loading page

A Self-Adaptive Physics-Informed Gated Recurrent Unit Neural Networks Model for Estimating the Lifetime of Li-ion Batteries
  • +3
  • Mohammad AlShaikh Saleh,
  • Alamera Nouran Alquennah,
  • Ali Ghrayeb,
  • Shady S. Refaat,
  • Haitham Abu-Rub,
  • Sunil P. Khatri
Mohammad AlShaikh Saleh

Corresponding Author:[email protected]

Author Profile
Alamera Nouran Alquennah
Ali Ghrayeb
Shady S. Refaat
Haitham Abu-Rub
Sunil P. Khatri


Physics-Informed Neural Networks (PINNs) have recently emerged as a promising approach for applying deep neural networks to solve partial differential equations (PDEs). However, accurately addressing challenging regions in the solutions of stiff PDEs necessitates adaptive methods. Additionally, the inherent limitations of baseline PINN in handling sequential or time-series data significantly constrain their applicability. In light of this, this paper introduces a Self-Adaptive Physics-Informed Attention-based Gated Recurrent Unit (SA-PI-AGRU) model, which enhances the baseline PINN framework to address these critical issues. The proposed SA-PI-AGRU model advances PINNs by integrating an attention-based GRU layer, which is particularly effective at analyzing sequential data. This dual objective of minimizing losses while optimizing the weighting parameters ensures a robust training and testing process, which can be used for many applications, including language modelling and text generation, prognostics and health management, and other prediction/forecasting problems. The efficacy of the SA-PI-AGRU model is demonstrated through an essential case study, which is to predict the state of health (SoH) of lithium-ion batteries (LIBs), utilizing four different battery datasets from the National Aeronautics and Space Administration (NASA). The obtained results suggest significant improvements in predictive accuracy and network initialization capabilities compared to the baseline PINN and other benchmark models.
06 Jun 2024Submitted to TechRxiv
07 Jun 2024Published in TechRxiv