Accurate State Of Health Estimation Research Articles

Industrial Battery State-of-Health Estimation with Incomplete Limited Data Towards Second-Life Applications

Battery State of Health (SOH) estimation is vital across applications ranging from portable electronics to electric vehicles, particularly in second-life applications where accurate prediction becomes complex due to varying degradation levels. This paper introduces a novel SOH estimation model to address the lack of labeled data, employing Domain Adversarial Neural Networks (DANN) combined with 1-dimensional Convolutional Neural Networks (CNN). The proposed method allows for effective transfer of knowledge between diverse battery conditions, enhancing adaptability and efficiency by utilizing both source and target datasets. Experimental results demonstrate that the proposed model achieves a Mean Absolute Error (MAE) of 1.68% and a Root Mean Squared Error (RMSE) of 2.50%, with minimal data. Specifically, the model requires only one cell of unlabeled data from the second-life target domain, utilizing only the dQ/dV curve for estimation. Proposed model sets a new standard in second-life battery health monitoring and management by effectively leveraging a minimal amount of data for training, this approach offers a robust solution for accurate SOH estimation, particularly in scenarios with limited access to labeled data. Conflict of Interest Statement The authors declare no conflicts of interest.

Joint estimation of State of Charge (SOC) and State of Health (SOH) for lithium ion batteries using Support Vector Machine (SVM), Convolutional Neural Network (CNN) and Long Sort Term Memory Network (LSTM) models

This paper proposes a data-driven method for jointly estimating the State of Charge (SOC) and State of Health (SOH) of batteries, addressing the impact of battery aging on SOC estimation. Initially, Support Vector Machine (SVM) is employed to estimate the SOH of the battery, using the constant voltage charging time and constant voltage discharging time of lithium-ion batteries as inputs, and SOH as the output. By training the SVM model, accurate SOH estimation is achieved. Subsequently, the rated capacity of the battery is adjusted based on the estimated SOH to obtain the current maximum available capacity. This adjustment allows for the coupling of SOH and SOC, resulting in SOC estimation that accounts for aging factors. Leveraging the advantages of Convolutional Neural Networks (CNN) in feature extraction and Long Short-Term Memory (LSTM) neural networks in handling long-term sequential data, a CNN-LSTM model is utilized for SOC estimation. The proposed method utilizes the Oxford Battery Dataset (Cells 1–8) and the NASA Battery Dataset (B0005–B0007) for SOH estimation, and the Oxford Battery Dataset (Cell 8) and the NASA Battery Dataset (B0007) for SOC estimation. The SOH estimation results demonstrate that the Root Mean Square Error (RMSE) is less than 0.81 % and the Mean Absolute Error (MAE) is less than 0.65 % for Cells 1–8, while for B0005 to B0007, the RMSE is less than 1.81 % and the MAE is less than 1.29 %. For SOC estimation, the results show that the average RMSE over the entire lifecycle of Cell 8 is 0.3923 % and the average MAE is 0.3339 %, whereas for B0007, the average RMSE over the entire lifecycle is 0.6123 % and the average MAE is 0.4976 %.

State of Health Estimation of Lithium‐ion Batteries Based on Machine Learning with Mechanical‐Electrical Features

As one of the key parameters to characterize the life of lithium‐ion batteries, the state of health (SOH) is of great importance in ensuring the reliability and safety of the battery system. Considering the complexity of practical application scenarios, a novel method based on mechanical‐electrical feature extraction and machine learning is proposed to accurately estimate the SOH. A series of degradation experiments are designed to generate battery aging datasets, including the stress and voltage changes. Health features are directly extracted from the stress‐voltage profile and the mechanical‐electrical health feature factors are obtained through correlation analysis. The long short‐term memory (LSTM) network is introduced to map the relationship between mechanical‐electrical responses and the SOH, where the health feature factors are selected as input vectors. The effectiveness of the proposed method is demonstrated by battery datasets under different conditions, from which the estimated errors are less than 1.5%. This work demonstrates that the analysis and utilization of mechanical‐electrical parameters can not only realize accurate SOH estimation, but also provide a broader field for battery energy management.

