A controllable deep transfer learning network with multiple domain adaptation for battery state-of-charge estimation

Isaiah Oyewole, Abdallah Chehade and Youngki Kim

Applied Energy, 2022, vol. 312, issue C, No S0306261922001842

Abstract: Deep learning models have been drawing significant attention in the literature of state-of-charge (SOC) estimation because of their capabilities to capture non-trivial temporal patterns. However, most of such models ignore cell-to-cell variations or focus on short-term estimations that are not practical for battery cells with limited charging-discharging history. We propose a Controllable Deep Transfer Learning (CDTL) network for short and long-term SOC estimations at early stages of degradation. The CDTL utilizes shared knowledge between the target cells of interest and historical source cellswith rich SOC data usingcontrollable Multiple Domain Adaptation (MDA). Specifically,the CDTL consists of two long-short term memory (LSTM) networks, the source LSTM, and the target LSTM.The source LSTM istrained onSOC data from historical battery cells.The target LSTMis then trained using limited available SOC data from the target cell and thetransferredknowledge from the source LSTM usingcontrollable MDAwith adaptive regularization. The contributions of the CDTL are two-folded. First, it reducesthe likelihood of negative transfer learning using controllable MDA with adaptive regularization, whichenhances the target LSTMgeneralizability for long-term SOC estimation. Second, the CDTL offers theoretical guarantees on the controllability and convergenceof transferred knowledge from the source cell to target cell. The experimental results demonstrate that the proposed CDTL outperforms existing deepand transfer learning benchmarkswith1) amaximum improvement of 60% in root-mean-squared error (RMSE) for battery cells with the same chemistry,2) an averageimprovement of 50% in RMSE across different battery chemistries, and3) about39% reduction in computational time.

Keywords: Lithium-ion batteries; Deep learning model; Transfer learning; Multiple domain adaptation; State-of-charge (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (15)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0306261922001842
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:appene:v:312:y:2022:i:c:s0306261922001842

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/journaldescription.cws_home/405891/bibliographic
http://www.elsevier. ... 405891/bibliographic

DOI: 10.1016/j.apenergy.2022.118726

Access Statistics for this article

Applied Energy is currently edited by J. Yan

More articles in Applied Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().