FlowBatt predicts battery health trajectories with low error
FlowBatt: Flow Matching for Probabilistic Battery Degradation Prediction
Machine Learning
Summary
Batteries get worse over time, but it's hard to predict exactly how and when. The authors created FlowBatt, a new AI method that learns from early battery data to forecast how battery health will change with uncertainty. It works well across many battery types and conditions, giving not just one prediction but a range of possible futures. This helps people better understand and plan for battery life in devices and energy systems.
What this means in practice
- •For battery engineers: Generate probabilistic battery degradation trajectories early in a battery’s life to improve design and testing decisions.
- •For energy storage operators: Use multiple predicted battery health paths with uncertainty estimates to better schedule maintenance and replacement for energy storage systems.
Authors
Hamidreza Eivazi, Eslam Sharaawy, Stefan Wittek, André Hebenbrock, Raphael Ginster, Steffen Blömeke
Abstract
Battery degradation remains a central challenge in the development and broad application of sustainable energy technologies. Accurate degradation prediction is challenging, as battery aging emerges from complex and heterogeneous interactions among cycling behavior, operating conditions, and cell chemistry. Existing machine-learning approaches typically focus on deterministic end-of-life predictions or modeling degradation curves within fixed chemistry settings, leaving probabilistic state of health (SOH) trajectory modeling across heterogeneous chemistries underexplored. We introduce FlowBatt, a use-inspired conditional generative framework that adapts flow matching with a diffusion transformer (DiT) backbone to battery degradation trajectory modeling. FlowBatt models full SOH trajectories as probabilistic degradation processes conditioned on early-cycle capacity data. To strengthen this conditioning pathway, we use explainable AI analysis to diagnose and improve the encoder that maps early-cycle capacity matrices into conditioning vectors. We evaluate FlowBatt on five public benchmark settings spanning diverse chemistries and aging conditions, comparing it with supervised and diffusion-based trajectory models as well as established baselines for remaining useful life (RUL) prediction under shared data splits. FlowBatt achieves the best trajectory-wise SOH prediction performance on all five datasets, with errors below 2.5%, and delivers competitive RUL prediction performance. By generating multiple plausible trajectories, FlowBatt provides empirical prediction intervals for battery degradation modeling. These results indicate that flow-matching-based trajectory modeling is a promising framework for probabilistic battery health prediction.