Battery State Of Health Research Articles

Exploration of maintenance technology of aviation new energy power battery under machine learning

The existing prediction models on the market have uncertainties and errors, which cannot accurately predict the remaining life of batteries. These problems lead to excessive or delayed maintenance of batteries, thereby affecting their performance and safety. Therefore, machine learning-based maintenance technology for aviation new energy power batteries has become a new research direction. This study used machine learning algorithms to construct a battery status classification and prediction model by collecting a large amount of aviation new energy power battery data. Through experiments, the model significantly improved its accuracy in battery status recognition tasks, with a maximum of 96%. It can accurately identify tasks such as battery health status, lifespan prediction, and fault detection. The model had made progress in balancing accuracy and recall, with a high F1 value. This meant that the model could accurately identify the abnormal state of the battery while minimizing misjudgment of normal batteries as much as possible. These research results provided important support for battery maintenance in the aviation field, with the potential to improve battery availability, extend service life, and ensure flight safety while reducing maintenance costs.

Physics-Informed Design of Hybrid Pulse Power Characterization Tests for Rechargeable Batteries

Industry-standard diagnostic methods for rechargeable batteries, such as hybrid pulse power characterization (HPPC) tests for hybrid electric vehicles, provide some indications of state of health (SoH), but lack a physical basis to guide protocol design and identify degradation mechanisms. We develop a physics-based theoretical framework for HPPC tests, which are able to accurately determine specific mechanisms for battery degradation in porous electrode simulations. We show that voltage pulses are generally preferable to current pulses, since voltage-resolved linearization more rapidly quantifies degradation without sacrificing accuracy or allowing significant state changes during the measurement. In addition, asymmetric amounts of information gain between charge /discharge pulses are found from differences in electrode kinetic scales. We demonstrate our approach of physics-informed HPPC on simulated Li-ion batteries with nickel-rich cathodes and graphite anodes. Multivariable optimization by physics-informed HPPC rapidly determines kinetic parameters that correlate with degradation phenomena at the anode, such as solid-electrolyte interphase (SEI) growth and lithium plating, as well as at the cathode, such as oxidation-induced cation disorder. If validated experimentally, standardized voltage protocols for HPPC tests could play a pivotal role in expediting battery SoH assessment and accelerating materials design by providing new electrochemical features for interpretable machine learning of battery degradation.

Data-driven battery health state estimation based on charging and switching cabinets

Accurate evaluation of the battery’s state of health (SOH) in the charging and switching cabinet is crucial to ensure the battery operates safely and reliably, while also reducing maintenance costs for the battery system. A support vector regression technique, utilising the sparrow algorithm optimisation, is suggested to improve the precision of assessing the battery’s state of health in the charging and switching cabinet. This algorithm tackles the task of identifying parameters in the conventional model. Analysing the ageing dataset of lithium batteries is the initial stage to determine the health parameters that signal the battery’s health state. The support vector machine regression algorithm is employed to select the kernel function and penalty factor, which are fine-tuned using the sparrow optimisation technique. The data is utilised to create the SSA-SVR model. The battery health status of the charging and switching cabinet is assessed. The study shows that the enhanced support vector regression model can effectively monitor the status of lithium-ion batteries and achieve superior estimation results for different types of batteries.

Health State Assessment of Lithium-Ion Batteries Based on Multi-Health Feature Fusion and Improved Informer Modeling

Accurately assessing the state of health (SOH) of lithium batteries is of great significance for improving battery safety performance. However, the current assessment for SOH suffers from the difficulty of selecting health features and the lack of uncertainty using data-driven methods. To this end, this paper proposes a health state assessment method for lithium-ion batteries based on health feature extraction and an improved Informer model. First, multiple features that can reflect the SOH of lithium-ion batteries were extracted from the charging and discharging time, the peak value of incremental capacity curve (ICC), and the inflection point value of differential voltage curve, etc., and the correlation between multiple health features and the health state was evaluated by gray correlation analysis. Then, an improved Informer model is proposed to establish a health state estimation method for lithium-ion batteries. Finally, the proposed algorithm is tested and validated using publicly available battery charge/discharge datasets and compared with other algorithms. The results show that the method in this paper can realize high-precision SOH prediction with a root-mean-square error (RMSE) of 0.011, and the model fit reaches more than 98%.

