Charge Estimation Of Lithium-ion Batteries Research Articles

A novel hybrid optimized incremental relevance vector machine and filtering technique for state of charge estimation of lithium-ion batteries

Despite not requiring a comprehensive understanding of the intricate electrochemical reactions within the battery, the data-driven approach faces challenges regarding state of charge (SOC) fluctuations during abrupt changes in battery current. Currently, research on data-driven filtering methods predominantly focuses on neural network-based algorithms, with limited exploration of the relevance vector machine (RVM) algorithm that possesses advantages in handling small sample sizes, high sparsity, and probabilistic distributions. Drawing inspiration from this premise, the present manuscript introduces an innovative fusion algorithm, founded upon the framework of the adaptive Kalman filtering (AKF) algorithm, which intricately melds the optimized incremental RVM (OIRVM) with the Coulomb counting methodology, called Coulomb_AKF_OIRVM (CFR) algorithm. Experimental findings suggest that the CFR algorithm displays exceptional generalization capacity across different driving cycles and temperatures, exhibiting high estimation accuracy and robustness. The average root mean square error, determination coefficient, mean absolute error and maximum absolute error of the public datasets and experimental datasets are 0.25 %, 0.02 %, 0.20 %, and 0.85 %, respectively.

Analysis and Diagnosis of the Effect of Voltage and Current Sensor Faults on the State of Charge Estimation of Lithium-ion Batteries Based on Neural Networks

Analysis and Diagnosis of the Effect of Voltage and Current Sensor Faults on the State of Charge Estimation of Lithium-ion Batteries Based on Neural Networks

A novel suppressing Kalman filter divergence method for the state of charge estimation of lithium-ion batteries under complex conditions

The estimation method for state of charge (SOC) of lithium-ion batteries based on the Extended Kalman Filter (EKF) is prone to losing the ability to track sudden changes under complex driving conditions. Thus, this method cannot guarantee estimation accuracy and robustness. To overcome this deficiency, fading factors are introduced into the error covariance to enhance the effect of newly generated measurement data on the current filtering estimation. A Suboptimal Multiple Fading EKF (SMFEKF) SOC estimation method is proposed herein. The fading factors are solved by forcing the new error sequence of the predicted and actual terminal voltage values to remain orthogonal. The new error sequence that remains orthogonal undergoes transitions from strong autocorrelation in the original stable state to weak autocorrelation. Through real-time adjustment of the Kalman gain matrix, the effective tracking ability of the system in the event of sudden changes gets enhanced. To verify the effectiveness of the proposed method, first, a battery dynamic condition test library covering multiple driving scenarios (such as cities, suburbs, and highways) is established through ADVISOR advanced vehicle simulator driving condition tests. Second, a second-order equivalent circuit model is established and the recursive least squares method is used for parameter identification. Finally, a detailed comparison is made between SMFEKF and EKF in terms of SOC estimation accuracy and robustness under driving conditions with different levels of complexity. It is found that four operating conditions are the main reasons for filtering divergence in EKF. The results show that the root mean square errors of SMFEKF are 63.72 %, 54.20 %, and 21.30 % those of EKF under the three complex conditions, respectively. The new method effectively reduces SOC estimation error and solves the problem of EKF filtering divergence under complex conditions.

A novel approach for improving the performance of deep learning-based state of charge estimation of lithium-ion batteries: Choosy SoC Estimator (ChoSoCE)

Deep learning-based (DL) methods have recently come to the forefront among the data-driven models due to their success in capturing the complexities of the battery. Many previous DL-based studies for SoC estimation have almost exclusively focused on improving DL structure by proposing various architectures. Questions regarding the outlier or atypical predictions have yet to be adequately addressed. Furthermore, few works benefit from optimization algorithms to determine the hyperparameters of DL. In this study, we have addressed the problem of how to obtain the hyperparameter of DL and fix the improper DL predictions. To this aim, we used two different optimization algorithms to determine the hyperparameters of DL and proposed a novel algorithm that considers the previous SoC estimations. The algorithm either approves or rejects the DL predictions for the relevant step and offers new values for the rejected ones. The proposed scheme is evaluated using a battery dataset which includes different driving cycles. According to the results, it is observed that the optimized DL outperforms the empirical one by at least 35% in terms of performance indices. Moreover, the proposed novel algorithm successfully integrates into all variations and significantly improves the performance index scores.

