Advances in Reliable Computing and Energy Storage

The field of reliable computing and energy storage is moving towards innovative solutions to address the challenges of aging and degradation in integrated circuits and battery systems. Recent developments focus on designing more reliable and efficient systems, with a emphasis on domain adaptation, physics-informed neural networks, and integrated sensing frameworks. Notably, researchers are exploring new approaches to predict remaining useful life, estimate electrochemical parameters, and improve state-of-charge estimation accuracy. These advancements have the potential to enhance safety, extend lifespans, and facilitate fast charging in various applications. Noteworthy papers include: HybridoNet-Adapt, which introduces a domain-adapted framework for accurate lithium-ion battery RUL prediction. On-site estimation of battery electrochemical parameters via transfer learning based physics-informed neural network approach, which presents a novel framework for on-site model characterization. Smart Sensing Breaks the Accuracy Barrier in Battery State Monitoring, which introduces an integrated sensor framework to improve SOC estimation accuracy. DeepOFormer, which proposes a deep operator learning approach for fatigue life prediction with domain-informed features.

Sources

Extending Silicon Lifetime: A Review of Design Techniques for Reliable Integrated Circuits

HybridoNet-Adapt: A Domain-Adapted Framework for Accurate Lithium-Ion Battery RUL Prediction

On-site estimation of battery electrochemical parameters via transfer learning based physics-informed neural network approach

Smart Sensing Breaks the Accuracy Barrier in Battery State Monitoring

DeepOFormer: Deep Operator Learning with Domain-informed Features for Fatigue Life Prediction

Built with on top of