Censored-Variational Gaussian Process for Predicting Probabilistic RUL of Li-ion Battery Using Right-censored Data

Accurate prediction of the remaining useful life (RUL) of batteries plays a crucial role in ensuring their reliable operation and optimizing maintenance strategies. In this paper, we propose a censored-variational Gaussian Process (C-VGP) model for probabilistic RUL prediction, taking into account right-censored data. The performance of the C-VGP model is compared with the typical Gaussian process regression (GPR) and GPR with right-censored data removed (GPR*). Numerical experiments on battery testing datasets demonstrate that neglecting right-censored data in the GPR model leads to larger errors, while the GPR* model sacrifices information. In contrast, our proposed C-VGP model outperforms both models in terms of accuracy and robustness. It achieves a high coefficient of determination
$R^{2}$
of 93.56% even with a significant proportion of censored data (57.67%) in the training set. Moreover, the proposed C-VGP model enables time-varying conditional survival analyses, providing valuable insights into the probabilities of the battery's remaining life exceeding certain thresholds at different time points. The proposed model offers a comprehensive solution for accurate battery RUL prediction, encompassing the handling of right-censored data, capturing time-varying patterns, and providing reliable predictions. Its practicality and effectiveness can make it a valuable tool for battery management and maintenance applications.