State of Health (SOH) Estimation of Lithium-Ion Batteries Based on ABC-BiGRU

As a core component of new energy vehicles, accurate estimation of the State of Health (SOH) of lithium-ion power batteries is essential. Correctly predicting battery SOH plays a crucial role in extending the lifespan of new energy vehicles, ensuring their safety, and promoting their sustainable development. Traditional physical or electrochemical models have low accuracy in measuring the SOH of lithium batteries and are not suitable for the complex driving conditions of real-world vehicles. This study utilized the black-box characteristics of deep learning models to explore the intrinsic correlations in the historical cycling data of lithium batteries, thereby eliminating the need to consider the internal chemical reactions of lithium batteries. Through Pearson correlation analysis, this study selects health indicators (HIs) from lithium battery cycling data that significantly impact SOH as input features. In the field of lithium batteries, this paper applies ABC-BiGRU for the first time to SOH prediction. Compared with other recursive neural network models, ABC-BiGRU demonstrates superior predictive performance, with maximum root mean square error and mean absolute error of only 0.016799317 and 0.012626847, respectively.

Hybrid Random Forest Regression and Artificial Neural Networks for Modelling and Monitoring the State of Health of Li-Ion Battery

Lithium-ion batteries play a significant role in modern energy storage systems for a number of applications, including renewable energy installations, electric cars, and portable devices. In order to guarantee the long-term dependability and safety of these battery packs, comprehensive modelling and monitoring approaches are required for accurate State of Health (SoH) evaluation. This research suggests an innovative strategy that combines the strengths of Random Forest Regression (RFR) and Artificial Neural Networks (ANN) for reliable Li-ion battery SoH modelling and monitoring. The research starts with the collection of thorough Li-ion battery data, which includes voltage, current, temperature, and cycling characteristics. The battery dataset's nonlinear relationships are captured utilising RFR as the main modelling method. In terms of feature selection and prediction precision, RFR's ensemble of decision trees shines, making it a strong contender for modelling complex battery behaviour. The SoH prediction is then enhanced by the use of ANN, a deep learning framework renowned for its ability to extract detailed patterns from data. The characteristics of RFR are complemented by ANN's capacity to discover hidden features and nonlinear correlations, improving the overall prediction performance. The suggested hybrid approach, that combines RFR and ANN, is trained and verified utilising a diverse database acquired from Li-ion battery sources under operational circumstances. To assess the prediction accuracy of a suggested framework measures like Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R-squared (R2) values are employed. The outcomes show that the hybrid RFR-ANN model works better than the individual RFR and ANN models, producing better SoH predictions. A viable solution for real-time Li-ion battery health monitoring is provided by this combination of conventional ML and deep learning approaches, which demonstrates the synergy among complexity and interpretability. This research advances battery SoH assessment and paves the way for the practical incorporation of precise monitoring systems into applications like electric vehicles, where timely and accurate SoH data is essential for maximising battery performance and extending operational lifespan.

An Adaptive Energy Management Approach for Battery-Supercapacitor Hybrid Energy Storage System

Energy storage systems (ESS) are indispensable in daily life and have two types that can offer high energy and high power density. Hybrid energy storage systems (HESS) are obtained by combining two or more energy storage units to benefit both types. Energy management systems (EMS) are essential in ensuring HESS's reliability, high performance, and efficiency. One of the most critical parameters for EMS is the battery state of health (SoH). Continuous monitoring of the SoH provides essential information regarding the system's status, detects unusual performance degradations and enables planned maintenance, prevents system failures, helps keep efficiency at a consistently high level, and helps ensure energy security by reducing downtime. The SoH parameter depends on parameters such as Depth of Discharge (DoD), charge and discharge rate (C-Rate), and temperature. Optimal values of these parameters directly affect the lifetime and operating performance of the battery. The proposed Adaptive Energy Management System (AEMS) uses the SoH parameter of the battery as the control input. It provides optimal control by dynamically updating the C-Rate and DoD parameters. In addition, the supercapacitor integrated into the system with filter-based power separation prevents deep discharge of the batteries. Under the proposed AEMS control, HESS has been observed to generate 6.31% more energy than a system relying solely on batteries. This beneficial relationship between supercapacitors and batteries efficiently managed by AEMS opens new possibilities for advanced energy management in applications ranging from electric vehicles to renewable energy storage systems.