State-of-health estimation for lithium-ion batteries based on GWO–VMD-transformer neural network

State-of-health (SOH) estimation of lithium-ion batteries stands as a fundamental metric within the battery management system. It reflects the current level of battery aging and is important for early warning of battery failure to avoid unsafe battery behavior. Therefore, accurate SOH estimation can ensure safe and reliable battery operation. In this paper, the capacity data of the discharge phase are used as the input of the SOH estimation model, and a gray wolf optimization (GWO)–variable mode decomposition (VMD)-transformer-based SOH estimation method for lithium-ion batteries is proposed in a data-driven framework. First, the GWO algorithm is adopted to optimize VMD to decompose the original battery capacity degradation sequence into a series of intrinsic mode functions (IMFs). Then, the transformer is used to separately predict each of these IMFs. Finally, the predicted values of each IMF are integrated to obtain the final prediction of the battery capacity degradation sequence. The model undergoes testing across various datasets, and comparative evaluations are conducted against other data-driven prediction models. The experimental findings underscore the superior SOH estimation performance of the proposed method, along with its robustness when confronted with diverse types of lithium-ion batteries, spanning distinct operational conditions and different aging degrees.

Online State of Health Estimation for Series-Connected LiFePO₄ Battery Pack Based on Differential Voltage and Inconsistency Analysis

Low-complexity and accurate state of health estimation of series-connected batteries has always been a difficult problem to solve in a well-designed battery management system. Lithium iron phosphate battery has been widely used as energy storage carrier due to its better safety and longer cycle life. In this paper, we proposed an online state of health estimation method for lithium iron phosphate battery pack based on differential voltage and inconsistency analysis. According to the aging mechanism of lithium iron phosphate battery, the region capacity in differential voltage curve is extracted as health feature to establish an aging model. Furthermore, all four inconsistency cases that affect pack capacity are analyzed, and the calculation formulas are concluded relying only on three representative battery modules, thereby reducing the computational burden. The pack capacity is estimated to verify the feasibility of the proposed method at different aging cycles. The estimation errors of the state of health of eight in-pack battery modules are less than 2%, and further the maximum error for the battery pack is only 2.27% in all aging cycles. In addition, the maximum error of the state of health for the other battery pack is only slightly over 1% at different inconsistencies.

A Transfer Learning-Based Method for Personalized State of Health Estimation of Lithium-Ion Batteries.

State of health (SOH) estimation of lithium-ion batteries (LIBs) is of critical importance for battery management systems (BMSs) of electronic devices. An accurate SOH estimation is still a challenging problem limited by diverse usage conditions between training and testing LIBs. To tackle this problem, this article proposes a transfer learning-based method for personalized SOH estimation of a new battery. More specifically, a convolutional neural network (CNN) combined with an improved domain adaptation method is used to construct an SOH estimation model, where the CNN is used to automatically extract features from raw charging voltage trajectories, while the domain adaptation method named maximum mean discrepancy (MMD) is adopted to reduce the distribution difference between training and testing battery data. This article extends MMD from classification tasks to regression tasks, which can therefore be used for SOH estimation. Three different datasets with different charging policies, discharging policies, and ambient temperatures are used to validate the effectiveness and generalizability of the proposed method. The superiority of the proposed SOH estimation method is demonstrated through the comparison with direct model training using state-of-the-art machine learning methods and several other domain adaptation approaches. The results show that the proposed transfer learning-based method has wide generalizability as well as a positive precision improvement.

Accurate State of Health Estimation of Battery System based on Multi-stage Constant Current Charging and Behavior Analysis in Real-world Electric Vehicles

Accurate State of Health Estimation of Battery System based on Multi-stage Constant Current Charging and Behavior Analysis in Real-world Electric Vehicles

State-of-Health Estimation of Lithium-ion Batteries Based on Singular Value Decomposition and an Improved Group Method of Data Handling

Lithium-ion batteries are complex electrochemical systems, and the degradation of their state of health (SOH) is a nonlinear process. Accurate SOH estimation is critical to lithium-ion battery life and safety. This paper uses a data-driven approach to study SOH estimation of lithium-ion batteries. Firstly, this paper uses the singular value decomposition (SVD) method to extract features from the battery charging history data. Secondly, the particle swarm optimization (PSO) algorithm is used to optimize the parameter configuration of the group method of data handling (GMDH). Finally, the SOH estimation is completed using the optimized GMDH. The results show that the proposed PSO-GMDH estimation model maintains an error within 0.89% for estimating its subsequent SOH using historical data of a certain battery, and maintains an error within 0.5% for estimating the SOH of another battery of the same model using historical data of multiple batteries. At the same time, the results also show that the PSO-GMDH estimation model has higher estimation accuracy than the GMDH model without parameter optimization.

