric vehicle batteries. It plays a significant role in determining driving range, ensuring operational safety, and extending the service life of battery energy storage systems. Accurate SOC estimation can ensure the safety and reliability of vehicles. To tackle the challenge of precise SOC estimation in complex environments, this study introduces an improved forgetting factor recursive least squares (IFFRLS) method, which integrates the Golden Jackal optimization (GJO) algorithm with the traditional FFRLS method. This integration is grounded in the formulation of a lithium battery state equation derived from a second-order RC equivalent circuit model. Additionally, the research utilizes the interactive multiple model unscented Kalman filter (IMMUKF) algorithm for SOC estimation, with experimental validation conducted under various conditions, including hybrid pulse power characterization (HPPC), urban dynamometer driving schedule (UDDS), and real underwater scenarios. The experimental results demonstrate that the SOC estimation method of lithium batteries based on IFFRLS-IMMUKF exhibits high accuracy and a favorable temperature applicability range.

FUZZY LOGIC-BASED POWER MANAGEMENT IN GRID-CONNECTED SOLAR ENERGY SYSTEMS

With the ever-increasing application of photovoltaic systems on the power grid, energy flow management and grid stability have become a key factor, especially under varying conditions like variable cloud cover and fluctuating load demands. The paper looks forward to proposing a fuzzy logic approach to the management of energy regarding a solar energy system connected to a grid, aiming at obtaining an optimised power distribution among PV generation, the grid, and battery storage. The proposed system will be driven by five input parameters, PV value, grid availability, load demand, battery state of charge, and tariff rate, to regulate the energy flow activity within different scenarios. The simulation results developed in the MATLAB Simulink environment proved the effectiveness of the applied controller in maintaining energy stability and fulfilling the requirements of a load within seven case studies for a 24-hour duration. The work points out the potential of fuzzy logic, besides reliability, in enhancing the efficiency of various renewable energy systems integrated with conventional energy supply grids.<p> </p><p><strong> Article visualizations:</strong></p><p><img src="/-counters-/soc/0799/a.php" alt="Hit counter" /></p>

Optimal Sizing, Energy Balance, Load Management and Performance Analysis of a Hybrid Renewable Energy System

This work utilizes the particle swarm optimization (PSO) for optimal sizing of a solar–wind–battery hybrid renewable energy system (HRES) for a rural community in Rivers State, Nigeria (Okorobo-Ile Town). The objective is to minimize the total economic cost (TEC), the total annual system cost (TAC) and the levelized cost of energy (LCOE). A two-step approach is used. The algorithm first determines the optimal number of solar panels and wind turbines. Based on the results obtained in the first step, the optimal number of batteries and inverters is computed. The overall results obtained are then compared with results from the Non-dominant Sorting Genetic Algorithm II (NGSA-II), hybrid genetic algorithm–particle swarm optimization (GA-PSO) and the proprietary derivative-free optimization algorithm. An energy management system monitors the energy balance and ensures that the load management is adequate using the battery state of charge as a control strategy. Results obtained showed that the optimal configuration consists of solar panels (151), wind turbine (3), inverter (122) and batteries (31). This results in a minimized TEC, TAC and LCOE of USD 469,200, USD 297,100 and 0.007/kWh, respectively. The optimal configuration when simulated under various climatic scenarios was able to meet the energy needs of the community irrespective of ambient conditions.

Multi-innovation adaptive Kalman filter algorithm for estimating the SOC of lithium-ion batteries based on singular value decomposition and Schmidt orthogonal transformation

The state of charge (SOC) of lithium battery is a key parameter for effective management of battery management systems (BMS). To address the problems of low precision, complex computation and poor robustness of traditional charging state estimation methods, an enhanced algorithm based on Unscented Kalman filter (UKF) is proposed. The singular value decomposition (SVD) method is adopted to ensure the normal operation of the Unscented Kalman Filter (UKF) algorithm even when the matrix P lacks positive semi-definiteness from a mathematical perspective. This enhancement significantly improves the theoretical robustness of UKF. Schmidt orthogonal transformation is concurrently used to reduce the computational complexity in the sampling point selection process, and the multi-innovation theory is combined with adaptive noise control to further improve the accuracy of SOC estimation. The algorithm is validated using the Urban Dynamometer Driving Schedule (UDDS) condition. The simulation results are excited using Singular value decomposition-multi-innovation adaptive Schmidt orthogonal unscented Kalman filter method (SVD-MIASOUKF). 0.95 % and 1.29 % of maximum errors are obtained at 25 °C and −10 °C, while the maximum errors are 2.46 %–2.99 % using SVD-UKF and UKF. The proposed approach shows faster convergence speed and higher estimation accuracy in comparison to traditional algorithms.

