A Review on Battery Model-Based and Data-Driven Methods for Battery Management Systems

Lucaferri, Valentina; Quercio, Michele; Laudani, Antonino; Riganti Fulginei, Francesco

doi:10.3390/en16237807

Cited by 22 publications

(3 citation statements)

References 72 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These data-driven, or black box, models have gained in popularity in battery modeling. Employing a huge dataset of battery measurements, these models deploy machine learning techniques to understand the link between output variables (such as voltage and capacity) and input factors (like temperature, current, and state of charge) [47]. The DD model's capability to identify and track a battery's dynamics and accurately estimate the SoC has led to an increase in their utilization, since this is considered a significant challenge with the conventional white models.…”

Section: State-of-charge Estimation Approachesmentioning

confidence: 99%

Comparative Study-Based Data-Driven Models for Lithium-Ion Battery State-of-Charge Estimation

Hussein,

Esoofally,

Donekal

et al. 2024

Batteries

View full text Add to dashboard Cite

Batteries have been considered a key element in several applications, ranging from grid-scale storage systems through electric vehicles to daily-use small-scale electronic devices. However, excessive charging and discharging will impair their capabilities and could cause their applications to fail catastrophically. Among several diagnostic indices, state-of-charge estimation is essential for evaluating a battery’s capabilities. Various approaches have been introduced to reach this target, including white, gray, and black box or data-driven battery models. The main objective of this work is to provide an extensive comparison of currently highly utilized machine learning-based estimation techniques. The paper thoroughly investigates these models’ architectures, computational burdens, advantages, drawbacks, and robustness validation. The evaluation’s main criteria were based on measurements recorded under various operating conditions at the Energy Systems Research Laboratory (ESRL) at FIU for the eFlex 52.8 V/5.4 kWh lithium iron phosphate battery pack. The primary outcome of this research is that, while the random forest regression (RFR) model emerges as the most effective tool for SoC estimation in lithium-ion batteries, there is potential to enhance the performance of simpler models through strategic adjustments and optimizations. Additionally, the choice of model ultimately depends on the specific requirements of the task at hand, balancing the need for accuracy with the complexity and computational resources available and how it can be merged with other SoC estimation approaches to achieve high precision.

show abstract

Section: State-of-charge Estimation Approachesmentioning

confidence: 99%

Comparative Study-Based Data-Driven Models for Lithium-Ion Battery State-of-Charge Estimation

Hussein,

Esoofally,

Donekal

et al. 2024

Batteries

View full text Add to dashboard Cite

show abstract

“…Battery SOH indicates the health status of the battery, which is usually defined as capacity degradation or internal resistance growth [5][6][7][8]. A lead-acid battery is composed of positive and negative plates, separators, and electrolytes.…”

Section: Introductionmentioning

confidence: 99%

Non-Invasive Method-Based Estimation of Battery State-of-Health with Dynamical Response Characteristics of Load Surges

Fan,

Lin,

Huang

2024

Energies

View full text Add to dashboard Cite

Battery state-of-health (SOH) estimation is an effective approach to evaluate battery reliability and reduce maintenance costs for battery-based backup power supply systems. This paper proposes a novel SOH estimation method for batteries, which only uses the response characteristics of load surges and is, therefore, non-destructive to the estimated battery and its system. The discrete wavelet transform (DWT) method based on multi-resolution analysis (MRA) is used for wavelet energy features extraction, and the fuzzy cerebellar model neural network (FCMNN) is introduced to design the battery SOH estimator. The response voltage signals to load surges are used in the training and detection process of the FCMNN. Compared to conventional methods, the proposed method only exploits characteristics of online response signals to the inrush currents rather than injecting interference signals into the battery. The effectiveness of the proposed method is validated by detailed simulation analysis and experiments.

show abstract

“…The resistance of the cell can be assumed as constant. For modeling, the R-int cell model is adopted [23][24][25]. The dependence of EMF on the degree of discharge can be described analytically [26,27].…”

mentioning

confidence: 99%

Simulation of the operation of the on-board energy storage in the tractional system of a quarry locomotive

Kondratieva,

Overianova,

Tkachenko

et al. 2024

TST

View full text Add to dashboard Cite

The ways of updating the rolling stock of open-pit railways have been considered and the main methods of using the energy storage on the locomotive for open-pit railways have been determined. A mathematical model has been developed, which includes a model of train movement along the railway section and during maneuvering and a model of energy processes in the traction system with onboard energy storage. Simulations were performed in a cycle that included movement from the crushing plant to the transshipment point with empty dump trucks, maneuvering during loading, movement from the crushing plant to the transshipment point with loaded dump trucks, and maneuvering during unloading. The simulation took into account the limitation of power consumption at the level of 4000 kW. The parameters of the energy storage device were determined, for which Toshiba SCiB 20Ah-HP cells were selected. The power of the energy storage is 3600 kW, and the energy capacity is 414 kWh. The use of modules for the formation of an energy storage device is proposed. It was determined that the energy consumption per work cycle with the selected energy exchange algorithm taking into account electrodynamic braking is about 200 kWh, and the charge reduction per drive cycle is 36%. The service life of the energy storage with the selected cells is estimated at 8 years.

show abstract

A Review on Battery Model-Based and Data-Driven Methods for Battery Management Systems

Cited by 22 publications

References 72 publications

Comparative Study-Based Data-Driven Models for Lithium-Ion Battery State-of-Charge Estimation

Comparative Study-Based Data-Driven Models for Lithium-Ion Battery State-of-Charge Estimation

Non-Invasive Method-Based Estimation of Battery State-of-Health with Dynamical Response Characteristics of Load Surges

Simulation of the operation of the on-board energy storage in the tractional system of a quarry locomotive

Contact Info

Product

Resources

About