LiFe-net: Data-driven Modelling of Time-dependent Temperatures and Charging Statistics Of Tesla's LiFePo4 EV Battery

TL;DR

This paper introduces LiFe-net, a data-driven neural model that accurately predicts EV battery temperature evolution using accessible diagnostics, outperforming traditional models in generalization and stability.

Contribution

The paper presents a novel neural operator-based surrogate model for EV battery temperature estimation, incorporating stability losses for improved accuracy and generalization.

Findings

LiFe-net with time stability loss achieves 2.77% average relative error.

The model outperforms baseline models in generalization to unseen data.

Incorporating stability loss enhances temperature prediction accuracy.

Abstract

Modelling the temperature of Electric Vehicle (EV) batteries is a fundamental task of EV manufacturing. Extreme temperatures in the battery packs can affect their longevity and power output. Although theoretical models exist for describing heat transfer in battery packs, they are computationally expensive to simulate. Furthermore, it is difficult to acquire data measurements from within the battery cell. In this work, we propose a data-driven surrogate model (LiFe-net) that uses readily accessible driving diagnostics for battery temperature estimation to overcome these limitations. This model incorporates Neural Operators with a traditional numerical integration scheme to estimate the temperature evolution. Moreover, we propose two further variations of the baseline model: LiFe-net trained with a regulariser and LiFe-net trained with time stability loss. We compared these models in terms of generalization error on test data. The results showed that LiFe-net trained with time stability loss outperforms the other two models and can estimate the temperature evolution on unseen data with a relative error of 2.77 % on average.