Enhanced composite controller for PV/PMSG/PEMFC and BESS‐based DC microgrids voltage regulation: Integrating integral terminal sliding mode controller and recursive backstepping controller

AbstractThe variability of renewable energy sources due to weather patterns often leads to a mismatch between power generation and consumption within microgrids (MGs). This challenge is exacerbated when integrating bio‐renewable units, complicating stability maintenance in MGs. This research work introduces a novel solution to address this issue: a composite controller merging an integral terminal sliding mode controller with a recursive backstepping controller for direct current MGs (DCMGs). The proposed DCMG incorporates solar photovoltaic units, wind farms based on permanent magnet synchronous generators, proton exchange membrane fuel cells fuelled by hydrogen gas, an electrolyser, battery energy storage systems, and DC loads. First, a comprehensive mathematical model for the components within the DCMG is developed to design the proposed composite controller. This controller not only overcomes the inherent limitations and convergence issues of conventional SMCs but also ensures stable DC‐bus voltage and maintains power balance across various operational conditions. Moreover, a fuzzy logic‐based energy management system is introduced to regulate power flow, considering factors like battery state of charge and renewable energy sources' total power output. The control Lyapunov function confirms the DCMG system's asymptotic stability. Finally, the proposed controller's effectiveness is validated through simulations on both MATLAB/Simulink and Arduino Mega 2650 processor‐in‐the‐loop platforms under various operational conditions. In both platforms, the proposed controller surpasses an existing controller in terms of settling time, overshoot, and tracking error of the DC‐bus voltage.

Collaborative Optimization Framework for Coupled Power and Transportation Energy Systems Incorporating Integrated Demand Responses and Electric Vehicle Battery State-of-Charge

The growing adoption of electric vehicles (EVs) and advancements in dynamic wireless charging (DWC) technology have strengthened the interdependence between power distribution networks (PDNs) and electrified transportation networks (ETNs), leading to the emergence of coupled power and transportation energy systems (CPTESs). This development introduces new challenges, particularly as DWC technology shifts EV charging demand from residential plug-in charging to charging-while-driving during commuting hours, causing simultaneous congestion in both ETNs and PDNs during peak times. The present work addresses this issue by developing a collaborative optimization framework for CPTESs that incorporates integrated demand responses (IDRs) and EVs battery state-of-charge (SOC). In the ETN, a multiperiod traffic assignment model with time-shiftable traffic demands (MTA-TSTD) is established to optimize travelers’ routes and departure times while capturing traffic flow distribution. Meanwhile, effective path generation models with EVs battery SOC are proposed to optimize charging energy during driving and construct the effective path sets for MTA-TSTD. In the PDN, a multiperiod optimal power flow model with time-shiftable power demands (MOPF-TSPD) is formulated to schedule local generators and flexible power demands while calculating the power flow distribution. To enhance temporal and spatial coordination in CPTESs, a distributed coordinated operation model considering IDRs is proposed, aiming to optimize energy consumption, alleviate congestion, and ensure system safety. Finally, an adaptive effective path generation algorithm and an ETN–PDN interaction algorithm are devised to efficiently solve these models. Numerical results on two test systems validate the effectiveness of the proposed models and algorithms.

Impact of external heating and state of charge on discharge performance and thermal runaway risk in 21700 Li-ion batteries

This study investigates the combined effects of external heating and State of Charge (SOC) on the discharge performance and thermal runaway risk of 21700 Li-ion batteries. Experiments subject commercially available 21700 cylindrical cells to various external heating conditions at different SOC levels (20, 40, 60, 80, and 100 %) while measuring discharge performance and thermal behavior at different discharge rates (0.2, 0.5, 1, and 1.5C). The study emphasizes the significance of Li-ions' spatial arrangement and maintaining electrical charge in the electrolyte to evaluate battery performance. Numerical simulations are then conducted to complement the experimental data and provide deeper insights. The results reveal a significant degradation in discharge performance with increasing external heat, characterized by voltage drops and reduced capacity. Cells with higher SOC levels exhibit more severe exothermic reactions during external heating, leading to a higher likelihood of thermal runaway. Cells operated at a moderate SOC of 40 % demonstrate a significantly lower risk of thermal runaway under similar heating conditions. The rapid rise in temperature at 100 % SOC of batteries showed a sharp increase of over 20 °C per second. Temperature spikes were noted at specific time intervals corresponding to different SOC levels: 100, 80, 60, 40, and 20. At this critical point, temperatures ranged from 135 to 182 °C, indicating potential thermal issues from internal short circuits causing separator melting. These findings highlight the critical role of SOC management in ensuring the safe and reliable operation of 21700 Li-ion batteries, particularly in applications involving elevated temperatures.

