Summary of Physics-informed Neural Networks with Skip Connections For Modeling and Control Of Gas-lifted Oil Wells, by Jonas Ekeland Kittelsen et al.
Physics-Informed Neural Networks with Skip Connections for Modeling and Control of Gas-Lifted Oil Wells
by Jonas Ekeland Kittelsen, Eric Aislan Antonelo, Eduardo Camponogara, Lars Struen Imsland
First submitted to arxiv on: 4 Mar 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 method for enhancing Physics-Informed Neural Networks (PINNs) to control complex systems like gas-lifted oil wells. The proposed improvement, called PINC, is designed to address limitations in traditional PINNs by introducing skip connections and refining terms in the Ordinary Differential Equation (ODE). This enhancement leads to more accurate gradients during training, resulting in better modeling of highly nonlinear systems. Specifically, the improved PINC reduces validation prediction error by 67% compared to the original PINC, while also increasing gradient flow through network layers by four orders of magnitude. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Physics-Informed Neural Networks (PINNs) are powerful tools for solving complex problems like oil well control. The new PINC framework extends this technology to long-range prediction and control of dynamic systems. This paper shows how to make PINC work better with highly nonlinear systems, like gas-lifted oil wells. By making some simple changes, the authors get more accurate predictions and better control. |
