Remaining Useful Life Prediction of Lithium-ion Battery Based on Cycle-consistency Learning

Abstract

The prediction of the Remaining Useful Life (RUL) of lithium-ion batteries plays an important role in battery health management. The existing methods have some limitations in battery RUL prediction, including the problem of error accumulation, and the inapplicability of RUL model under different working conditions. For one battery, the existing prediction methods have the problem of error accumulation; for batteries under different working conditions, the corresponding life distribution is discrete, so the model cannot be generalized. To address the above problems, a RUL prediction method based on cycle-consistency learning is studied. Firstly, the original degradation data is mapped to the representation subspace, in which the data at the same degradation level are aligned with each other. On this basis, a new RUL prediction theory is established. Finally, the MIT-Stanford lithium-ion battery data is used to verify the effectiveness of the proposed method.