A fusion algorithm of multidimensional element space mapping architecture for SOC estimation of lithium-ion batteries under dynamic operating conditions

Accurate estimation of the state of charge (SOC) is pivotal for ensuring the reliable operation of lithium-ion batteries in electric vehicles, particularly under complex real-world conditions. This paper introduces a novel SOC estimation method named Multidimensional Elemental Space Mapping Architecture (MESMA), which integrates the battery equivalent circuit model with a data-driven approach to tackle adaptability under intricate conditions and high-dimensional input data correlation. Initially, a least squares method incorporating a forgetting factor is employed to identify the battery circuit model parameters and analyze their correlation with SOC. Subsequently, a feature fusion algorithm is introduced to discern spatial variables highly correlated with SOC by leveraging both original voltage and current data and circuit model parameters as inputs to a Convolutional Neural Network (CNN) model, and an eight-input and one-output spatially mapped feature CNN model is established. Finally, the XGBoost model is harnessed for battery SOC estimation. The effectiveness and adaptability of MESMA are validated using experimental data from both public single condition and mixed condition datasets, including FUDS, Mixed-1, etc. The results unequivocally demonstrate that MESMA accurately estimates the SOC of lithium-ion batteries under varying operating conditions. Furthermore, it exhibits remarkable adaptability and stability across different temperatures, effectively capturing SOC trends.

A real-world battery state of charge prediction method based on a lightweight mixer architecture

This paper proposes a lightweight model based on the improved Mixer architecture—TrendFlow-Mixer, designed for efficient prediction of the state of charge (SOC) of lithium-ion batteries. SOC accuracy is crucial for the safe operation, usage, and maintenance of power batteries. When predicting the SOC of real-world batteries, the algorithm's generalization, robustness, and computational efficiency across different battery types must be considered. To this end, TrendFlow-Mixer introduces targeted improvements to battery characteristics, significantly alleviating the Mixer architecture's lag in SOC prediction. The model's core structure integrates the Fast Fourier Transform and arrangement transformation convolutional structures. This allows for efficient extraction of domain-specific spatial features and enables cross-channel correlation interactions. This reduces the model's parameter size while enhancing its adaptability to new domains. The model quickly captures data trend changes and identifies data flow patterns, improving computational efficiency by 70 % compared to Transformer-based architectures. TrendFlow-Mixer employs a dual-prediction head, combining rapid feature change analysis with a nonlinear prediction output to generate SOC predictions. This design facilitates fine-tuning of the model's structure and parameters while enhancing overall flexibility. Experimental results show that in a laboratory dynamic condition dataset, the model achieves a minimum mean absolute error (MAE) of 0.11 %, with the maximum prediction error under extreme temperatures controlled within 4.66 %. In validation using real-world data from the BMW i3, the mean absolute percentage error remains around 1 %, with a minimum MAE of 0.465 %. The results demonstrate that TrendFlow-Mixer possesses high computational efficiency, excellent generalization, and adaptability, effectively predicting SOC trends.

УПРАВЛІННЯ ГІБРИДНОЮ СИСТЕМОЮ ЕЛЕКТРОЖИВЛЕННЯ ТВАРИННИЦЬКОЇ ФЕРМИ З ВІДНОВЛЮВАЛЬНИМИ ДЖЕРЕЛАМИ ТА ЕЛЕКТРОТРАНСПОРТОМ

The article considers the improvement of the control with using the generation of renewable energy sources forecast for a grid-connected a hybrid power supply system of a livestock farm with electric transport and a gas generator. The task is to form a graph of the state of charge of the main battery with a limitation of the depth of discharge with the maximum use of renewable sources energy. The calculation method of the state of charge of a battery and power consumption graph when working with the grid and in autonomous mode has been improved, with the definition of recommendations for charging electric transport. A mechanism has been developed for correcting the power consumption based on the deviation of the battery charge state relative to the specified value, with the correction disabled to implement the function of eliminating the export of excess energy to the grid or gas generator. This ensures the limitation of the gas generator power within certain limits and helps to limit the influence of generation and load deviations relative to the forecast on the battery discharge depth. The structure of the energy processes model in the system for the daily operation cycle has been developed. In the process of modeling, the deviation of renewable energy generation up to 20% and 10% was studied simultane-ously with a 10% increase in load.

