Comparative Study of EKF and UKF for SOC Estimation of Lithium-ion Batteries

Xiao, Tian; Shi, Xiaohan; Zhou, Boxi; Wang, Xiaolei

doi:10.1109/isgt-asia.2019.8880915

Cited by 14 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the second step, the RR, RF and XGBoost models are selected as the basic machine learning models, trained on the training set, and the optimal hyperparameters of each model are found using the validation set. The third step is to calculate the weight of each model according to formula (11), and the fourth step is to perform a weighted sum-mation on the prediction results of each model, and output the final predicted value.…”

Section: Principle Of Machine Learning Algorithm and Fusion Modelmentioning

confidence: 99%

“…Therefore, it is possible to simply predict the remaining driving range of the electric vehicle from the mapping relationship between the SOC of the power battery and the driving range of the vehicle [3][4][5][6]. Common SOC estimation methods are based on characterization parameters, ampere-hour integration, model-based estimation, and data-driven methods [7][8][9][10][11][12][13][14][15]. State of Energy (SOE), directly describes the energy supply capacity of the power battery, and is more suitable for predicting the remaining driving range than the SOC.…”

Section: Introductionmentioning

confidence: 99%

“…FIGURE11 Model interpretation. We not only used RF method to get feature importance, but also used XGBoost to validate the feature importance…”

mentioning

confidence: 99%

See 2 more Smart Citations

Method for predicting the remaining mileage of electric vehicles based on dimension expansion and model fusion

Sheng

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

Accurately predicting the remaining mileage of electric vehicles (EVs) can effectively alleviate user's mileage anxiety and develop refinement of energy management strategy. However, traditional prediction methods not only consume time and resources, but also accumulate errors and lack interpretability. In this paper, we proposed a model based on dimension expansion and model fusion strategy, which uses the extreme gradient boosting (XGBoost) algorithm to directly predict the remaining mileage of EVs. After pre‐processing the real running data of EVs, we constructed the field of remaining driving range and analyzed the relationship between features and remaining driving range, and then directly predicted the remaining driving mileage. Compared with other machine learning methods, XGBoost model has the highest accuracy. Then dimensional extended data set was obtained based on prior knowledge and symbol conversion, which improved the model performance. Finally, the model fusion strategy was adopted to further improve the generalization ability and stability of the model. The experimental results show that the Bootstrap aggregating (Bagging) fusion model has the highest predictive performance on the test set and outperformed other methods. The maximum RAE is not more than 3.5%, RMSE is less than 3km and MAE is about 2 km.

show abstract

Section: Principle Of Machine Learning Algorithm and Fusion Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Method for predicting the remaining mileage of electric vehicles based on dimension expansion and model fusion

Sheng

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

show abstract

“…Methods for passive balancing can be used in two ways. The first method is to use a fixed shunt resistor [7], and the second method is to use a controllable shunt resistor [10]. Although it does not appear to be as elegant as active balancing since energy is spent in heat, there are number of reasons why this technique has become the preferred method of most BMS, including: Simple design, low-cost parts, simple installation, and expandable design.…”