Multi-innovation and strong tracking based H[formula omitted] filter for state of charge estimation of lithium-ion batteries

Accurate state of charge (SOC) is a crucial indicator of the battery management system, which ensures the safety performance of lithium-ion batteries (LiBs). However, traditional SOC estimation methods such as extended Kalman filter and H∞ filter (HIF) do not perform satisfactorily when dealing with sudden state changes, which pose a safety hazard to the normal operation of LiBs. This paper proposes two effective strategies to endow the HIF with the strong tracking capability to react to state mutations. Initially, the single innovation in the HIF is extended to the multi-innovation so that the estimation accuracy is ameliorated by incorporating the historical data. Additionally, a suboptimal fading factor is introduced into the HIF to adjust the gain matrix online by forcing the innovation sequence to keep orthogonal. The fading factor fully utilizes the rich information in the innovation sequence, enabling the filter to track changing states well. Finally, the discharge experiments and dynamic stress tests are conducted to verify that the proposed strategy can ameliorate the precision and robustness without bringing extra computational burden.

State of charge estimation of lithium-ion batteries based on PSO-TCN-Attention neural network

Lithium-ion batteries are acted as energy storage devices and widely used in many fields, such as mobile, electric vehicles, and renewable energy sources, etc. However, their reliability, performance and safety are limited by state of charge (SOC) estimation of Lithium-ion batteries. In order to address this issue, a PSO-TCN-Attention network model is proposed in this work. The particle swarm optimization (PSO) algorithm is utilized to optimize the structural parameters of temporal convolutional network (TCN), enabling the model automatically learn and adapt the characteristics of lithium-ion batteries under different temperature conditions. Then, the attention mechanism allows the network adaptively focus on key time steps, enhancing the capture of time dependency in the SOC estimation from the Lithium-ion battery dataset, and further improving the accuracy and robustness of the model. Moreover, as the dataset used for SOC prediction consists of battery data from all dynamic operating conditions at various temperatures, the model is validated against LSTM and TCN networks. Results demonstrate that the SOC estimation of PSO-TCN-Attention network model is the most optimal, whose RMSE and MAXE is less than 1 % and 5.75 %, respectively, and R2 coefficient of determination exceeds 99.88 %.

An Improved Self-Adaptive Flower Pollination-Backpropagation Neural Network for the State of Charge Estimation of Lithium-Ion Batteries with Output Sliding Average Window Strategy

With the rapid development of electric vehicles and green energy sources, the use of backpropagation neural network (BPNN) to precisely estimate the state of charge (SOC) in lithium-ion batteries has become a popular research topic. However, traditionally BPNN has low prediction accuracy and large output fluctuations. To address the shortcomings of BPNN, self-adaptive flower pollination algorithm (SFPA) was proposed to optimize the initial weights and thresholds of BPNN, and an output sliding average window (OSAW) strategy is proposed to smooth SOC outputs in this research, which SOC estimation method is named SFPA-BP-OSAW. In addition, the performance of the newly proposed method is compared with other common related algorithms under different working conditions to verify the effectiveness of SFPA-BP-OSAW. The experimental results show that the mean absolute error of SFPA-BP-OSAW is 0.771% and 0.897%, and the root mean square error is 0.236% and 0.37%, respectively, under HPPC and BBDST working conditions. Experimental data and error analysis show that the method proposed in this paper has fast convergence, high prediction accuracy, and curve smoothness.

State of charge estimation for lithium-ion batteries based on data augmentation with generative adversarial network

Ever-increasing efforts in state of charge (SOC) of lithium-ion battery estimation techniques have been centered on machine learning-based methods, and a prerequisite guaranteeing the effectiveness of these methods demands an abundance of high-quality datasets. However, performing battery-related experiments is time-consuming and expensive, and manufacturers are reluctant to release their datasets due to confidentiality constraints. This limited data availability has hindered further research in this area. This paper proposes a time series augmentation model (TS-DCGAN) based on a deep convolutional generative adversarial framework. By converting the data generation problem into image generation and utilizing the advancements in GAN-based image generation, the proposed method can produce high-quality battery data. The distributional similarity and diversity of generated datasets are evaluated quantitatively and qualitatively with several metrics. The SOC estimator trained on the synthetic datasets achieved comparable execution to the actual data. Additionally, when integrated with a few real datasets, the performance of baseline SOC estimators improved to varying degrees. Extensive experiments demonstrate that the proposed method can generate synthetic data that accurately reflects the original feature distributions and temporal dynamics. This has the potential to greatly assist researchers in developing reliable battery SOC estimators.

