ACCEPT: Diagnostic Forecasting of Battery Degradation Through Contrastive Learning

TL;DR

ACCEPT addresses the mismatch between data-driven battery degradation forecasting and physics-based understanding by fusing a physics-informed degradation simulator with contrastive-learning-based embeddings. Two encoders project simulated curves and operational data into a shared latent space, enabling zero-shot degradation forecasting and cross-chemistry generalization. The model achieves state-of-the-art accuracy with minimal historical data, quantifies degradation modes via the underlying simulation parameters, and provides uncertainty estimates by sampling multiple degradation scenarios. This approach promises faster, more interpretable degradation predictions applicable across LIB chemistries and operating conditions, with potential impact on EV and BESS reliability and safety.

Abstract

Modeling lithium-ion battery (LIB) degradation offers significant cost savings and enhances the safety and reliability of electric vehicles (EVs) and battery energy storage systems (BESS). Whilst data-driven methods have received great attention for forecasting degradation, they often demonstrate limited generalization ability and tend to underperform particularly in critical scenarios involving accelerated degradation, which are crucial to predict accurately. These methods also fail to elucidate the underlying causes of degradation. Alternatively, physical models provide a deeper understanding, but their complex parameters and inherent uncertainties limit their applicability in real-world settings. To this end, we propose a new model - ACCEPT. Our novel framework uses contrastive learning to map the relationship between the underlying physical degradation parameters and observable operational quantities, combining the benefits of both approaches. Furthermore, due to the similarity of degradation paths between LIBs with the same chemistry, this model transfers non-trivially to most downstream tasks, allowing for zero-shot inference. Additionally, since categorical features can be included in the model, it can generalize to other LIB chemistries. This work establishes a foundational battery degradation model, providing reliable forecasts across a range of battery types and operating conditions.

Figures (8)

• Figure 1: Summary of approach. Whilst standard data-driven techniques directly train a time-series model to predict the time-series, this model trains an operational data (current, temperature, voltage, static meta data inc. LIB chemistry and initial capacity) encoder and a simulated curve encoder. Curves are matched to their operational data to enable a zero-shot degradation prediction.
• Figure 2: Example of an operational degradation curve with the corresponding matched simulated curve.
• Figure 3: On the left of the image, a degradation curve from the same battery at different points in its lifecycle is shown. In the training process, each of these curves would form a positive and negative pair with the simulated curves on the upper right and lower right, respectively.
• Figure 4: Future capacity degradation curves as predicted by the model against test LIBs no. 1-4 from 100 cycles of input data. The model has the added benefit against current techniques that it is not limited to a certain output (context) length.
• Figure 5: Quantitative results of degradation modes for capacity loss of Test LIB 1.