Distributed Secondary Control of DC Microgrid with Power Management Based on Time-of-Use Pricing and Internal Price Rate

This paper presents a novel approach to manage distributed DC microgrids (DCMG) by integrating a time-of-use (ToU) electricity pricing scheme and an internal price rate calculation mechanism. The proposed power-management system is designed to effectively handle uncertainties such as utility grid (UG) availability, fluctuating electricity prices, battery state of charge (SOC) levels, and frequent plug-ins and plug-outs of electric vehicles (EVs). Uncertainties in DCMG systems often lead to inefficiencies, power imbalances, and inexact voltage regulation issues within DCMGs. In addition, to maintain the power balance and constant voltage regulation under various operational states, the proposed scheme also incorporates secondary control into the DCMG power-management system. Unlike the existing approaches that often fail to adapt dynamically to changing conditions, the proposed method is the first approach to consider the concept of internal price rate in designing the DCMG power management. To address this challenge, this approach proposes a more resilient power-management strategy to enhance the efficiency and adaptability of DCMG systems. Extensive simulations and experimental validations demonstrate the practicality and adaptability of the proposed control strategy under diverse test conditions, including operation transitions between grid-connected mode (GCM) and islanded mode (IM), low battery SOC condition, operation transition from the current control mode (CCM) to distributed secondary control mode (DSCM), and EV plug-in scenarios. The test results confirm that the proposed method enhances the reliability, efficiency, and economic viability of DCMG systems, making it a promising solution for future smart grid and renewable energy integrations.

Mechanism and Data-Driven Fusion SOC Estimation

An accurate assessment of the state of charge (SOC) of electric vehicle batteries is critical for implementing frequency regulation and peak shaving. This study proposes mechanism- and data-driven SOC fusion calculation methods. First, a second-order Thevenin battery model is developed to obtain the physical parameters of the battery. Second, data from the Thevenin battery model and data from four standard cycling conditions in the electric vehicle industry are added to the dataset of the feed-forward neural network data-driven model to construct the test and training sets of the data-driven model. Finally, the error of the mechanism and data-driven fusion modeling method is quantitatively analyzed by comparing the estimation error of the method for the battery SOC at different temperatures with the accuracy of the data-driven SOC estimation method. The simulation results show that the root mean square error, the mean age absolute error, and the maximum error of mechanism and data-driven method for the estimation error of battery SOC are lower than those of the data-driven method by 0.9%, 0.65%, and 1.3%, respectively. The results show that the mechanism and data-driven fusion SOC estimation method has better generalization performance and higher SOC estimation accuracy.

Methods for faster estimation of the entropy profile of a lithium-ion battery: A comparison of accelerated potentiometry and the estimation of entropy through thermal signatures

The operating temperature of a lithium-ion battery (LIB) has strong effects on its electrochemical performance, safety, and lifetime. Reliable predictions of cell temperature and heat generation rate are required for the design and thermal management of battery systems. The entropy variation of a LIB has a significant influence on the heat generation and the cell temperature variation, especially at a lower C-rate. Since the entropy is a function of State-of-Charge (SoC), and may change during ageing, the entropy profile may as well be used as an indicator for battery State-of-Health diagnostics. The present experimental methods, such as potentiometric or calorimetric methods, for determining the entropy variation throughout a battery's full SoC window are time-consuming and require specialized equipment with good thermal insulation and instrumentation. Hence, faster and more convenient methods are needed. In this paper, we compare an accelerated potentiometric method with a new entropy characterization method where the entropy profile is extracted from the thermal signature of a LIB during charge and discharge at low C-rates. The accelerated potentiometric method aims to obtain the entropy from thermal cycling while the cell is still not completely relaxed to its stable OCV. The thermal signature method monitors the variations of a cell's outer surface temperature during a low constant current charge or discharge, from which the continuous variation of entropy with the SoC can be extracted. The obtained entropy profile was validated through a modeling approach that combines a P2D-electrochemical model for battery operation and a 3D-finite-element model for the thermal behavior during battery operation. Good agreement between the model predictions and experiments was achieved on the temporal variation of the cell's outer surface temperature.

