Summary of Predicting Ship Responses in Different Seaways Using a Generalizable Force Correcting Machine Learning Method, by Kyle E. Marlantes et al.
Predicting Ship Responses in Different Seaways using a Generalizable Force Correcting Machine Learning Method
by Kyle E. Marlantes, Piotr J. Bandyk, Kevin J. Maki
First submitted to arxiv on: 13 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Fluid Dynamics (physics.flu-dyn); Machine Learning (stat.ML)
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 proposes a hybrid machine learning method that combines low-fidelity equation-of-motion corrections with high-fidelity numerical simulations to improve predictions of ship responses under various wave conditions. The method is tested on two case studies: a nonlinear Duffing equation and high-fidelity heave and pitch response data of a Fast Displacement Ship (FDS) in head seas. The authors investigate the generalizability of the hybrid model by making predictions in irregular wave conditions that differ from those used for training. Comparisons are made with two benchmarks: a linear physics-based model and a data-driven LSTM model. The results show that the hybrid method offers improved prediction accuracy and generalizability when trained on a small dataset. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about finding a better way to predict how ships will move in different ocean conditions using machine learning. Right now, people use computers to simulate these movements, but it takes a lot of computing power and data. The authors created a new method that combines simple physics equations with the computer simulations to make more accurate predictions. They tested this method on two different scenarios: one that’s like a math problem, and another that uses real data from a ship moving in waves. The results show that their new method is better at predicting how ships will move than some other methods. |
Keywords
» Artificial intelligence » Lstm » Machine learning