An Improved Model Combining Machine Learning and Kalman Filtering Architecture for State of Charge Estimation of Lithium-Ion Batteries

Accurate state of charge (SOC) estimation of lithium-ion batteries is a fundamental prerequisite for ensuring the normal and safe operation of electric vehicles, and it is also a key technology component in battery management systems. In recent years, lithium-ion battery SOC estimation methods based on data-driven approaches have gained significant popularity. However, these methods commonly face the issue of poor model generalization and limited robustness. To address such issues, this study proposes a closed-loop SOC estimation method based on simulated annealing-optimized support vector regression (SA-SVR) combined with minimum error entropy based extended Kalman filter (MEE-EKF) algorithm. Firstly, a probability-based SA algorithm is employed to optimize the internal parameters of the SVR, thereby enhancing the precision of original SOC estimation. Secondly, utilizing the framework of the Kalman filter, the optimized SVR results are incorporated as the measurement equation and further processed through the MEE-EKF, while the ampere-hour integral physical model serves as the state equation, effectively attenuating the measurement noise, enhancing the estimation accuracy, and improving generalization ability. The proposed method is validated through battery testing experiments conducted under three typical operating conditions and one complex and random operating condition with wide temperature variations under only one condition training. The results demonstrate that the proposed method achieves a mean absolute error below 0.60% and a root mean square error below 0.73% across all operating conditions, showcasing a significant improvement in estimation accuracy compared to the benchmark algorithms. The high precision and generalization capability of the proposed method are evident, ensuring accurate SOC estimation for electric vehicles.

An Improved AhI Method With Deep Learning Networks for State of Charge Estimation of Lithium-Ion Battery

An Improved AhI Method With Deep Learning Networks for State of Charge Estimation of Lithium-Ion Battery

Fast State of Charge Estimation for Lithium-ion Battery Based on Electrochemical Impedance Spectroscopy Frequency Feature Extraction

Fast State of Charge Estimation for Lithium-ion Battery Based on Electrochemical Impedance Spectroscopy Frequency Feature Extraction

Self-Adaptive Neural Network-Based Fractional-Order Nonlinear Observer Design for State of Charge Estimation of Lithium-Ion Batteries

Self-Adaptive Neural Network-Based Fractional-Order Nonlinear Observer Design for State of Charge Estimation of Lithium-Ion Batteries

State of Charge Estimation for Lithium-Ion Batteries at Various Temperatures by Extreme Gradient Boosting and Adaptive Cubature Kalman Filter

State of Charge Estimation for Lithium-Ion Batteries at Various Temperatures by Extreme Gradient Boosting and Adaptive Cubature Kalman Filter

Parameter identification and state of charge estimation for lithium-ion batteries under wide temperature range

Parameter identification and state of charge estimation for lithium-ion batteries under wide temperature range

An Adaptive Extended Kalman Filter for Model-Based Fault Diagnosis and State of Charge Estimation of Lithium-Ion Batteries

Precisely gauging the state of charge (SOC) of a lithium-ion battery poses a considerable obstacle due to the battery's intricate electrochemical properties, which are highly dynamic and nonlinear. The effectiveness of the control strategy employed in electric vehicles heavily hinges on the precise estimation of the battery's SOC. Among the crucial elements, the accurate assessment of SOC for power lithium-ion batteries stands out. Ensuring the durability and reliability of battery management systems in electric vehicles to predict SOC is a multifaceted endeavor. Given the inherently nonlinear degradation pattern of batteries, achieving precise forecasting of SOC while minimizing degradation proves to be a demanding task. The accurate determination of battery SOC holds significant significance for both battery electric vehicles and hybrid electric vehicles. Lithium-ion batteries have gained extensive usage in various facets of daily life due to their positive environmental and resource-related attributes. The precise determination of SOC is pivotal in ensuring proper battery operation. Nonetheless, the challenges of SOC estimation under low temperatures have received limited attention. To tackle this issue, this study introduces an adaptive extended Kalman Filter for model-based fault diagnosis and SOC estimation of lithium-ion batteries.

