“…Especially in power hybrid battery packs for industrial applications, the electrochemical inconsistency between the two individual cells can have a great impact on the effective management of the battery packs. Thus, realizing highly accurate SOC estimation of individual cells is key, [ 51 ] and further realization of battery pack estimation is also necessary for discussion. We separately get graphite/LiCoO soft pack cell profiles from the CALCE database at room temperature, which consists of multiple SOC variation ranges during different cycles.…”
As lithium‐ion batteries are the main power source of new energy vehicles, making accurate predictions of unknown State of Charge (SOC) during vehicle operation for vehicle data monitoring is vital to the advancement of intelligent new energy vehicles. In this manuscript, an expression tree‐based genetic programming regression model (ETGPR) is proposed to estimate the real‐time SOC of lithium‐ion batteries. The proposed model mainly adopts the symbolic regression technique. In addition to the current–voltage curves being fed into the model, an additional approach is designed to ensure real‐time model predictions in dynamic situations, which includes the previous moment's power in the input parameters. Different seed hyperparameters in the model are set, and the model automatically performs evolutionary calculations. Subsequently, each parameter of the model is optimally adjusted to obtain a set of regression expressions that accurately reflect the relationship between the SOC and each parameter after a specified number of iterations. Finally, the generated expression is proven to perform better in terms of its ability to capture the nonlinear relationship between SOC and battery variables. Also, the model demonstrates excellent robustness in the presence of notable noise from input‐independent features compared to other models, a root mean square error (RMSE) of less than 0.3% and a mean absolute error (MAE) of less than 0.2% are achieved. Furthermore, the potential of the model's implement‐ability under variable temperature and real driving data conditions is verified.
“…Especially in power hybrid battery packs for industrial applications, the electrochemical inconsistency between the two individual cells can have a great impact on the effective management of the battery packs. Thus, realizing highly accurate SOC estimation of individual cells is key, [ 51 ] and further realization of battery pack estimation is also necessary for discussion. We separately get graphite/LiCoO soft pack cell profiles from the CALCE database at room temperature, which consists of multiple SOC variation ranges during different cycles.…”
As lithium‐ion batteries are the main power source of new energy vehicles, making accurate predictions of unknown State of Charge (SOC) during vehicle operation for vehicle data monitoring is vital to the advancement of intelligent new energy vehicles. In this manuscript, an expression tree‐based genetic programming regression model (ETGPR) is proposed to estimate the real‐time SOC of lithium‐ion batteries. The proposed model mainly adopts the symbolic regression technique. In addition to the current–voltage curves being fed into the model, an additional approach is designed to ensure real‐time model predictions in dynamic situations, which includes the previous moment's power in the input parameters. Different seed hyperparameters in the model are set, and the model automatically performs evolutionary calculations. Subsequently, each parameter of the model is optimally adjusted to obtain a set of regression expressions that accurately reflect the relationship between the SOC and each parameter after a specified number of iterations. Finally, the generated expression is proven to perform better in terms of its ability to capture the nonlinear relationship between SOC and battery variables. Also, the model demonstrates excellent robustness in the presence of notable noise from input‐independent features compared to other models, a root mean square error (RMSE) of less than 0.3% and a mean absolute error (MAE) of less than 0.2% are achieved. Furthermore, the potential of the model's implement‐ability under variable temperature and real driving data conditions is verified.
“…These unique polarization behaviors limit the accuracy of model-based estimation algorithms in calculating its OCV, further increasing the difficulty of SOC estimation. Therefore, the accuracy of SOC estimation of LFP batteries by existing methods is lower than that of other types of batteries [18].…”
LiFePO4 batteries exhibit voltage plateau and voltage hysteresis characteristics during charging and discharging processes; however, the estimation of state-of-charge relies on voltage detection. Thus, the estimation accuracy of SOC is low in a traditional method. In this paper, a full charge and discharge SOC correction method is proposed; i.e., the SOC is corrected to 100% when the battery is fully charged and to 0% when fully discharged, and the actual usable capacity is corrected using the fully discharged capacity after being fully charged. Thereby, the cumulative error of the ampere-hour integration method is dynamically corrected. In engineering applications, however, the battery systems do not always undergo full charge and discharge cycling due to the operating conditions. By making full use of the distributed control characteristics of the multi-branch topology battery system, the present work proposes an optimized system control strategy to realize the unsynchronized full charge and discharge cluster by cluster, which extends the application of the full charge and discharge SOC correction method. The experimental results verify the accuracy of the proposed SOC correction method and the feasibility of the control strategy. A more reliable and efficient battery management scheme is provided for LFP battery system, which has high practical value in engineering.
“…2 However, a continuous battery operation may cause capacity degradation and change the internal parameters of the battery. 3,4 To ensure long-term stable operation of EVs, an accuracy estimation of state of charge (SOC) must be requested to predict LIB remaining capacity.…”
Accurate state of charge (SOC) estimation for lithium-ion batteries is essential to guarantee long-term stable operation of electric vehicles. In this study, an equivalent sliding mode observer (ESMO) is proposed to estimate the battery SOC. First, a sliding mode observer (SMO) was designed with Walcott-Zak structure to increase the sliding region. Next, a controlled equivalent function was used to replace sign function in the SMO, which can lessen chattering issue and increase system robustness. Furthermore, this study performs online parameter identification of a second-order resistance capacitor equivalent circuit model using the forgetting factor recursive least squares approach. Lastly, the experiments under dynamic current conditions were conducted to verify the proposed ESMO. The results show that the mean square error of the ESMO is decreased to 0.5%, which implies that the proposed ESMO can estimate the SOC with higher accuracy compared to the traditional SMO.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.