A Data-Fusion-Model Method for State of Health Estimation of Li-Ion Battery Packs Based on Partial Charging Curve

The estimation of State of Health (SOH) for battery packs used in Electric Vehicles (EVs) is a complex task with significant importance, accompanied by several challenges. This study introduces a data-fusion model approach to estimate the SOH of battery packs. The approach utilizes dual Gaussian Process Regressions (GPRs) to construct a data-driven and non-parametric aging model based on charging-based Aging Features (AFs). To enhance the accuracy of the aging model, a noise model is established to replace the random noise. Subsequently, the state-space representation of the aging model is incorporated. Additionally, the Particle Filter (PF) is introduced to track the unknown state in the aging model, thereby developing the data-fusion-model for SOH estimation. The performance of the proposed method is validated through aging experiments conducted on battery packs. The simulation results demonstrate that the data-fusion model approach achieves accurate SOH estimation, with maximum errors less than 1.5%. Compared to conventional techniques such as GPR and Support Vector Regression (SVR), the proposed method exhibits higher estimation accuracy and robustness.

Data-Driven Transfer-Stacking-Based State of Health Estimation for Lithium-Ion Batteries

State of health (SOH) of lithium-ion batteries plays a vital role in the safe and reliable operation of electric vehicles. However, most of the existing SOH estimation methods still require a large number of battery aging data, while the established model usually lacks generalization. Here, we build a data-driven transfer learning model to obtain more generality on the SOH estimation. Firstly, potential health features are extracted from battery charging data and then pruned via the importance function. Secondly, support vector regression (SVR) is employed to establish source models with different battery data, which takes selected features as the input and capacity as the output. Thirdly, the transfer-stacking (TS) method is utilized to combine all source models. A TS-SVR method for SOH estimation is then established only using the first 30 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> target battery data after solving the optimization problem of assigning weight to each source model. Finally, the proposed algorithm is verified by three different battery datasets and shows better estimation performance than the comparative algorithms. It is proved that the proposed method uses only a small amount of target battery data, while together with the source battery data, can achieve an accurate SOH estimation during its life cycle.

Data-driven state of health estimation for lithium-ion battery based on voltage variation curves

The state of health (SOH) estimation of lithium-ion batteries (LIBs) is crucial for battery management system, but the accuracy and generalizability of the widely used data-driven methods are strongly dependent on the selection of LIBs health features (HFs). In this paper, four types of LIBs with different anode types from four datasets, including NASA dataset, CALCE dataset, Oxford dataset and UL-PUR dataset, were selected to extract the area of constant current charging and discharging voltage curves as two sets of HFs, and then the high correlation between the HFs and SOH is verified by their Pearson coefficient. Secondly, with the two sets of HFs, the SOH of selected batteries in the four datasets are evaluated under Gaussian Process Regression, Long and Short-Term Memory neural network and Back Propagation neural network respectively. With a training/test set ratio model of 50/50 and cross-validation method, all algorithms obtain accurate SOH estimation results. Finally, the estimation results are compared with reference data under the same dataset and training mode, and it is found that the proposed method shows better estimation accuracy and robustness than other evaluation methods by multiple HFs or even complex algorithms.

A charging-feature-based estimation model for state of health of lithium-ion batteries

Within battery management systems, the state of health of lithium-ion batteries is a key and vital enabler to ensure battery safety and efficiency. However, the accurate state of health estimation is still a critical but challenging task, and the complex electrochemical attributes underlying the degradation processes of lithium-ion batteries are not directly available. In response to this challenge, this study proposes a charging-feature-based model to realize state of health estimation by Gaussian process regression. In this approach, two features are extracted only from the monitoring parameters obtained from charging current and voltage curves. These extracted features have been demonstrated to be correlated with the state of health. Subsequently, a regression model with a 2-dimensional linear mean function and a new double-covariance function is developed to improve estimation performance. Consequently, the proposed model effectively tracks both global and local degradation trends synchronously. Finally, the reliability and accuracy of the proposed model are verified using two different batteries datasets. The results illustrate that the proposed model is capable of realizing accurate batteries’ state of health estimation, thereby outperforming other counterparts in uncertainty representation and estimation errors, whether under static profiles or dynamic profiles.

