A novel intelligent weight decreasing firefly–particle filtering method for accurate state‐of‐charge estimation of lithium‐ion batteries

Qiao, Jialu; Wang, Shunli; Yu, Chunmei; Yang, Xiao Guang; Fernandez, Carlos

doi:10.1002/er.7596

Cited by 11 publications

(6 citation statements)

References 31 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with the paper 32 (which used the ST‐DAEKF algorithm, the MAE is 0.99% under BBDST conditions), the MAE is improved by 0.193%. Compared with the paper 33 (which used the IWDF‐PF algorithm, the MAE accuracy is verified to be 0.96% under BBDST conditions and RMSE is 1.12%), which is an improvement of 0.163% on MAE and 0.0728% on RMSE. Although the average absolute error is greater than the verification result under the DST condition, the stationarity is better than the estimated result under the DST condition.…”

Section: Experiments Verification and Analysismentioning

confidence: 84%

“…The setting appropriate number of neurons can not only improve the calculation accuracy but also improve convergence speed and avoid over-adaptive. When the number of inputs and outputs is small, a single hidden layer is used, and the formula for calculating the number of hidden layers is Equation (33). The transfer function of the hidden layer is set to tansig, and the transfer function of the output layer is set to purlin, whose specific forms are shown in Equations ( 34) and (35).…”

Section: Bp Neural Network and Structure Designmentioning

confidence: 99%

See 1 more Smart Citation

A novel Drosophila‐back propagation method for the lithium‐ion battery state of charge estimation adaptive to complex working conditions

Wang

Fan

et al. 2022

Intl J of Energy Research

Self Cite

View full text Add to dashboard Cite

Accurate state of charge (SOC) for the lithium-ion battery is not only related to user experience but also the top target to avoid overcharge and overdischarge and to use it safely. The back propagation (BP) neural network is widely used in SOC estimation, but there exist some issues, such as easily falling local extreme value, converging slowly, or even unable to converge and even overfitting. The Drosophila algorithm has a simple algorithm and strong global optimization ability, but there is also a problem of direct inheritance to reduce the optimization ability. To solve these problems, an individual migration dynamic step Drosophila (Improved Drosophila) algorithm combined with the BP neural network is proposed to estimate the SOC of lithium-ion batteries and improve estimation accuracy. In addition, the performance of the proposed method is compared with that of its traditional algorithms and other commonly used functions. The experiments are carried out to verify the ternary lithium-ion battery under DST and BBDST conditions., the mean absolute error is less than 0.8%, and the root mean square error is less than 1.4%. The SOC estimation is carried out when the current data under the DST condition are missing, which also has good estimation performance, which shows the robustness of the algorithm. Compared to other algorithms, there is good estimation accuracy.

show abstract

Section: Experiments Verification and Analysismentioning

confidence: 84%

Section: Bp Neural Network and Structure Designmentioning

confidence: 99%

A novel Drosophila‐back propagation method for the lithium‐ion battery state of charge estimation adaptive to complex working conditions

Wang

Fan

et al. 2022

Intl J of Energy Research

Self Cite

View full text Add to dashboard Cite

show abstract

“…The extensive ELM method is also used to predict the capacity of lithium-ion batteries [80]. An SOH prediction method was proposed using the fusion model and attention mechanism, which uses linear regression, SVM, adaptive nonattention mechanism LSTM, attention mechanism LSTM, and experimental verification [81].…”

