Calendar Ageing Model for Li-Ion Batteries Using Transfer Learning Methods

Azkue, Markel; Lucu, Mattin; Martinez-Laserna, Egoitz; Aizpuru, Iosu

doi:10.3390/wevj12030145

Cited by 14 publications

(14 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This degradation pathway gets faster at higher temperatures, when storing at higher state-of-charge, and at higher charging rates. [398][399][400][401][402] This process results in ca. 10% loss in the cyclable charge capacity within ca.…”

Section: Vanadium Rfbs-the Technology Frontrunnersmentioning

confidence: 99%

Review—Flow Batteries from 1879 to 2022 and Beyond

Tolmachev

2023

J. Electrochem. Soc.

View full text Add to dashboard Cite

We present a quantitative bibliometric study of flow battery technology from the first zinc-bromine cells in the 1870s to megawatt vanadium redox flow battery (RFB) installations in the 2020s. We emphasize that the cost advantage of RFBs in multi-hour charge-discharge cycles is compromised by the inferior energy efficiency of these systems, and that there are limits on the efficiency improvement due to internal cross-over and the cost of power (at low current densities) and due to acceptable pressure drop (at high current densities). Differences between lithium-ion and vanadium redox flow batteries are discussed from the end-user perspective.

show abstract

Section: Vanadium Rfbs-the Technology Frontrunnersmentioning

confidence: 99%

Review—Flow Batteries from 1879 to 2022 and Beyond

Tolmachev

2023

J. Electrochem. Soc.

View full text Add to dashboard Cite

show abstract

“…Compared to Azkue et al (2021), Shen et al (2020) vary the amount of target data available for fine-tuning. They find that training a benchmark model from scratch needs three times more training samples compared to transfer learning.…”

Section: Battery Ageingmentioning

confidence: 99%

State of Health Forecasting of Heterogeneous Lithium-ion Battery Types and Operation Enabled by Transfer Learning

Bülow¹,

Meisen

2022

PHME_CONF

View full text Add to dashboard Cite

Due to the global transition to electromobility and the associated increased use of high-performance batteries, research is increasingly focused on estimating and forecasting the state of health (SOH) of lithium-ion batteries. Several data-intensive and well-performing methods for SOH forecasting have been introduced. However, these approaches are only reliable for new battery types, e.g., with a new cell chemistry, if a sufficient amount of training data is given, which is rarely the case. A promising approach is to transfer an established model of another battery type to the new battery type, using only a small amount of data of the new battery type. Such methods in machine learning are known as transfer learning. The usefulness and applicability of transfer learning and its underlying methods have been very successfully demonstrated in various fields, such as computer vision and natural language processing. Heterogeneity in battery systems, such as differences in rated capacity, cell cathode materials, as well as applied stress from use, necessitate transfer learning concepts for data-based battery SOH forecasting models. Hereby, the general electrochemical behavior of lithium-ion batteries, as a major common characteristic, supposedly provides an excellent starting point for a transfer learning approach for SOH forecasting models. In this paper, we present a transfer learning approach for SOH forecasting models using a multilayer perceptron (MLP). We apply and evaluate it on the method presented by von Bülow, Mentz, and Meisen (2021) using five battery datasets. In this regard, we investigate the optimal conditions and settings for the development of transfer learning with respect to suitable data from the target domain, as well as hyperparameters such as learning rate and frozen layers. We show that for the transfer of a SOH forecasting model to a new battery type it is more beneficial to have data of few old batteries, compared to data of many new batteries, especially in the case of superlinear degradation with knee points. Contrarily to computer vision freezing no layers is preferable in 95% of the experimental scenarios.

show abstract

“…With this computational capacity, continuous monitoring is possible with the different state estimation algorithms. In addition, it allows predictions of LIB life prognosis by using new and more complex methods for RUL prediction [13], [14]. On the other hand, by being able to track historical LIB data from multiple energy storage systems deployed in different applications, anomalies in LIB operation can be detected.…”

Section: Battery In the Cloudmentioning

confidence: 99%

Module-Level Modelling Approach for a Cloudbased Digital Twin Platform for Li-Ion Batteries

Lizaso-Eguileta

Martinez-Laserna

Rivas

et al. 2021

2021 IEEE Vehicle Power and Propulsion Conference (VPPC)

View full text Add to dashboard Cite

The pursue of the new increasingly intelligent, and heavier state estimation algorithms requires a significant amount of data and computing power, which may challenge their deployment in current BMS solutions. To address that issue, this paper proposes a cloud-based Digital Twin Platform to extend computing power and data storage capacity. This tool aims to contain the integration of models to analyse thermoelectric and ageing aspects of a LIB, based on experimental operation data by comparative analysis. Based on well-known cell-level modelling techniques, a module-level modelling approach is proposed and an experimental validation platform is suggested.

show abstract

Calendar Ageing Model for Li-Ion Batteries Using Transfer Learning Methods

Cited by 14 publications

References 18 publications

Review—Flow Batteries from 1879 to 2022 and Beyond

Review—Flow Batteries from 1879 to 2022 and Beyond

State of Health Forecasting of Heterogeneous Lithium-ion Battery Types and Operation Enabled by Transfer Learning

Module-Level Modelling Approach for a Cloudbased Digital Twin Platform for Li-Ion Batteries

Contact Info

Product

Resources

About