State of charge estimation of lithium-ion batteries using hybrid autoencoder and Long Short Term Memory neural networks

Fasahat, Mohammad; Manthouri, Mohammad

doi:10.1016/j.jpowsour.2020.228375

Cited by 114 publications

(34 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This unit structure improves the standard RNN unit, the cyclic modules of which only contain a simple structure of a hyperbolic tangent layer, and without concept of candidate states. 41 The forward transfer process of the LSTM unit at time step k is as follows: W c are related to the weight of forget gate, input gate, output state, and unit gate, respectively. The symbol b is the deviation value.…”

Section: Learning Algorithm Of Lstm Modelmentioning

confidence: 99%

State‐of‐health estimation and remaining useful life for lithium‐ion battery based on deep learning with Bayesian hyperparameter optimization

Kong

Wang

Ping

2021

Intl J of Energy Research

View full text Add to dashboard Cite

Section: Learning Algorithm Of Lstm Modelmentioning

confidence: 99%

State‐of‐health estimation and remaining useful life for lithium‐ion battery based on deep learning with Bayesian hyperparameter optimization

Kong

Wang

Ping

2021

Intl J of Energy Research

View full text Add to dashboard Cite

“…Learning algorithms may be applied to estimate the SOC, such as neural network (NN) [15][16][17][18], fuzzy logic [19], support vector machine (SVM) [20,21], and genetic algorithm [22,23]. These algorithms are generic and have good mapping accuracy in non-linear processes, but their sensitiveness quality and quantity of the training data are high and have a poor capability for fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

State of charge estimation for lithium‐ion batteries based on square root sigma point Kalman filter considering temperature variations

Mahboubi

Gavzan

Saidi

et al. 2022

IET Electrical Syst in Trans

View full text Add to dashboard Cite

The battery management system (BMS) in electric vehicles monitors the state of charge (SOC) and state of health (SOH) of lithium‐ion battery by controlling transient parameters such as voltage, current, and temperature prevents the battery from operating outside the optimal operating range. The main feature of the battery management system is the correct estimation of the SOC in the broad range of vehicle navigation. In this paper, to estimate real‐time of SOC in lithium‐ion batteries and overcome faults of Extended Kalman Filter (EKF), the Square‐Root Sigma Point Kalman Filter is applied on the basis of numerical approximations rather than analytical methods of EKF. For this purpose, the Hybrid Pulse Power Characterisation tests are combined with the non‐linear least square method that acquired the second‐order equivalent circuit model parameters. Then, the newly developed method is tested with an 18,650 cylindrical lithium‐ion battery with a nominal capacity of 2600 mAh in four different ambient temperatures. Finally, the accuracy and effectiveness of the two proposed methods are verified by comparing with results of pulse discharge and dynamic driving cycle tests. The comparison results indicate the error of the proposed algorithm is about 0.02 under the most test conditions.

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 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

State of charge estimation of lithium-ion batteries using hybrid autoencoder and Long Short Term Memory neural networks

Cited by 114 publications

References 24 publications

State‐of‐health estimation and remaining useful life for lithium‐ion battery based on deep learning with Bayesian hyperparameter optimization

State‐of‐health estimation and remaining useful life for lithium‐ion battery based on deep learning with Bayesian hyperparameter optimization

State of charge estimation for lithium‐ion batteries based on square root sigma point Kalman filter considering temperature variations

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

Contact Info

Product

Resources

About