Data-Driven State of Charge Estimation for Power Battery With Improved Extended Kalman Filter

Highly accurate state of charge (SOC) estimation of lithium-ion batteries is one of the key technologies of battery management systems in electric vehicles. The performance of SOC estimation directly influences the driving range and safety of these vehicles. Due to external disturbances, temperature variation and electromagnetic interference, accurate SOC estimation becomes difficult. To accurately estimate the SOC of lithium-ion batteries, this article presents a novel machine-learning method to address the risk of gradient explosion and gradient decent using the dynamic nonlinear auto-regressive models with exogenous input neural network (NARX) with long short-term memories (LSTM).The proposed hybrid NARX model embeds LSTM memory, which provides jump-ahead connections in the time-unfolded model. These jump-ahead connections provide a shorter path for the propagation of gradient information, therefore reducing long-term dependence on the recurrent neural network. Experimental results show that the estimation performance root mean square error (RMSE) of the proposed model is less than 1%, and this model has better multitime prediction performance. Finally, the hybrid NARX and LSTM model is compared with the standard back propagation neural network based on particle swarm optimization (BPNN-PSO), the least-squares support vector machine (LS-SVM) and LSTM existing models under urban dynamometer driving schedule (UDDS) and dynamic stress test (DST) conditions. The proposed hybrid NARX-LSTM model yield relative to other methods and can estimate the battery SOC with high accuracy. The RMSE of proposed model is improved by approximately 60% compared with the standard LSTM.

An optimized long short-term memory-weighted fading extended Kalman filtering model with wide temperature adaptation for the state of charge estimation of lithium-ion batteries

Online Estimation and Error Analysis of both SOC and SOH of Lithium-ion Battery based on DEKF Method

Accurate online parameter identification and state of charge (SOC) estimation are both very crucial for ensuring the operating safety of lithium-ion batteries and usually the former is a base of the latter. To achieve accurate and stable SOC estimation results, this paper proposes a model-based method, which incorporates a vector forgetting factor least square (VFFLS) algorithm and an improved adaptive cubature Kalman filter (IACKF). Firstly, considering it is difficult for the traditional forgetting factor recursive least square (FFRLS) algorithm to balance the accuracy, convergence, and stability for multiple parameters with different time-varying periods, an improved VFFLS method is employed to determine the multiple parameters of the first-order RC battery model online. It supersedes the single forgetting factor in the FFRLS with multiple forgetting factors in a vector form for improving adaptive capability to multiple time-varying parameters. Secondly, aiming at the fact that the standard cubature Kalman filter (CKF) cannot operate properly when the error covariance matrix is non-positive definite, which is caused by disturbance, initial error, and the limit of the computer word length, the UR decomposition rather than the Cholesky decomposition is applied, thus improving the algorithm stability. In addition, an adaptive update strategy is added to the CKF to enhance accuracy and convergence speed. Finally, comparative experiments with different operating patterns, positive and non-positive definite error covariance matrices, and temperatures are carried out. Experimental results showed that the proposed method can estimate the SOC accurately and stably.

Optimized EKF algorithm using TSO-BP neural network for lithium battery state of charge estimation

In order to improve the accuracy of the battery state of charge (SOC) estimation, in this paper we take a lithium-ion battery as an example to study the adaptive Kalman filter based SOC estimation algorithm. Firstly, the second-order battery system model is introduced. Meanwhile, the temperature and charge rate are introduced into the model. Then, the temperature and the charge rate are adopted to estimate the battery SOC, with the help of the parameters of an adaptive Kalman filter based estimation algorithm model. Afterwards, it is verified by the numerical simulation that in the ideal case, the accuracy of SOC estimation can be enhanced by adding two elements, namely, the temperature and charge rate. Finally, the actual road conditions are simulated with ADVISOR, and the simulation results show that the proposed method improves the accuracy of battery SOC estimation under actual road conditions. Thus, its application scope in engineering is greatly expanded.

Dynamic ultrasonic response modeling and accurate state of charge estimation for lithium ion batteries under various load profiles and temperatures

The state of charge (SOC) displays the remaining power of the vehicle battery, its accurate estimation benefits the protection of the battery and determines the adjustment of the operating state. In this paper, a genetic algorithm-optimized back propagation neural network (GA-BP) for optimization of the Adaptive Extended Kalman Filter (AEKF) is proposed to estimate the SOC of li-ion batteries. The 2-order RC equivalent model is established. Based on the 2-order RC equivalent model and Hybrid Pulse Power Characterization (HPPC), parameters of the NCR18650B lithium battery is identified. Preliminarily estimated SOC, using EKF and battery parameters. In order to improve the accuracy of SOC estimation, a BP neural network optimization method based on genetic algorithm (GA-BP) is proposed. The AEKF is obtained by optimizing the EKF through an adaptive sampling strategy. The SOC estimated by GA-BP is converted into the input of the AEKF, which further improves the accuracy of the vehicle battery SOC estimation. The simulation and experimental results show that, compared with EKF, the maximum SOC estimation error of AEKF optimized by GA-BP neural network is reduced from 2.3% to 0.7%, and the average SOC estimation error is reduced from 1.28% to 0.41%. The latter has better convergence and robustness.