Battery state of health estimation across electrochemistry and working conditions based on domain adaptation

Accurately assessing the health status of lithium-ion batteries is essential to ensure their safe and efficient application in electric vehicles and energy storage systems. Although various methods have been proposed to achieve battery state of health (SOH) estimation, most of them are only applicable to certain battery types or operating conditions. To address this issue, a novel method is proposed in this study, which leverages data-driven techniques and domain adaptation to cater to different battery electrochemistry and operating conditions. First, the evolution of battery aging is investigated and the incremental capacity sequence with ample aging information is extracted to indicate battery health. Then, the convolutional neural network and bidirectional long-short term memory network are combined to capture the nonlinear relationship between the input sequence and battery SOH. Next, a domain adaptation (DA) based on adversarial training is employed to enhance model adaptability by realizing domain-invariant features extraction. Furthermore, data augmentation is utilized to address data imbalance caused by significant lifespan disparity among different batteries. Finally, datasets with different battery types and aging conditions are used to verify the proposed method. The average estimation error of battery SOH can be controlled within 4.77 %, with over 30 % reduction contributed by the DA.

Towards a State of Health Definition of Lithium Batteries through Electrochemical Impedance Spectroscopy

In the era of Industry 4.0, achieving optimization in production and minimizing environmental impact has become vital. Energy management, particularly in the context of smart grids, plays a crucial role in ensuring sustainability and efficiency. Lithium-ion batteries have emerged as a leading technology for energy storage due to their versatility and performances. However, accurately assessing their State of Health (SOH) is essential for maintaining grid reliability. While discharge capacity and internal resistance (IR) are commonly used SOH indicators, battery impedance also offers valuable insights into aging degradation. This article explores the use of Electrochemical Impedance Spectroscopy (EIS) to define the SOH of lithium batteries. By analyzing impedance spectra at different frequencies, a comprehensive understanding of battery degradation is obtained. A life cycle analysis is conducted on cylindrical Li–Mn batteries under various discharge conditions, utilizing EIS measurements and an Equivalent Circuit Model (ECM). This study highlights the differential effects of aging on battery characteristics, emphasizing the variations at different life stages and the behavior changes on each region of the impedance spectrum. Furthermore, it demonstrates the efficacy of EIS and the advantages of this technique compared to the solely IR measurements used in tracking SOH over time. This research contributes to advancing the understanding of lithium battery degradation and underscores the importance of EIS in defining their State of Health for Smart Grids applications.

Lithium-ion battery SOH prediction based on VMD-PE and improved DBO optimized temporal convolutional network model

Accurately estimating the state of health (SOH) in lithium-ion batteries is crucial for optimizing performance, cost management, enhancing safety, extending lifespan, and promoting environmental sustainability. However, due to factors such as capacity regeneration, battery capacity degradation data exhibits nonlinear and non-stationary characteristics, making it challenging to accurately predict SOH. In order to improve prediction accuracy, this paper proposes a novel SOH prediction model based on VMD-PE-IDBO-TCN. Firstly, the variational mode decomposition-permutation entropy (VMD-PE) method is innovatively introduced to decompose the original battery SOH data and reorganize it into a series of subsequences, reducing the impact of non-stationary components on the prediction results. Moreover, temporal convolutional network (TCN) prediction models are used for each subsequence, and an improved dung beetle optimization (IDBO) algorithm is used to optimize the TCN parameters, where this IDBO algorithm incorporates SPM chaotic mapping, golden sine strategy, and adaptive Gaussian-Cauchy mixed mutation perturbation. The IDBO algorithm rapidly and accurately identifies the optimal parameter combination, significantly enhancing the predictive performance of the TCN model. Finally, the predicted values of each subsequence are superimposed to obtain the final prediction result. Two different lithium-ion battery datasets from NASA and CALCE are used for experimental validation. Experimental results show that the proposed model has higher prediction accuracy, with a maximum RMSE of only 0.0072 and a maximum MAPE of only 0.67 %, and has good adaptability to different types of batteries and batteries operating at high temperatures.

