Battery Lifetime Prediction and Degradation Reconstruction based on Probabilistic Convolutional Neural Network

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

1 Citationer (Scopus)
6 Downloads (Pure)

Abstract

Capacity degradation of lithium-ion batteries influences their service abilities as energy storage systems. Lifetime prediction, historical degradation curve trajectory, and capacity estimation help prognose the long-term serviceability and timely health status of batteries, which guides early maintenance and intelligent management. This paper proposed a novel method to predict the lifetime, reconstruct the historical degradation curve and estimate the capacity via excavating the information hindered under partially charged capacity and temperature curves. Only partial raw data of temperature and charged capacity are needed for modeling without manual feature engineering. The convolutional neural network is used to build the lifetime prediction and capacity estimation models. In addition, the probabilistic regression is added to the establishment of the capacity estimation model, which could provide the probabilistic estimation results. Finally, transfer learning is adopted to update the model with a few available data of testing batteries. Results show that the predictions are accurate and reliable.

OriginalsprogEngelsk
TitelIEEE 13th International Symposium on Power Electronics for Distributed Generation Systems (PEDG)
ForlagIEEE
Publikationsdato2022
ISBN (Elektronisk)978-1-6654-6618-9
DOI
StatusUdgivet - 2022
Begivenhed13th IEEE International Symposium on Power Electronics for Distributed Generation Systems, PEDG 2022 - Kiel, Tyskland
Varighed: 26 jun. 202229 jun. 2022

Konference

Konference13th IEEE International Symposium on Power Electronics for Distributed Generation Systems, PEDG 2022
Land/OmrådeTyskland
ByKiel
Periode26/06/202229/06/2022
NavnIEEE International Symposium on Power Electronics for Distributed Generation Systems (PEDG)
ISSN2329-5767

Bibliografisk note

Publisher Copyright:
© 2022 IEEE.

Fingeraftryk

Dyk ned i forskningsemnerne om 'Battery Lifetime Prediction and Degradation Reconstruction based on Probabilistic Convolutional Neural Network'. Sammen danner de et unikt fingeraftryk.

Citationsformater