Lithium-ion battery degradation forecasting using data-driven time series models

The maritime industry faces significant challenges as it adapts from a major carbon emitter to a low-emission sector, intending to eventually achieve zero emissions. This transition requires innovative solutions for both new and old vessels, lithium-ion batteries show promise in achieving these goals. Battery management systems improve reliability and safety by monitoring voltage, current, and temperature through sensors. These parameters enable the prediction of remaining usable life, allowing for prompt maintenance and replacement before failure occurs. Publicly accessible lithium battery datasets provide a useful starting point for predictive degradation model development. This study investigates time series modeling methodologies for lithium-ion battery degradation, utilizing NASA’s battery degradation dataset. Three models viz. Autoregressive, Autoregressive Integrated Moving Average, and its extension using seasonality parameters were developed. They were tested with four train/test ratios to predict the remaining useful life values and assess the accuracy of the predicted degradation curve against experimental results. From the results, it was observed that the Autoregressive Integrated Moving Average model had the least combined average Root Mean Square Error values, resulting in a good overall degradation curve fitting, whereas the Seasonal Autoregressive Integrated Moving Average model was able to predict the End of Life values more accurately.

Subjects

lithium-ion batteries

data driven time series model

AR

ARIMA

SARIMA

remaining useful life

DDC Class

330: Economics

380: Commerce, Communications, Transport

519: Applied Mathematics, Probabilities

623: Military Engineering and Marine Engineering

660: Chemistry; Chemical Engineering

Lizenz

https://creativecommons.org/licenses/by/4.0/

Publication version

publishedVersion

Name

v007t14a004-omae2025-156104-1.pdf

Size

1.87 MB

Format

Adobe PDF

Options

Lithium-ion battery degradation forecasting using data-driven time series models