Section: Cell Balancingmentioning

confidence: 99%

Modeling and Simulation of Battery Management System (BMS) for Electric Vehicles

Bhovi¹,

Ranjith²,

Sachin³

et al. 2021

JUSST

View full text Add to dashboard Cite

Electric cars have evolved into a game-changing technology in recent years. A Battery Management System (BMS) is the most significant aspect of an Electric Vehicle (EV) in the automotive sector since it is regarded as the brain of the battery pack. Lithium-ion batteries have a large capacity for energy storage. The BMS is in charge of controlling the battery packs in electric vehicles. The major role of the BMS is to accurately monitor the battery’s status, which assures dependable operation and prolongs battery performance. The BMS’s principal job is to keep track, estimate, and balance the battery pack’s cells. The major goals of this work are to keep track of battery characteristics, estimate SoC using three distinct approaches, and balance cells. Coulomb Counting, Extended Kalman Filter, and Unscented Kalman Filter are the three algorithms that will be implemented. Current is used as an input parameter to implement the coulomb counting method. In contrast to voltage and temperature, the current value is taken into account by the Extended and Unscented Kalman Filters. To calculate the state transition and measurement update matrix, these parameters are considered. This matrix will then be used to calculate SoC. Results of all the algorithms will be comparatively analyzed. MATLAB R2020a software is used for the simulation of different algorithms and SoC calculation. Three states of BMS are considered and they are Discharging phase, the Standby/resting phase, and the Charging phase. At the beginning of the Simulation, the SoC values of the cells were 80%. At the end of simulation maximum values of SoC of Coulomb counting, Extended Kalman Filter (EKF), and Unscented Kalman Filter (UKF) reached are 100%, 98.74%, and 98.46% respectively. After SoC Estimation, Cell balancing is also performed over 6 cells of the battery pack.

show abstract

“…The ampere-hour integration method calculates the change of SOC by integrating current over time, which has a low time cost [9,10]. The OCV lookup method estimates the SOC value by interpolating the OCV on the OCV-SOC curve [11][12][13]. However, SOC estimation based on the ampere-hour integration method is an open-loop estimation approach, and its accuracy is influenced by continuous current sampling errors and inaccurate initial SOC value.…”

Section: Introductionmentioning

confidence: 99%

High-Precision and Robust SOC Estimation of LiFePO4 Blade Batteries Based on the BPNN-EKF Algorithm

Zhang

Chen

et al. 2023

Batteries

View full text Add to dashboard Cite

The lithium iron phosphate (LiFePO4) blade battery is a long, rectangular-shaped cell that can be directly integrated into battery pack systems. It enhances volumetric power density, significantly reduces costs, and is widely utilized in electric vehicles. However, the flat open circuit voltage and significant polarization differences under wide operational temperatures are challenging for accurate voltage modeling of battery management systems (BMSs). In particular, inaccurate state of charge (SOC) estimation may cause overcharging and over-discharging risks. To accurately perceive the SOC of LiFePO4 blade batteries, a SOC estimation method based on the backpropagation neural network-extended Kalman filter (BPNN-EKF) algorithm is proposed. BPNN is a neural network model that utilizes the backpropagation algorithm to update model parameters, while EKF is an optimal estimation algorithm. Firstly, dynamic working condition tests, including the New European Driving Cycle (NEDC) and high-speed working (HSW) condition tests, are conducted under a wide temperature range (−25–43 °C). HSW conditions refer to a simulated operating condition that mimics the driving of an electric vehicle on a highway. The minimum voltage of the battery system is used as the output for training the BPNN model. We derive the Kalman gain by combining the BPNN output voltage. Additionally, the EKF algorithm is employed to correct the SOC value using voltage error information. Concerning long SOC calculation intervals, capacity errors, initial SOC errors, and current and voltage sampling errors, the maximum SOC estimation RMSE is 3.98% at −20 °C NEDC, 3.62% at 10 °C NEDC, and 1.68% at 35 °C HSW. The proposed algorithm can be applied to different temperatures and operations, demonstrating high robustness. This BPNN-EKF algorithm has the potential to be embedded in electric vehicle BMS systems for practical applications.

show abstract

Comparative Study of EKF and UKF for SOC Estimation of Lithium-ion Batteries

Cited by 14 publications

References 13 publications

Method for predicting the remaining mileage of electric vehicles based on dimension expansion and model fusion

Method for predicting the remaining mileage of electric vehicles based on dimension expansion and model fusion

Modeling and Simulation of Battery Management System (BMS) for Electric Vehicles

High-Precision and Robust SOC Estimation of LiFePO4 Blade Batteries Based on the BPNN-EKF Algorithm

Contact Info

Product

Resources

About