Summary of Physics-informed Neural Networks For Encoding Dynamics in Real Physical Systems, by Hamza Alsharif
Physics-informed Neural Networks for Encoding Dynamics in Real Physical Systems
by Hamza Alsharif
First submitted to arxiv on: 7 Jan 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 This dissertation investigates physics-informed neural networks (PINNs) as candidate models for encoding governing equations, and assesses their performance on experimental data from two different systems. The study demonstrates that PINNs outperform equivalent uninformed neural networks (NNs) in reconstructing the solution of a simple nonlinear pendulum system and 2D heat diffusion across a metal block surface. For the pendulum system, accuracy improvements were observed with PINNs achieving 18x and 6x better results compared to NNs for linearly-spaced and uniformly-distributed random training points, respectively. Similarly, in test cases using real data collected from an experiment, PINNs showed improved accuracy of 9.3x and 9.1x over NNs for linearly-spaced and uniformly-distributed random points, respectively. The study also highlights the limitations of both PINNs and NNs in reconstructing the heating regime due to difficulties in optimizing network parameters over a large domain in both time and space. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research looks at special kinds of artificial intelligence called physics-informed neural networks (PINNs). These models try to understand how physical systems work, like a swinging pendulum or heat moving across a metal block. The study shows that PINNs are really good at figuring out what’s happening in these systems and making predictions. For example, they did much better than other types of AI models at understanding the motion of a simple pendulum and the way heat spreads on a metal block. This is important because it could help us use AI to control or predict things like temperature changes or mechanical movements. |
Keywords
* Artificial intelligence * Diffusion * Temperature