Driving behavior-guided battery health monitoring for electric vehicles using extreme learning machine

An accurate estimation of the state of health (SOH) of batteries is critical to ensuring the safe and reliable operation of electric vehicles (EVs). Feature-based machine learning methods have exhibited enormous potential for rapidly and precisely monitoring battery health status. However, simultaneously using various health indicators (HIs) may weaken estimation performance due to feature redundancy. Furthermore, ignoring real-world driving behaviors can lead to inaccurate estimation results as some features are rarely accessible in practical scenarios. To address these issues, we proposed a feature-based machine learning pipeline for reliable battery health monitoring, enabled by evaluating the acquisition probability of features under real-world driving conditions. We first summarized and analyzed various individual HIs with mechanism-related interpretations, which provide insightful guidance on how these features relate to battery degradation modes. Moreover, all features were carefully evaluated and screened based on estimation accuracy and correlation analysis on three public experimental battery degradation datasets. Finally, the scenario-based feature fusion and acquisition probability-based practicality evaluation method construct a useful tool for feature extraction with consideration of driving behaviors. This work highlights the importance of balancing the performance and practicality of HIs during the development of feature-based battery health monitoring algorithms.

Joint Estimation of SOC and SOH for Lithium-Ion Batteries Based on Dual Adaptive Central Difference H-Infinity Filter

The accurate estimation of the state-of-charge (SOC) and state-of-health (SOH) of lithium-ion batteries is crucial for the safe and reliable operation of battery systems. In order to overcome the practical problems of low accuracy, slow convergence and insufficient robustness in the existing joint estimation algorithms of SOC and SOH, a Dual Adaptive Central Difference H-Infinity Filter algorithm is proposed. Firstly, the Forgetting Factor Recursive Least Squares (FFRLS) algorithm is employed for parameter identification, and an inner loop with multiple updates of the parameter estimation vector is added to improve the accuracy of parameter identification. Secondly, the capacity is selected as the characterization of SOH, and the open circuit voltage and capacity are used as the state variables for capacity estimation to improve its convergence speed. Meanwhile, considering the interaction between SOC and SOH, the state space equations of SOC and SOH estimation are established. Moreover, the proposed algorithm introduces a robust discrete H-infinity filter equation to improve the measurement update on the basis of the central differential Kalman filter with good accuracy, and combines the Sage–Husa adaptive filter to achieve the joint estimation of SOC and SOH. Finally, under Urban Dynamometer Driving Schedule (UDDS) and Highway Fuel Economy Test (HWFET) conditions, the SOC estimation errors are 0.5% and 0.63%, and the SOH maximum estimation errors are 0.73% and 0.86%, indicating that the proposed algorithm has higher accuracy compared to the traditional algorithm. The experimental results at different initial values of capacity and SOC demonstrate that the proposed algorithm showcases enhanced convergence speed and robustness.

Effects of floating charge ageing on electrochemical impedance spectroscopy of lead-acid batteries

The lead-acid battery as a direct current emergency power supply to the substation is subjected to long-term floating charge ageing, which is a special working condition. However, there is limited research on estimating the battery life for floating charge ageing. Compared to other parameters, Electrochemical Impedance Spectroscopy (EIS) is closely related to changes in the battery. This paper investigates a simple and effective method based on EIS to estimate the state of health (SOH) of lead-acid batteries used in substation backup power supply. In this paper, a high-temperature floating charge ageing experiment was carried out to simulate the ageing process of backup power supply in a substation and shorten the experimental time. The Pearson correlation coefficient of impedance from 0.01 Hz to 1000 Hz was calculated with the battery's SOH, and the impedances at three frequencies (19.860 Hz, 9.931 Hz, and 3.946 Hz) with high correlation coefficients were selected as indicators of battery SOH. The proposed health indicators and method were validated by batteries retired from the substations, and the results showed that the impedances selected could be used as indicators of lead-acid batteries, with an average estimation error of 2.723 %.