Section: Application Analysis From Other Studiesmentioning

confidence: 99%

A Critical Review of Improved Deep Convolutional Neural Network for Multi-Timescale State Prediction of Lithium-Ion Batteries

et al. 2022

Self Cite

View full text Add to dashboard Cite

Lithium-ion batteries are widely used as effective energy storage and have become the main component of power supply systems. Accurate battery state prediction is key to ensuring reliability and has significant guidance for optimizing the performance of battery power systems and replacement. Due to the complex and dynamic operations of lithium-ion batteries, the state parameters change with either the working condition or the aging process. The accuracy of online state prediction is difficult to improve, which is an urgent issue that needs to be solved to ensure a reliable and safe power supply. Currently, with the emergence of artificial intelligence (AI), battery state prediction methods based on data-driven methods have high precision and robustness to improve state prediction accuracy. The demanding characteristics of test time are reduced, and this has become the research focus in the related fields. Therefore, the convolutional neural network (CNN) was improved in the data modeling process to establish a deep convolutional neural network ensemble transfer learning (DCNN-ETL) method, which plays a significant role in battery state prediction. This paper reviews and compares several mathematical DCNN models. The key features are identified on the basis of the modeling capability for the state prediction. Then, the prediction methods are classified on the basis of the identified features. In the process of deep learning (DL) calculation, specific criteria for evaluating different modeling accuracy levels are defined. The identified features of the state prediction model are taken advantage of to give relevant conclusions and suggestions. The DCNN-ETL method is selected to realize the reliable state prediction of lithium-ion batteries.

show abstract

“…In addition to the model-based SOC closed-loop estimation strategy, meta-heuristic optimization algorithms have been applied to the estimation of battery state of charge by researchers. For example, Qiao et al 40 proposed an intelligent down-weighted firefly particle filter algorithm, and realized the real-time accurate estimation of the state of charge on the second-order RC equivalent circuit model. Li et al 41 proposed an improved whale optimization algorithm to optimize the prediction process of the feedforward neural network, and further realize the accurate representation of the non-linear characteristics of the battery.…”

Section: Introductionmentioning

confidence: 99%

Battery hysteresis compensation modeling and state‐of‐charge estimation adaptive to time‐varying ambient temperature conditions

Shi

Wang

Fernandez

et al. 2022

Intl J of Energy Research

Self Cite

View full text Add to dashboard Cite

Temperature and cell hysteretic effects are two major factors that influence the reliability and safety in long-term management of battery-integrated systems.In this paper, a hysteresis-compensated electrical characteristic model is established to track the terminal voltage of batteries with the uncertain hysteretic effect of the open-circuit voltage. Then, an autoregressive exogenous model with multi-feature coupling is employed for the identification of the parameters to make them adaptive to the uncertainties of the temperature and hysteretic effects. After that, a novel method for state-of-charge (SOC) estimation based on an adaptive moving window-square root unscented Kalman filter is constructed to avoid the filtering divergence problem caused by the negative error covariance matrix. Multiple constraints, such as Coulombic efficiency, varying ambient temperatures, and hysteresis voltage, are considered for the SOC estimation. Experimental results show that the root-mean-square error for SOC calculation can be limited to 0.0211 when the temperature varied up to 40 C and the root-mean-square error of the voltage measurement noise up to 61.9 mV. The proposed method provides an effective way for batteryintegrated management of electric vehicles. K E Y W O R D Sadaptive moving window-square root unscented Kalman filter, adaptive noise matching, hysteresis-compensated modeling, lithium-ion battery, state-of-charge

show abstract

A novel intelligent weight decreasing firefly–particle filtering method for accurate state‐of‐charge estimation of lithium‐ion batteries

Abstract: Accurate state-of-charge estimation plays an extremely crucial role in battery management systems. To realize the real-time and precise state-of-charge esti-

Cited by 11 publications

References 31 publications

A novel Drosophila‐back propagation method for the lithium‐ion battery state of charge estimation adaptive to complex working conditions

A novel Drosophila‐back propagation method for the lithium‐ion battery state of charge estimation adaptive to complex working conditions

A Critical Review of Improved Deep Convolutional Neural Network for Multi-Timescale State Prediction of Lithium-Ion Batteries

Battery hysteresis compensation modeling and state‐of‐charge estimation adaptive to time‐varying ambient temperature conditions

Contact Info

Product

Resources

About