Authors: Hao Tu, Manashita Borah, Scott Moura, Yebin Wang, Huazhen Fang
Published on: April 23, 2024
Impact Score: 8.2
Arxiv code: Arxiv:2404.14767
Summary
- What is new: First study on predicting the remaining energy of a battery cell across wide current ranges using a novel definition and a machine learning approach.
- Why this is important: The challenge of accurately predicting remaining discharge energy in lithium-ion batteries over various C-rates due to complex electro-thermal dynamics.
- What the research proposes: A two-part solution integrating a dynamic physics-based model with machine learning to predict remaining discharge energy with high accuracy.
- Results: The proposed approach achieves high prediction accuracy and is amenable to training and computation.
Technical Details
Technological frameworks used: Integration of physics-based modeling with machine learning
Models used: Dynamic models combined with machine learning algorithms
Data used: Battery voltage and temperature data across various C-rates
Potential Impact
Energy sector, electric vehicle manufacturers, renewable energy storage systems, and companies involved in battery technology and sustainability initiatives
Want to implement this idea in a business?
We have generated a startup concept here: EnerPredict.
Leave a Reply