Detailed Analysis of Li-ion Batteries for Use in Unmanned Aerial Vehicles

With the developing technologies in the aviation, the transition to more electrical systems is increasing day by day. For this reason, research on the development of batteries has accelerated. Nowadays, Lithium ion (Li-ion) batteries are more widely preferred due to their energy-to-weight ratio and advantages such as having a lower self-discharge rate when not working compared to other battery technologies. Batteries convert the stored chemical energy into electrical energy and heat is released as a result of the chemical reactions. The heat released negatively affects the battery's lifespan, charging/discharging time and battery output voltage. The battery must be modeled correctly to see these negative effects and intervene in time. In this way, negative situations that may occur in the battery can be intervened at the right time without any incident. 
 In this study, the unmanned aerial vehicle (UAV) is powered by Li-ion batteries. It is simulated in Matlab/Simulink environment using the electrical equivalent circuit. A detailed model is created, taking into account temperature, state of charge (SoC), cell dynamics and operating functions. To estimate state of health (SoH) of the battery, resistance values must be known. Resistance and capacity values in the equivalent circuit of the Li-ion battery are obtained with the help of the simulation model. So, the SoH of the Li-ion batteries can be accurately predicted with the results obtained.

Rapid estimation of battery state of health using partial electrochemical impedance spectra and interpretable machine learning

The longevity and efficacy of lithium-ion batteries diminish over time, making accurate estimation of their health state essential. Traditional methods, based on long-term charge and discharge data, are limited in speed and data richness. This study introduces a novel approach using partial Electrochemical Impedance Spectroscopy (EIS) and interpretable machine learning for rapid and precise battery health state estimation. Our method selects partial impedance spectra, in contrast to conventional techniques that rely on global impedance spectra, and applies interpretable machine learning. The SHAP (SHapley Additive exPlanations) framework is used to interpret the contribution of each impedance feature, enhancing model transparency and reliability. Comparative evaluations demonstrate that SHAP-enhanced partial impedance spectra provide higher prediction accuracy and are more quickly obtained than global spectra. This innovative application of interpretable machine learning in acquiring partial impedance spectra represents a significant advancement in battery health state estimation. Our findings propose a new paradigm in employing EIS for battery health analysis, promising enhanced precision and speed in practical applications.

Lithium-ion battery state of health prognostication employing multi-model fusion approach based on image coding of charging voltage and temperature data

The employment of readily obtainable parameters, including voltage and temperature, derived from the battery management system facilitates the real-time evaluation of lithium-ion batteries health status. However, the complex aging mechanisms and noise interference inherent in lithium-ion batteries present substantial challenges to accurate estimation. Hence, this research proposes a multi-model fusion approach utilizing Gramian Angular Field encoding to accurately predict the health status of lithium-ion batteries. Battery voltage and temperature data are acquired through system aging experiments. The Gramian Angular Field-based image encoding transforms these data into images, accentuating the subtle characteristics of the data and thereby enhancing its recognizability by neural networks. Subsequently, two-dimensional Convolutional Neural Networks are employed to extract features from the images, followed by one-dimensional Convolutional Neural Networks to reduce the dimensions of the feature matrix. The battery health status is then predicted utilizing Long Short-term Memory Networks. The culmination is the evaluation of the model performance through the application of quantitative error metrics. The study results show that the method can pinpoint the prediction error to within 2%, significantly improving accuracy over traditional prediction methods. It proves the great potential of direct data, such as voltage and temperature, in predicting battery health.

State of health prediction of lithium-ion batteries under early partial data based on IWOA-BiLSTM with single feature

The safe and stable operation of electric vehicles relies on fast and accurate predictions of the state of health (SOH) of the battery. To address challenges such as limited availability of extensive battery aging data or data with informative missingness, the novel SOH prediction method based on the improved method whale optimization algorithm (IWOA)-Bi-directional Long Short-Term Memory (BiLSTM) with strong correlated single aging feature is proposed. Firstly, to accurately predict the accelerated degradation process of the battery capacity, the knee-point in the capacity degradation curve is identified as a starting point for SOH prediction by Bacon-Watts model. Next, a small number of early partial aging features of the battery cycle are extracted, such as time of charging or discharging, and various correlation analysis methods are used to select the single feature with the highest correlation with capacity degradation to reduce the computational complexity of multiple feature factors. Finally, BiLSTM model is established to predict battery SOH. In addition, in order to improve the efficiency of the adjustment for hyperparameters, IWOA is proposed to optimize the BiLSTM’s hyperparameters. Compared to the traditional Whale Optimization Algorithm (WOA), IWOA has better global search capability, robustness, and efficiency through enhancements in search strategy, mutation operation, adaptive parameter adjustment, and performance optimization. The proposed method is validated using battery datasets from NASA and CALCE. Compared with BiLSTM and WOA-BiLSTM, the simulation results indicate that the MSE of SOH prediction based on IWOA-BiLSTM method mostly remains below 0.05, and index of agreement (IA) basically maintains higher than 99%.

