Summary of Coupling Neural Networks and Physics Equations For Li-ion Battery State-of-charge Prediction, by Giovanni Pollo et al.
Coupling Neural Networks and Physics Equations For Li-Ion Battery State-of-Charge Prediction
by Giovanni Pollo, Alessio Burrello, Enrico Macii, Massimo Poncino, Sara Vinco, Daniele Jahier Pagliari
First submitted to arxiv on: 21 Dec 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed novel neural network (NN) architecture combines physics-based and data-driven approaches to estimate the evolution of battery State of Charge (SoC). The NN consists of two cascaded branches: one predicts current SoC based on sensor readings, while the other estimates future SoC as a function of load behavior. By integrating battery dynamics equations into the training process, the Physics-Informed Neural Networks (PINNs) demonstrate improved generalization over variable prediction horizons. Compared to purely data-driven models and state-of-the-art methods, the PINNs achieve better prediction accuracy with a smaller architecture. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way to predict how a car battery’s power changes is developed in this research. It combines two approaches: one uses sensors to measure the current battery power, and another uses computer simulations to forecast future power levels based on how the car will be used. By combining these methods, the researchers created a new type of neural network that is more accurate at predicting battery power than previous models. This can help make electric cars better by improving their batteries’ performance. |
Keywords
» Artificial intelligence » Generalization » Neural network
