Summary of Ev-pinn: a Physics-informed Neural Network For Predicting Electric Vehicle Dynamics, by Hansol Lim et al.
EV-PINN: A Physics-Informed Neural Network for Predicting Electric Vehicle Dynamics
by Hansol Lim, Jee Won Lee, Jonathan Boyack, Jongseong Brad Choi
First submitted to arxiv on: 22 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 A novel approach to predicting dynamic parameters for electric vehicles (EVs) is introduced, enabling accurate path planning. The Physics-Informed Neural Network (PINN) method, EV-PINN, learns real-world parameters such as motor efficiency and aerodynamic drag using automatic differentiation and ground truth vehicle data. The model is validated using in-situ battery log data from Tesla Model 3 Long Range and Model S, achieving high accuracy and generalization to dynamics. This demonstrates the effectiveness of EV-PINN in estimating parameters and predicting battery usage under actual driving conditions without additional sensors. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Electric vehicles (EVs) need accurate path planning for efficient navigation. Scientists have developed a new way to predict important parameters like aerodynamic drag and rolling resistance using neural networks called Physics-Informed Neural Networks, or PINNs. This helps EVs plan their routes better. The team used data from Tesla cars to test the method, which worked well. This means that EVs can now predict how much energy they’ll use on a trip without needing extra sensors. |
Keywords
» Artificial intelligence » Generalization » Neural network
