PSA-DMCF-SVAE: A Lithium Battery SOH Prediction Framework with ProbSparse Self-Attention and Deep Multidimensional Features
Energy Storage and Applications · 01.08.2026 · 3 (3) · 11
DOI: 10.3390/esa3030011 ↗Kurz gefasst
Fachartikel in der Zeitschrift Energy Storage and Applications, online erschienen am 01.08.2026. Verfasst von Weihao Sun und 6 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Shanghai Special Plan for Local Colleges and Universities for Capacity Building.
Abstract (Originalsprache)
Accurate state of health (SOH) evaluation is essential for lithium-ion battery safety. Conventional prediction models suffer high computation overhead and insufficient multidimensional feature fusion, leading to poor generalization across working conditions. This work develops the PSA-DMCF-SVAE framework. Ten health factors are extracted from cycling data, and four high-correlation indicators are selected via Pearson screening. The method combines stacked ensemble learning and sparse variational autoencoder (SVAE) for multi-scale aging feature extraction, with an embedded ProbSparse self-attention module to adaptively weight base learners and cut computational complexity. Experiments on NASA battery data reveal over 40% lower prediction error and 42% less feature redundancy than classic stacking architectures. Cross-domain validation on an MIT fast-charging dataset confirms the model’s zero-shot generalization under high-rate, noisy discharge conditions, offering a practical solution for battery management systems.
Förderung
- National Natural Science Foundation of China
- Shanghai Special Plan for Local Colleges and Universities for Capacity Building
Zitieren
APA
Sun, W., Liu, G., Chen, J., Zhao, Y., Cheng, Y., Xiao, G., & Bavirisetti, D. P. (2026). PSA-DMCF-SVAE: A Lithium Battery SOH Prediction Framework with ProbSparse Self-Attention and Deep Multidimensional Features. Energy Storage and Applications, 3(3), 11. https://doi.org/10.3390/esa3030011
Vancouver
Sun W, Liu G, Chen J, Zhao Y, Cheng Y, Xiao G, et al. PSA-DMCF-SVAE: A Lithium Battery SOH Prediction Framework with ProbSparse Self-Attention and Deep Multidimensional Features. Energy Storage and Applications. 2026;3(3):11. doi:10.3390/esa3030011
BibTeX
@article{Sun2026,
author = {Sun, Weihao and Liu, Gang and Chen, Jiawei and Zhao, Yiyao and Cheng, Yuting and Xiao, Gang and Bavirisetti, Durga Prasad},
title = {PSA-DMCF-SVAE: A Lithium Battery SOH Prediction Framework with ProbSparse Self-Attention and Deep Multidimensional Features},
journal = {Energy Storage and Applications},
year = {2026},
volume = {3},
number = {3},
pages = {11},
doi = {10.3390/esa3030011}
}
EUVIMED