aiqbench analysis
This research introduces a novel cross-expert framework leveraging GRUs, CNNs, and Transformers to jointly predict lithium-ion battery remaining useful life and capacity using only partial-charging data. By fusing short-term behavioral representations with long-term degradation trends, the model achieves state-of-the-art RUL accuracy on public datasets while demonstrating a specific trade-off between lifespan prediction and capacity estimation errors. The approach advances machine learning applications in predictive maintenance for energy storage systems without requiring full-cycle historical inputs.
Joint Remaining Useful Life Prediction and Capacity Estimation of Lithium-Ion Batteries Using Partial-Charging Data
arXiv:2609.21932v1 Announce Type: new Abstract: Joint remaining useful life (RUL) prediction and capacity estimation require representations of both gradual degradation and recent battery behavior. This paper presents a cross-expert framework using partial-charging measurements without measured historical full-cycle capacity as an input. The RUL Expert encodes nominal 10-min segments from ten cycles sampled within a 30-cycle history using a pretrained gated recurrent unit (GRU) encoder, a two-dimensional convolutional neural network (2D-CNN), and a temporal GRU. The Capacity Expert processes statistical descriptors of nominal 40-min segments from ten consecutive cycles using a 2D-CNN and a Transformer. A feature-wise linear modulation module uses the short-term representation to condition the long-term representation for joint prediction. Training comprises supervised autoencoder pretraining, independent expert pretraining, and fusion training with frozen experts. On two public battery-aging datasets, the reference configuration achieves mean RUL root-mean-square errors of 143.69 and 161.10 cycles and capacity errors of 12.36 and 7.28mAh, respectively. On Dataset I, fusion reduces both mean errors relative to either standalone expert. The results demonstrate a trade-off between RUL and capacity accuracy: the proposed method attains the lowest reported RUL RMSE among the compared methods on both datasets, whereas several baselines yield lower capacity errors.
Abstract:Joint remaining useful life (RUL) prediction and capacity estimation require representations of both gradual degradation and recent battery behavior. This paper presents a cross-expert framework using partial-charging measurements without measured historical full-cycle capacity as an input. The RUL Expert encodes nominal 10-min segments from ten cycles sampled within a 30-cycle history using a pretrained gated recurrent unit (GRU) encoder, a two-dimensional convolutional neural network (2D-CNN), and a temporal GRU. The Capacity Expert processes statistical descriptors of nominal 40-min segments from ten consecutive cycles using a 2D-CNN and a Transformer. A feature-wise linear modulation module uses the short-term representation to condition the long-term representation for joint prediction. Training comprises supervised autoencoder pretraining, independent expert pretraining, and fusion training with frozen experts. On two public battery-aging datasets, the reference configuration achieves mean RUL root-mean-square errors of 143.69 and 161.10 cycles and capacity errors of 12.36 and 7.28mAh, respectively. On Dataset I, fusion reduces both mean errors relative to either standalone expert. The results demonstrate a trade-off between RUL and capacity accuracy: the proposed method attains the lowest reported RUL RMSE among the compared methods on both datasets, whereas several baselines yield lower capacity errors.
Machine Learning (cs.LG)
arXiv:2609.21932 [cs.LG]
(or arXiv:2609.21932v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.21932 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 286 words
Related coverage
News Archive 2026
Quantum Computing Report · Jul 25, 2026
Early Cycle Charge Trajectory Generative Prediction and Full Life Cycle Health Management of Iron-Chromium Flow Batteries Based on FlowBD-E1
arXiv · Aug 19, 2026
Dynamic Loss Balancing for Joint SOH and RUL Prediction of Lithium-Ion Batteries via a Rotary SOH-Injected Prior Battery Transformer
arXiv · Jul 23, 2026
The current bottleneck is political will, not research
AI Alignment Forum · Jul 11, 2026