Summary of Physics-informed Machine Learning For Battery Pack Thermal Management, by Zheng Liu et al.
Physics-informed Machine Learning for Battery Pack Thermal Management
by Zheng Liu, Yuan Jiang, Yumeng Li, Pingfeng Wang
First submitted to arxiv on: 15 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 The paper presents a novel approach to constructing surrogate models for estimating battery pack temperature distribution using physics-informed machine learning. With the increasing demand for lithium-ion batteries, temperature control is crucial for performance and safety. Existing methods rely on extensive training datasets and finite element analysis, which are time-consuming and costly. The proposed physics-informed convolutional neural network (CNN) model enforces physical laws, making it suitable for this task. The authors developed a 21700 battery pack indirect liquid cooling system and built a simplified finite element model based on experiment results. They constructed a loss function considering the heat conduction equation using the finite difference method. The physics-informed loss function improved training convergence with less data. Compared to the data-driven method, the proposed CNN showed over 15% improvement in accuracy. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about developing a new way to predict how hot or cold electric car batteries will get based on their design and temperature control system. Right now, making these predictions takes a lot of time and money. The researchers came up with a new approach that uses physical laws to help the prediction process. They built a special cooling system for batteries and used it to test their idea. Their method was better than the old way at predicting battery temperatures and can be used to make electric cars safer and more efficient. |
Keywords
» Artificial intelligence » Cnn » Loss function » Machine learning » Neural network » Temperature