Multi-temperature capable enhanced bidirectional long short term memory-multilayer perceptron hybrid model for lithium-ion battery SOC estimation

In this study, we propose a novel hybrid modeling framework for State of Charge (SOC) estimation across a broad temperature spectrum. First, we build a hybrid model to optimize stacked layers of stacked bidirectional long short term memory networks by introducing dropout mechanisms. At the same time, we also optimize the traditional multi-layer perceptron model to ResMLP, which is improved by introducing residual linkage, and then integrate the two optimization models. Finally, the synergistic effect and attention mechanism of genetic algorithm and particle swarm optimization are used to optimize its parameters. We then rigorously tested the model on nine datasets, including HPPC, DST and BBDST, at different temperatures of 5 °C, 15 °C and 35 °C. Using MAE, RMSE and MAXE benchmarks, our research results show that the proposed hybrid model outperforms the benchmark algorithm, achieving significantly enhanced performance and higher accuracy, and the maximum SOC estimation error is kept below 4.53 %. In addition, experimental evaluation at different temperatures shows the robustness and adaptability of the proposed algorithm.

Data driven approach for state-of-charge estimation of lithium-ion cell using stochastic variational Gaussian process

Modern electric vehicles rely on lithium-ion batteries. Electric vehicles (EVs) utilize intricate battery packs that require the oversight of a battery management system (BMS) to ensure safe, reliable, and efficient operation. The state estimation of the battery pack is an important responsibility carried out by the BMS. Accurately estimating the State-of-Charge (SOC) poses a considerable engineering challenge since it cannot be directly measured at the battery terminals. This study introduces a novel data-driven methodology for accurately estimating the SOC in Lithium-ion batteries, with a particular focus on its relevance in EV contexts. The framework is built upon the Stochastic Variational Gaussian Process (SVGP)—an improved version of the conventional Gaussian Process (GP). Unlike GP, It can scale up to very large datasets. Furthermore, SVGP uses variational inference to estimate the posterior instead of calculating, making it computationally efficient. The model training process involves using laboratory test data from an 18650 Lithium-ion Nickel Manganese Cobalt (NMC) cell that has gone through eight dynamic drive cycles. The findings showcase a remarkable level of precision in estimation, as indicated by an average R2 value of 0.99 and a Mean Square Error (MSE) as low as 0.02.

Smart home power management algorithm using real-time model predictive control for a stand-alone PV system with battery energy storage

A smart home power management system is critical for stand-alone home-photovoltaic (HPV) with battery energy storage. Existing approaches often focus on maximizing power extraction from PV systems without considering real-time power adjustments or battery state of charge (SoC), which can lead to over-current or over-voltage issues that damage the battery. To address these limitations, this paper proposes a home power management algorithm that dynamically adjusts the power flow between the PV system, home loads, and the battery based on real-time system power measurements and battery SoC. This dynamic adjustment ensures an uninterrupted power supply to the home loads while maintaining battery safety. The proposed home manager algorithm features multiple operating modes: Maximum power point (MPP) charging, partial charging, fast charging, float charging, and partial discharging. Each mode is integrated with its dedicated model predictive controller (MPC) to achieve its specific control objective. Finally, through a semi-experimental simulation using a process-in-the-loop (PIL) test approach with the embedded board eZdsp TMS320F28335, testing under various irradiance levels shows that the home manager achieves significant improvement over conventional approaches. For instance, over the MPP mode it achieve a power efficiency of 99.36% with a 2.05% SoC increase, while fast charging mode resulted in 87.44% efficiency with an 11.2% SoC increase. However, float charging mode maintained an 87.27% efficiency with a 2.6% SoC increase, and partial discharging led to a 1.3% SoC decrease. The overall battery efficiency reached 96.45%, demonstrating the algorithm’s ability to optimize power flow, ensure a reliable energy supply, and maintain battery safety under varying weather conditions.

Real-time electrochemical-strain distribution and state-of-charge mapping via distributed optical fiber for lithium-ion batteries

Deep learning has opened new avenues for estimating the dynamic state of charge in batteries. However, hindered by macroscopic and limited electrochemical inputs, data-driven models still struggle to accurately capture local states inside batteries. This study aims to leverage distributed fiber optic sensing and long short-term memory to enhance the accuracy and reliability of the state of charge estimation and to visualize its distribution. First, the internal strain is closely linked to the lithium embedded state of graphite particles, with a coefficient of 0.992 between strain amplitude and capacity over long cycles. Incorporating strain as an additional physical parameter significantly improves accuracy. The proposed model achieves a prediction error of only 2.01 %, representing a 41.2 % improvement compared to models that exclude stain data. Factors such as current and ambient temperature are considered to prove the effectiveness of this method. Furthermore, by combining the trained model with internal strain distribution, the developed intuitive imaging for local state visualization reveals aging tendencies and uneven behavior in lithium-ion batteries. This predictive and imaging approach offers valuable insights for local state analysis and advances battery research and design.