A review of non-probabilistic machine learning-based state of health estimation techniques for Lithium-ion battery

Sui, Xin; He, Shan; Vilsen, Søren Byg; Meng, Jinhao; Teodorescu, Remus; Stroe, Daniel‐Ioan

doi:10.1016/j.apenergy.2021.117346

Cited by 232 publications

(69 citation statements)

References 154 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance comparison of current advanced ANNs and DLs is summarized in Table I. AI is increasingly used for state estimation in batteries (e.g., SOC, SOH, and/or state of temperature) [18], RUL prediction [19], and balancing control [20]. AI-based lifetime controller (see Fig.…”

Section: B Lifetime Control Using Aimentioning

confidence: 99%

Smart battery concept: A battery that can breathe

Teodorescu¹,

Sui²,

Acharya³

et al. 2022

IET Conf. Proc.

View full text Add to dashboard Cite

Lithium-ion batteries are used in a wide range of applications such as electric vehicles and energy storage systems. However, the aging of the battery cell is inevitable. Especially for battery packs with hundreds of battery cells connected in series/parallel, the aging process will be aggravated due to the difference between battery cells, leading to a limited lifetime and reliability issues. This paper introduces the concept of Smart Battery that combines advanced power electronics and artificial intelligence (AI) intending to develop a new generation of battery solutions for transportation and grid storage. The key feature for controlling the lifetime is the bypass device, a halfbridge that can control individual cell-level load management without affecting the load. An advanced AI-based lifetime controller is trained to recognize the signs of stressed battery cells and decide to insert rest time, resulting in a pulsed current operation. Finally, the following features are expected to be achieved: increased safety and reliability by fault-tolerant operation, user-controlled lifetime, and software reconfiguration for 2 nd life applications. The early experimental results are promising, showing cycle lifetime extension over 50%.

show abstract

Section: B Lifetime Control Using Aimentioning

confidence: 99%

Smart battery concept: A battery that can breathe

Teodorescu¹,

Sui²,

Acharya³

et al. 2022

IET Conf. Proc.

View full text Add to dashboard Cite

show abstract

“…AI is emerging and increasingly used for state estimation in batteries, such as state of charge (SOC), state of health (SOH), state of temperature (SOT) [14], remaining useful lifetime (RUL) prediction [15], and balancing control [16]. AI-based lifetime predictor can be trained based on laboratory data, then the mapping between features (i.e.…”

Section: Ai-based State Estimation Of Lithium Cellsmentioning

confidence: 99%

Multidimensional Machine Learning Balancing in Smart Battery Packs

Fonso

Sui

Acharya

et al. 2021

IECON 2021 – 47th Annual Conference of the IEEE Industrial Electronics Society

Self Cite

View full text Add to dashboard Cite

Lithium-ion batteries have high energy density, lightweight and long life cycle, thus they are the choice for powering electric vehicles. The needed high voltage battery pack is achieved using series-connected cells, that ideally should be identical. However, parameter variations of cells in EVs, along with different working conditions can cause State of Charge (SoC) and temperature imbalances that shorten battery lifetime. Moreover, a series connection can potentially be exposed to singlecell failure. This paper proposes a redundant smart battery topology based on the series connection of individual cell modules. Each module is formed by a cell with an insertion/bypass circuit and a wireless processor that monitors cell states and communicates with a Master controller. To synthesize the nominal voltage, a battery pack with a small redundant number of cells is considered. In this way, it can be made both fault-tolerant and reach higher safety. The problem is then shifted to the control algorithm that at each sampling time has to select "n" cells out of the total cells, according to some goals. A Machine Learningbased control algorithm was developed and tested in Matlab to insert/bypass the cells and reach simultaneous balancing of both SoC and temperature. The new method based on the K-nearest algorithm has been compared in simulation with a conventional sorting balancing method and showed superior performance, especially in temperature balancing.

show abstract

“…However, the MSCC charging method needs a complex controller to decide the turning point of adjacent stages during the charging process, which usually requires accurate SOC and SOH estimation. In recent years, SOC and SOH estimations based on machine learning have developed rapidly, and most of them were developed based on data analysis [14]- [17]. Even though, few of them further investigated the effect of the proposed MSCC charging methods on the battery lifetime.…”

Section: Introductionmentioning

confidence: 99%

Lifetime Extension of Lithium-Ion Batteries With Low-Frequency Pulsed Current Charging

Huang

Liu²,

Meng

et al. 2023

IEEE J. Emerg. Sel. Topics Power Electron.

Self Cite

View full text Add to dashboard Cite

The pulsed current has been proposed to achieve fast charging and extend the lifetime of Lithiumion (Li-ion) batteries. However, the optimal condition of the pulsed current is still inconclusive in previous studies. This paper experimentally investigated the effect of the lowfrequency Positive Pulsed Current (PPC) charging on the lifetime and charging performance of Li-ion batteries. A two-stage degradation model of Li-ion batteries is developed to determine the inhibitory effect of the PPC on degradation mechanisms at different aging stages. Moreover, the changes in the Internal Resistance (IR) and the Incremental Capacity (IC) curve are provided to thoroughly explore the effects of the PPC on the degradation of Li-ion batteries. Compared with the traditional Constant Current (CC) charging, the lifetime, maximum rising temperature, and energy efficiency of the Li-ion batteries that were cycled by the PPC charging are improved by 81.6%, 60.5%, and 9.1%, respectively, after 1000 cycles. Therefore, low-frequency PPC charging should be considered as a promising charging strategy for Li-ion batteries.

show abstract

A review of non-probabilistic machine learning-based state of health estimation techniques for Lithium-ion battery

Cited by 232 publications

References 154 publications

Smart battery concept: A battery that can breathe

Smart battery concept: A battery that can breathe

Multidimensional Machine Learning Balancing in Smart Battery Packs

Lifetime Extension of Lithium-Ion Batteries With Low-Frequency Pulsed Current Charging

Contact Info

Product

Resources

About