The estimation of state of charge(SOC) is among the key technologies in battery management system. Compared with many estimation methods, neural network has obvious advantages in the estimation accuracy. But requiring great amount of data is its main limitation. In order to solve the above problems, a method for SOC estimation based on the cross validation of artificial neural network and k-fold was proposed. An 18650 power lithium-ion battery is used as the experimental object, and the data are obtained by collecting the battery voltage, current and temperature data. High SOC estimation accuracy on different verification sets is pursued under circumstance of low data amount. The BP artificial neural network model is established based on the Keras platform with tensorflow, and K-fold cross validation method is added to the network. After training, the model is used to predict the experimental data. The estimation of SOC is realized by function fitting. Compared with the traditional BP neural network prediction, the prediction accuracy is 99%. Finally, it is proved that the method combining BP neural network and K-flow cross validation is effective and the validity of the neural network model for SOC estimation is verified.

With the rapid development of renewable energy technologies, energy storage batteries are increasingly utilized in power systems. Accurate estimation of the state of charge (SOC) is crucial for ensuring battery performance and operational safety. To enhance SOC estimation accuracy under varying power demands, this paper proposes an SOC estimation method based on dynamic capacity correction. First, the sources of error in traditional SOC estimation methods under complex operating conditions are analyzed, and corresponding improvement strategies are suggested. Second, the capacity variation characteristics of energy storage batteries at different discharge rates are investigated, and a quantitative characterization model of the relationship between discharge rate and capacity is established. Then, a developed algorithm combining a neural network, which integrates convolutional neural networks (CNN), bidirectional gated recurrent units (Bi-GRU), and an attention mechanism, with an extended Kalman filter (EKF) is designed. Leveraging their strengths in nonlinear relationship modeling and noise resistance, a capacity-adaptive SOC estimation method considering discharge rates is proposed. Experimental results validate the effectiveness of the proposed dynamic capacity correction and CGA-EKF algorithm, demonstrating significantly improved SOC estimation accuracy and stability compared to traditional methods under various dynamic power conditions.

A comparative study on state-of-charge estimation for lithium-rich manganese-based battery based on Bayesian filtering and machine learning methods

A well-known Luenburger observer and two sliding mode observers (SMO) for battery state of charge (SOC) estimation based on an improved battery equivalent circuit are presented. The comparison of their SOC estimation results is discussed. The testing data under different discharge current profiles generated by DUALFOIL battery simulation program are used to extract the circuit model parameters and verify the effectiveness of the observers for the SOC estimation. It shows that two sliding mode based SOC observers have robust tracking performance and provide more accurate SOC estimation in electric vehicle driving conditions.

To accurately estimate the state of charge (SOC) of lithium-ion power batteries in the event of errors in the battery model or unknown external noise, an SOC estimation method based on the H-infinity filter (HIF) algorithm is proposed in this paper. Firstly, a fractional-order battery model based on a dual polarization equivalent circuit model is established. Then, the parameters of the fractional-order battery model are identified by the hybrid particle swarm optimization (HPSO) algorithm, based on a genetic crossover factor. Finally, the accuracy of the SOC estimation results of the lithium-ion batteries, using the HIF algorithm and extended Kalman filter (EKF) algorithm, are verified and compared under three conditions: uncertain measurement accuracy, uncertain SOC initial value, and uncertain application conditions. The simulation results show that the SOC estimation method based on HIF can ensure that the SOC estimation error value fluctuates within ±0.02 in any case, and is slightly affected by environmental and other factors. It provides a way to improve the accuracy of SOC estimation in a battery management system.

State of Charge (SOC) estimation plays a crucial role in managing the performance and longevity of electric vehicle (EV) batteries. Various estimation techniques, including various Kalman Filters (KF), have been employed for this purpose. The mathematical process and limits of different KF family algorithms are analysed. In this study, an impact of nonlinear KF parameters on SOC estimation accuracy for EV batteries is analyzed. Specifically, the performance of Extended Kalman Filter (EKF), Unscented Kalman Filter (UKF), and Particle Filter (PF) is examined. EKF is most preferred for SOC estimation whereas introducing sigma points in UKF is the basic difference between EKF and UKF. In comparison to EKF and UKF, PF is more flexible since it applies to nonlinear systems with non-Gaussian distributions. Utilising a sequence of noisy measurements, KF is a recursive method that approximates the state of a dynamic system. It requires accurate parameters such as process noise covariance (Q) and measurement noise covariance (R) to work effectively. In this work, the effect of these parameters on state of charge estimation using nonlinear KFs has been analysed under different settings of noise covariance matrices. Tuning these parameters is essential for optimizing the performance of the KF and ensuring accurate and reliable state estimation in real-world applications. To find parameter values that provide the best balance between accuracy, robustness, and computational efficiency, the tuning process involves experimentation, simulation, and validation using real-world data. According to the results observed, the filter parameters such as three diagonal elements of Q are selected as 2e-8, 0.005, 0.003 and R as 2e-6. By evaluating the state estimation accuracy under different driving scenarios, robustness and sensitivity of filtering technique in estimating SOC for EV batteries has been studied. This analysis contributes to the optimization of SOC estimation algorithms, enhancing the reliability and efficiency of EV battery management systems.

State-of-Charge Estimation of VRLA Batteries Using Neural Networks and Extended Kalman Filter