Stacking integrated learning model via ELM and GRU with mixture correntropy loss for robust state of health estimation of lithium-ion batteries

Accurate estimation of the state of health (SOH) is crucial for the safe and stable operation of lithium-ion batteries. However, since the labeled values may contain non-Gaussian noise which may lead to a decrease in the effectiveness of traditional data-driven based estimation methods. Therefore, a novel robust stacking integrated learning model (ILM) is proposed to enable accurate SOH estimation under non-Gaussian noises (or outliers) conditions. The mixture correntropy loss (MCL) is used in original extreme learning machine (ELM) and the gated recurrent unit (GRU) frameworks to develop novel robust learning models, i.e MCL-ELM and MCL-GRU, and they are used as the sub-models of the proposed ILM, which takes into account the generalization performance of the model and the overall trend of SOH over the time series. In addition, the entropy weighting method that can well reflect the differences between the sub-models is utilized to reduce the complexity of the stacked ILM. Furthermore, the local tangent space alignment is used to capture the local relationships between different loops to enhance the effectiveness of the extracted health features. Several numerical experiments are performed under different cases to validate the estimation effect of the proposed model by using two publicly available datasets, and the experimental results demonstrate that the maximum RMSE, MAE, and MAPE values of the proposed model are 1.391%, 0.932%, and 1.480%, respectively, under non-Gaussian noises conditions.

Lithium battery health state assessment based on vehicle-to-grid (V2G) real-world data and natural gradient boosting model

Accurate state of health (SOH) estimation of batteries in vehicle-to-grid (V2G) applications is critical for the safety of vehicles, chargers, and grids. In this paper, a novel SOH estimation model based on inverse ampere-time integration and natural gradient boosting (NGBoost) is proposed and verified by real operating data from V2G electric vehicles (EVs). Raw data is segmented, where segments of charging and grid-feeding with relatively smooth currents are selected to constitute the dataset for research. On top of this, five model inputs have been selected through Pearson correlation and physical meaning analysis. Hyperparameters of the model are optimized and model performance is compared with the other nine commonly used machine learning methods. The results show that the NGBoost model has the highest estimation accuracy with the mean absolute percentage error and root mean squared error of 1.484% and 2.302 A h, respectively. To increase the transparency of the model, the Shapley additive explanation (SHAP) method is utilized to provide a full explanation of its predictions. Furthermore, the model is validated to be robust to noise and shows great potential for integration into embedded battery management systems for fast and accurate SOH estimation in V2G applications.

Bioinspired spiking spatiotemporal attention framework for lithium-ion batteries state-of-health estimation

State-of-health (SOH) estimation of batteries is crucial for ensuring the safety of energy storage systems. Prediction models based on external information (current, voltage, etc.) and artificial neural networks (ANN) are effective solutions. However, external information easily interferes, and the ANN-based model has data dependence, high energy consumption, and insufficient cognitive ability. This motivates us to utilize precise battery physical and chemical degradation information and brain-inspired spiking neural networks (SNNs) for accurate SOH estimation. Therefore, this study proposes a bioinspired spiking spatiotemporal attention neural network (SSA-Net) framework for battery health state monitoring by utilizing full-life-cycle electrochemical impedance spectroscopy (EIS). SSA-Net perfectly models brain neurons' information transmission mechanism and neuron dynamics, thereby endowing it with efficient spatiotemporal feature processing capabilities and low power consumption. Based on the designed spiking residual architecture, SSA-Net constructs a deep spiking information encoding framework achieving high gradient transfer efficiency. More importantly, this study proposes a novel SNN-based spiking spatiotemporal attention module, which realizes the enhancement of useful spiking features and discards worthless information through an adaptive spiking feature selection mechanism. Experimental results show that SSA-Net effectively extracts electrochemical features associated with battery degradation, facilitating precise modeling of the nonlinear relationship between EIS data and SOH and achieving competitive performance.

A state-of-health estimation method based on incremental capacity analysis for Li-ion battery considering charging/discharging rate

Incremental capacity analysis (ICA) is an effective method for analyzing the degradation mechanism and estimating the state of health (SOH) of lithium-ion batteries. However, the incremental capacity (IC) curve is sensitive to the initial state of charge (SOC) and the charging/discharging rate (CDR), which will lead to the deformation of the IC curve and the displacement of the health feature. In this paper, an ICA-based SOH estimation method that considers the charging/discharging rate is proposed, which can achieve accurate SOH estimation. Furthermore, a method for quickly obtaining a smooth IC curve based on finite-time differentiator is developed, which realizes the online processing of high-frequency sampling data. Experiments with different initial SOCs and charging/discharging rates were designed and performed. The degradation data during standard charging are used to construct the mapping relationship between the health feature and SOH. Considering different initial SOCs, health features without being affected by different charging/discharging rates are selected for SOH estimation. The validation results show that the SOH estimation errors are within 3% for batteries at different aging levels.

