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

Wang, Shunli; Ren, Pu; Takyi‐Aninakwa, Paul; Jin, Siyu; Fernandez, Carlos

doi:10.3390/en15145053

Cited by 90 publications

(24 citation statements)

References 113 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the literature, the capacity loss is often used synonymously with the self-discharge of a cell. 34,42 However, the self-discharge current measured during electrical characterization may deviate from the capacity loss. While leakage currents and side reactions certainly cause self-discharge, irreversible effects like LLI and LAM at the anode may also contribute to a cell voltage decline.…”

Section: Theorymentioning

confidence: 99%

Relaxation Effects in Self-Discharge Measurements of Lithium-Ion Batteries

Roth

Streck

Oberbauer

et al. 2023

J. Electrochem. Soc.

View full text Add to dashboard Cite

In order to determine the quality of newly produced lithium-ion cells, self-discharge measurements are performed after manufacturing during the so-called aging step. The aging step is a time-consuming and cost-intensive process due to relaxation effects disturbing the self-discharge measuremtens. Relaxation effects are mainly attributed to voltage relaxation and anode overhang equalization. In this work, different methods for electrical self-discharge measurement, such as the voltage decay method, the voltage hold method, and the capacity loss method, were investigated using commercial Samsung INR21700-50E cylindrical cells (NCA/silicon-graphite) and non-commercial pouch-cells (NMC622/graphite). Various preconditioning methods allowed a distinction to be made between undisturbed, short-term, and long-term disturbed cells. While short-term disturbances subsided after several hours, long-term disturbances due to anode overhang were found to significantly disturb all electrical self-discharge measurements for several weeks. A theoretical explanation was introduced, describing the lithium inventory change due to anode and coupled side reactions being measured differently by voltage- and capacity-based methods. Experimental results confirmed this notion and showed that voltage-based self-discharge measurements underestimated the anode overhang equalization. A comparison to the initial cell aging data indicated that the self-discharge measurement performed shortly after cell formation was disturbed by the anode overhang equalization.

show abstract

Section: Theorymentioning

confidence: 99%

Relaxation Effects in Self-Discharge Measurements of Lithium-Ion Batteries

Roth

Streck

Oberbauer

et al. 2023

J. Electrochem. Soc.

View full text Add to dashboard Cite

show abstract

“…To linearize nonlinear systems such as Li‐ion batteries, the state space equations’ linearization is obtained by utilizing the Taylor series expansion of the EKF method. [ 26,27 ] Therefore, the EKF algorithm is utilized to estimate the SOC of Li‐ion batteries. The state space equation and observation equation for a nonlinear system are shown in Equation (12).…”

Section: Soc Estimation Methods and Parameter Identificationmentioning

confidence: 99%

State‐of‐Charge Estimation of Lithium‐Ion Battery Based on an Improved Dual‐Polarization Model

et al. 2023

View full text Add to dashboard Cite

This article proposes a state‐of‐charge (SOC) estimation method to eliminate the influence of the hysteresis effect and the ambient temperature. First, an improved dual‐polarization (DP) model considering the hysteresis effect and the ambient temperature is established. A hysteresis voltage source is connected in series with a couple of resistance–capacitance pairs in the improved DP model, all the parameters of which are related to the ambient temperature to depict the temperature characteristics of the battery. Second, the forgetting factor recursive least squares method is utilized to identify the parameters under the battery dynamic test data at different temperatures. The proposed model and parameterization scheme integrate the effects of hysteresis and temperature, greatly enhancing the performance of the proposed method at different temperatures. Finally, an extended Kalman filter algorithm for SOC estimation is adopted to verify the improved DP model and the simulation indicates that the error of SOC estimation is within 1.5% at different ambient temperatures. The proposed method can improve the precision of the SOC estimation even if the temperature is below −10 or above 50 °C.

show abstract

“…The mean absolute percentage error (MAPE) and the weighted mean accuracy (WMA) are used as evaluation indexes to evaluate the performance and forecasting effect of the forecasting model [29]. The calculation formulas are as follows:…”

Section: Evaluating Indictormentioning

confidence: 99%

Research on Multiple Load Short-Term Forecasting Model of Integrated Energy Distribution System Based on Mogrifier-Quantum Weighted MELSTM

Song

Zhang

2023

Energies

View full text Add to dashboard Cite

Accurate and efficient short-term forecasting of multiple loads is of great significance to the operation control and scheduling of integrated energy distribution systems. In order to improve the effect of load forecasting, a mogrifier-quantum weighted memory enhancement long short-term memory (Mogrifier-QWMELSTM) neural network forecasting model is proposed. Compared with the conventional LSTM neural network model, the model proposed in this paper has three improvements in model structure and model composition. First, the mogrifier is added to make the data fully interact with each other. This addition can help enhance the correlation between the front and rear data and improve generalization, which is the main disadvantage of LSTM neural network. Second, the memory enhancement mechanism is added on the forget gate to realize the extraction and recovery of forgotten information. The addition can help improve the gradient transmission ability in the learning process of the neural network, make the neural network remain sensitive to distant data information, and enhance the memory ability. Third, the model is composed of quantum weighted neurons. Compared with conventional neurons, quantum weighted neurons have significant advantages in nonlinear data processing and parallel computing, which help to improve the accuracy of load forecasting. The simulation results show that the weighted mean accuracy of the proposed model can reach more than 97.5% in summer and winter. Moreover, the proposed model has good forecasting effect on seven typical days in winter, which shows that the model has good stability.

show abstract

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

Cited by 90 publications

References 113 publications

Relaxation Effects in Self-Discharge Measurements of Lithium-Ion Batteries

Relaxation Effects in Self-Discharge Measurements of Lithium-Ion Batteries

State‐of‐Charge Estimation of Lithium‐Ion Battery Based on an Improved Dual‐Polarization Model

Research on Multiple Load Short-Term Forecasting Model of Integrated Energy Distribution System Based on Mogrifier-Quantum Weighted MELSTM

Contact Info

Product

Resources

About