Co-estimation of state of charge and capacity for lithium-ion battery based on recurrent neural network and support vector machine

Wang, Qiao; Ye, Min; Wei, Meng; Lian, Gaoqi; Wu, Changzhi

doi:10.1016/j.egyr.2021.10.095

Cited by 36 publications

(14 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…and κ is the electrical conductivity of the electrolyte phase, κ eff D is the coefficient ionic conductivity factor for convenient list, which is mainly expressed by Equation (5). R is the gas constant, and T represents the battery temperature; f AE is the equivalent molecular activity coefficient of electrolyte.…”

Section: Charge Conservation Equationsmentioning

confidence: 99%

“…4 However, the reliability and safety of LIBs still suffer from some issues under complicated and extreme conditions, such as unstable driving ranges and the potential over-charging situation. It is reported that the battery state of charge (SOC) is an essential indicator to reliably characterize the driving distance, 5 and efficiently monitoring anode potential can strictly suppress lithium plating for optimizing charging efficiency. 6 Therefore, it is urgent for next-generation battery management system (BMS) to achieve the accurate observation of physics-based battery states, especially SOC and anode potential, to substantially ensure safe operation of EVs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Low‐complexity state of charge and anode potential prediction for lithium‐ion batteries using a simplified electrochemical model‐based observer under variable load condition

Pang

Geng

et al. 2022

Intl J of Energy Research

View full text Add to dashboard Cite

The accurate knowledge of the physics-based state of charge (SOC) and anode potential for lithium-ion batteries (LIBs) plays an essential role in the driving range prediction and charge strategy optimization of electric vehicles (EVs). However, the SOC estimation based on empirical equivalent circuit models and the lack of anode potential information makes it challenging in developing advanced battery management systems for EVs. For this reason, this paper proposes a low-complexity SOC and anode potential prediction method for LIBs using a simplified electrochemical model (SEM)-based observer under variable load condition. First, based on the Padé approximation and volume average method, a reduced-order SEM is proposed and verified. Then, a lowcomplexity proportional-integral-differential observer framework incorporating the SEM is developed to obtain the physics-based SOC and anode potential.

show abstract

Section: Charge Conservation Equationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Low‐complexity state of charge and anode potential prediction for lithium‐ion batteries using a simplified electrochemical model‐based observer under variable load condition

Pang

Geng

et al. 2022

Intl J of Energy Research

View full text Add to dashboard Cite

show abstract

“…The neural network method is known as a typical data-driven based method, which can obtain the mapping relationship between the parameters and SOC. It also can be applied to estimate SOC [14][15][16][17]. In general, the network training process is concomitant with abnormal phenomenon, such as voltage overfitting.…”

Section: Introductionmentioning

confidence: 99%

“…A co-estimation model based on NARX neural network was proposed by Wang et al to estimate SOC. The experimental results showed that the maximum RMSE of the model is 0.85% [17]. In addition, the NARX was also employed to predict the state of health or temperature for its natures of mining nonlinear mapping relationship and robustness to dynamic characteristics [33,34].…”

Section: Introductionmentioning

confidence: 99%

A Novel Ultracapacitor State-of-Charge Fusion Estimation Method for Electric Vehicles Considering Temperature Uncertainty

et al. 2022

View full text Add to dashboard Cite

An ultracapacitor State-of-Charge (SOC) fusion estimation method for electric vehicles under variable temperature environment is proposed in this paper. Firstly, Thevenin model is selected as the ultracapacitor model. Then, genetic algorithm (GA) is adopted to identify the ultracapacitor model parameters at different temperatures (−10 °C, 10 °C, 25 °C and 40 °C). Secondly, a variable temperature model is established by using polynomial fitting the temperatures and parameters, which is applied to promote the ultracapacitor model applicability. Next, the off-line experimental data is iterated by adaptive extended Kalman filter (AEKF) to train the Nonlinear Auto-Regressive Model with Exogenous Inputs (NARX) neural network. Thirdly, the output of the NARX is employed to compensate the AEKF estimation and thereby realize the ultracapacitor SOC fusion estimation. Finally, the variable temperature model and robustness of the proposed SOC fusion estimation method are verified by experiments. The analysis results show that the root mean square error (RMSE) of the variable temperature model is reduced by 90.187% compared with the non-variable temperature model. In addition, the SOC estimation error of the proposed NARX-AEKF fusion estimation method based on the variable temperature model remains within 2.055%. Even when the SOC initial error is 0.150, the NARX-AEKF fusion estimation method can quickly converge to the reference value within 5.000 s.

show abstract

“…The OCV can only be measured accurately after the battery has rested for a long time, which means this method can not meet the requirements of real life. The second type is data-driven method for example neural network [2,3], support vector machine [4], and fuzzy logic [5]. These methods need huge data sets for training the SOC estimation model.…”

Section: Introductionmentioning

confidence: 99%

State-of-charge estimation for lithium-ion batteries based on dual extended Kalman filter

Wei

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The strategy of estimating SOC by model is highly dependent on the accuracy of model. An SOC estimation method based on a dual extended Kalman fliter (DEKF) is proposed. One of the dual filters is employed to estimate the battery SOC, and the other is used to online identify the model parameters. The SOC estimation results by DEKF are compared with those by single EKF under the US06 Highway Driving Schedule test and Dynamic Stress Test (DST). The comparison results show that DEKF has higher SOC estimation and voltage prediction accuracy. Under the US06 and DST tests, the SOC mean absolute error (MAE) decreases from 2.57% and 3.00% to 1.18% and 1.56%, and the MAE of voltage prediction decreases from 54.6 mV and 38.3 mV to 43.9 mV and 29.1 mV, respectively. The SOC estimation and voltage prediction results demonstrate the effectiveness and accuracy of the proposed method.

show abstract

Co-estimation of state of charge and capacity for lithium-ion battery based on recurrent neural network and support vector machine

Cited by 36 publications

References 30 publications

Low‐complexity state of charge and anode potential prediction for lithium‐ion batteries using a simplified electrochemical model‐based observer under variable load condition

Low‐complexity state of charge and anode potential prediction for lithium‐ion batteries using a simplified electrochemical model‐based observer under variable load condition

A Novel Ultracapacitor State-of-Charge Fusion Estimation Method for Electric Vehicles Considering Temperature Uncertainty

State-of-charge estimation for lithium-ion batteries based on dual extended Kalman filter

Contact Info

Product

Resources

About