Recurrent Neural Networks for Estimating the State of Health of Lithium-Ion Batteries

Rapid technological changes and disruptive innovations have resulted in a significant shift in people’s behavior and requirements. Electronic gadgets, including smartphones, notebooks, and other devices, are indispensable to everyday routines. Consequently, the demand for high-capacity batteries has surged, which has enabled extended device autonomy. An alternative approach to address this demand is battery swapping, which can potentially extend the battery life of electronic devices. Although battery sharing in electric vehicles has been well studied, smartphone applications still need to be explored. Crucially, assessing the batteries’ state of health (SoH) presents a challenge, necessitating consensus on the best estimation methods to develop effective battery swap strategies. This paper proposes a model for estimating the SoH curve of lithium-ion batteries using the state of charge curve. The model was designed for smartphone battery swap applications utilizing Gated Recurrent Unit (GRU) neural networks. To validate the model, a system was developed to conduct destructive tests on batteries and study their behavior over their lifetimes. The results demonstrated the high precision of the model in estimating the SoH of batteries under various charge and discharge parameters. The proposed approach exhibits low computational complexity, low cost, and easily measurable input parameters, making it an attractive solution for smartphone battery swap applications.

Application of machine learning in ultrasonic diagnostics for prismatic lithium-ion battery degradation evaluation

Lithium-ion batteries are essential for electrochemical energy storage, yet they undergo progressive aging during operational lifespan. Consequently, precise estimation of their state of health (SOH) is crucial for effective and safe operation of energy storage systems. This paper investigates the viability of ultrasound-based methods for assessing the SOH of prismatic lithium-ion batteries. In the experimental framework, a designated prismatic lithium-ion battery was subjected to numerous charging and discharging cycles using a battery cycling system. Subsequently, ultrasonic detection experiments were conducted to record the waveforms of the transmitted and received signals. These signals were then processed through wavelet transforms to extract signal amplitude and time-of-flight data. To analyse these data, we applied four algorithms: linear regression, support vector machines, Gaussian process regression, and neural networks. The predictive performance of each algorithm was evaluated through extensive experimentation and analysis. The combination of ultrasonic signals with computational models has emerged as a robust technique for precise battery degradation assessment, suggesting its potential as a standard in battery health evaluation methods.

A self-attention knowledge domain adaptation network for commercial lithium-ion batteries state-of-health estimation under shallow cycles

Accurate state-of-health (SOH) estimation is crucial for the safety, efficiency, and reliability of battery-powered systems. Conventional SOH estimation methods are designed for the full state-of-charge (SOC) range of 0%–100%, assuming uniform distributions. Yet, batteries in real-world applications often operate under partial SOC ranges and experience shallow-cycle conditions, which result in distinct and unlabeled degradation profiles that make SOH estimation more complex. To tackle this issue, we propose a novel method—self-attention knowledge domain adaptation network (SKDAN)—which utilizes a self-attention distillation module combined with a multi-kernel maximum mean discrepancy framework to effectively navigate between these disparate domains. This strategy successfully extracts domain-specific features from charging curves, facilitating the transfer of knowledge from well-labeled full cycles to unlabeled shallow cycles. The effectiveness of the SKDAN method is validated through extensive testing on the CALCE and SNL battery datasets, demonstrating its robust capability to estimate SOH accurately across different SOC ranges, temperatures, and discharge rates. With a root-mean-square error (RMSE) of less than 2%, the SKDAN method outperforms existing transfer learning techniques for various SOC ranges. Additionally, it exhibits exceptional SOH estimation performance when applied to batteries from different manufacturers and operating under varied conditions. This study represents the first instance of accurately estimating battery SOH under shallow-cycle conditions without relying on full-cycle characteristic tests.