Physics-Informed Neural Networks for State of Health Estimation in Lithium-Ion Batteries

One of the most challenging tasks of modern battery management systems is the accurate state of health estimation. While physico-chemical models are accurate, they have high computational cost. Neural networks lack physical interpretability but are efficient. Physics-informed neural networks tackle the aforementioned shortcomings by combining the efficiency of neural networks with the accuracy of physico-chemical models. A physics-informed neural network is developed and evaluated against three different datasets: A pseudo-two-dimensional Newman model generates data at various state of health points. This dataset is fused with experimental data from laboratory measurements and vehicle field data to train a neural network in which it exploits correlation from internal modeled states to the measurable state of health. The resulting physics-informed neural network performs best with the synthetic dataset and achieves a root mean squared error below 2% at estimating the state of health. The root mean squared error stays within 3% for laboratory test data, with the lowest error observed for constant current discharge samples. The physics-informed neural network outperforms several other purely data-driven methods and proves its advantage. The inclusion of physico-chemical information from simulation increases accuracy and further enables broader application ranges.

State of health estimation of lithium-ion batteries based on multi-health features extraction and improved long short-term memory neural network

Accurate state of health estimation of lithium-ion batteries is essential to enhance the reliability and safety of a battery system. However, the estimation accuracy based on a data-driven model is degraded by one health feature and incorrect hyper-parameters selection. This paper develops a battery state of health estimation method based on multi-health features extraction and an improved long short-term memory neural network. To accurately describe the aging mechanism of batteries, health features are extracted from battery data, such as time features, energy features, and incremental capacity features. The correlation between multi-health features and state of health is evaluated by the grey relational analysis. Aiming at the problem that the hyper-parameters of an neural network model are difficult to select, an improved quantum particle swarm optimization algorithm is developed to correctly obtain the hyper-parameters. The experimental results show that the mean absolute error, mean absolute percentage error, and root mean square error of this method are all within 1%, which is much lower than other methods, with high state of health estimation accuracy and robustness.

ERMN: An enhanced meta-learning approach for state of health estimation of lithium-ion batteries

To ensure the safety of lithium-ion batteries (LIBs), accurately estimating the state of health (SOH) of LIBs is crucial for end-users. Challenged by new working conditions and limited training samples, conventional machine learning-based methods have performed unsatisfactorily on SOH estimation of LIBs. To this end, this article introduces an enhanced regressive matching network (ERMN) method for the accurate SOH estimation of LIBs. The method extends the matching network from classification tasks to regression tasks by filtering a certain number of support samples, which can therefore be used for the SOH estimation—a typical regression task. A new loss function is designed to further enhance the distribution of the filtered support SOHs, ensuring their distinguishability and concentration. Additionally, the particle swarm optimization algorithm is incorporated into the ERMN method to automate the selection of hyperparameters. Experimental results from four case studies, considering different charge policies and sample sizes, demonstrate the effectiveness and generalization of the proposed ERMN approach.

Research on Calendar Aging for Lithium-Ion Batteries Used in Uninterruptible Power Supply System Based on Particle Filtering

The aging process of lithium-ion batteries is an extremely complex process, and the prediction of the calendar life of the lithium-ion battery is important to further guide battery maintenance, extend the battery life and reduce the risk of battery use. In the uninterruptible power supply (UPS) system, the battery is in a floating state for a long time, so the aging of the battery is approximated by calendar aging, and its decay rate is slow and difficult to estimate accurately. This paper proposes a particle filtering-based algorithm for battery state-of-health (SOH) and remaining useful life (RUL) predictions. First, the calendar aging modeling for the batteries used in the UPS system for the Shanghai rail transportation energy storage power station is presented. Then, the particle filtering algorithm is employed for the SOH estimation and RUL prediction for the single-cell battery calendar aging model. Finally, the single-cell SOH and RUL estimation algorithm is expanded to the pack and group scales estimation. The experimental results indicate that the proposed method can achieve accurate SOH estimation and RUL prediction results.