State of charge estimation for lithium-ion batteries based on battery model and data-driven fusion method

The voltage plateau phase of LiFeO4 (LFP) batteries presents a formidable challenge when estimating the state of charge (SOC). Although numerous data-driven methods have been developed to address this issue, they often depend heavily on high-quality training data. Furthermore, these methods are typically regarded as “black-box” models, lacking interpretability. To overcome these challenges, a novel approach that integrates both model-based and data-driven techniques for battery SOC estimation is proposed in this paper. The proposed method is grounded in the battery model and complemented by the data-driven model, thus enhancing interpretability by incorporating domain knowledge. To reduce computational complexity, the Rint model is used for rough SOC estimation, with the eXtreme Gradient Boosting model (XGBoost) used for residual learning. The parameters of the battery model serve as input features for the XGBoost model. The effectiveness of the proposed method is empirically validated under different dynamic testing profiles. Experimental results demonstrate that integration battery domain knowledge into data-driven approaches not only enhances method interpretability but also significantly improves the SOC estimation accuracy for LFP batteries. Moreover, it exhibits robustness and exceptional generalization performance under unseen dynamic conditions, yielding root mean square errors of less than 1 % and maximum errors of less than 2 %.

State of charge estimation for lithium-ion battery based on improved online parameters identification and adaptive square root unscented Kalman filter

Accurate state of charge estimation is crucial for the safe and efficient operation of lithium-ion batteries. The Kalman filtering algorithm has been widely used in state-of-charge (SOC) estimation. To solve the problem of filter divergence and sensitivity to noise, the joint SOC estimation method is proposed to achieve accurate and robust estimation of SOC, which is composed of improved variable forgetting factor recursive least square (VFFRLS) and adaptive square root unscented Kalman filter (ASRUKF). The improved VFFRLS method uses the mean square value of the multi-step voltage residual instead of the traditional one-step voltage residual to correct the forgetting factor, and the ASRUKF improves the accuracy and stability of estimation by introducing the square root method and the adaptive method. Estimations under three typical working conditions are quantitatively studied, the experimental results show that the proposed method has good accuracy and stability. The maximum mean absolute error (MAE) is 0.0061, and the corresponding root mean square error (RMSE) is 0.0090. Furthermore, the experimental verification after adding offset errors to measured data shows that the proposed method can still track the reference SOC with satisfactory accuracy in the range of voltage offset error less than ±0.5 % and current offset error less than ±3 %, both for the constant offset error and the random error, and the SOC error is less than 2.5 %.

State of Charge Estimation of Lithium-Ion Battery Based on Back Propagation Neural Network and AdaBoost Algorithm

The accurate estimation of the state of charge (SOC) of lithium-ion batteries is critical in battery energy storage systems. This paper introduces a novel approach, the AdaBoost–BPNN model, to overcome the limitations of traditional data-driven estimation methods, such as a low estimation accuracy and poor generalization ability. The proposed model employs a back propagation neural network (BPNN) for the preliminary estimation. Subsequently, an AdaBoost–BPNN model is developed as a strong learner using the AdaBoost integration algorithm. Each BPNN sub-model serves as a weak learner within the AdaBoost framework. The final output of the strong learner is obtained by combining the individual outputs from the weak learners using weighting factors. This adaptive adjustment of weighting factors enhances the accuracy of SOC estimation. The proposed SOC estimation algorithm is evaluated and validated through experimental analysis. Throughout the paper, theoretical analysis is conducted, and the proposed AdaBoost–BPNN model is validated and verified using experimental results. The results demonstrate that the AdaBoost–BPNN model outperforms traditional methods in accurately estimating SOC under various conditions, including constant current-constant voltage (CCCV) charging, dynamical stress testing (DST), US06, a federal urban driving schedule (FUDS), and pulse discharge conditions.

State of Charge Estimation of Lithium-Ion Batteries Using Long Short-Term Memory and Bi-directional Long Short-Term Memory Neural Networks

State of Charge Estimation of Lithium-Ion Batteries Using Long Short-Term Memory and Bi-directional Long Short-Term Memory Neural Networks

An improved adaptive weights correction-particle swarm optimization-unscented particle filter method for high-precision online state of charge estimation of lithium-ion batteries

An improved adaptive weights correction-particle swarm optimization-unscented particle filter method for high-precision online state of charge estimation of lithium-ion batteries