State of Health Estimation of Batteries Using a Time-Informed Dynamic Sequence-Inverted Transformer

Abstract

The rapid adoption of battery-powered vehicles and energy storage systems over the past decade has made battery health monitoring increasingly critical. Batteries play a central role in the efficiency and safety of these systems, yet they inevitably degrade over time due to repeated charge discharge cycles. This degradation leads to reduced energy efficiency and potential overheating, posing significant safety concerns. Accurate estimation of a battery’s State of Health (SoH) is therefore essential for ensuring operational reliability and safety. Several machine learning architectures, such as LSTMs, transformers, and encoder-based models, have been proposed to estimate SoH from discharge cycle data. However, these models struggle with the irregularities inherent in real world measurements: discharge readings are often recorded at non uniform intervals, and the lengths of discharge cycles vary significantly. To address this, most existing approaches extract features from the sequences rather than processing them in full, which introduces information loss and compromises accuracy. To overcome these challenges, we propose a novel architecture: Time Informed Dynamic Sequence Inverted Transformer (TIDSIT). TIDSIT incorporates continuous time embeddings to effectively represent irregularly sampled data and utilizes padded sequences with temporal attention mechanisms to manage variable-length inputs without discarding sequence information. Experimental results on the NASA battery degradation dataset demonstrate that TIDSIT significantly outperforms existing models, achieving over a 43% reduction in prediction error compared to the strongest baseline. The model attains an RMSE% = 0.58%, indicating highly accurate SoH estimation. Furthermore, the architecture exhibits strong cross-battery generalization and shows promise for broader health monitoring tasks involving irregular time series data.