Summary of Real-time 2d Temperature Field Prediction in Metal Additive Manufacturing Using Physics-informed Neural Networks, by Pouyan Sajadi et al.
Real-Time 2D Temperature Field Prediction in Metal Additive Manufacturing Using Physics-Informed Neural Networks
by Pouyan Sajadi, Mostafa Rahmani Dehaghani, Yifan Tang, G. Gary Wang
First submitted to arxiv on: 4 Jan 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 introduces a novel machine learning framework, called physics-informed neural network (PINN), specifically designed for temperature field prediction in metal additive manufacturing (AM) processes. The PINN framework combines the strengths of both physics-based computational models and machine learning models to accurately predict temperature fields in real-time. The model uses a Convolutional Long Short-Term Memory (ConvLSTM) architecture, incorporates a physics-informed input, and features a physics-informed loss function. This approach enables the prediction of 2D temperature fields for future timestamps across diverse geometries, deposition patterns, and process parameters with high accuracy. The framework is validated in two scenarios: full-field temperature prediction for a thin wall and 2D temperature field prediction for cylinder and cubic parts. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper proposes a new way to predict temperatures during metal additive manufacturing (AM) processes. It uses a special kind of artificial intelligence called a physics-informed neural network (PINN). The PINN can learn from real-time temperature data and make predictions about future temperatures in different scenarios. This is important because it helps ensure that the AM process runs smoothly and efficiently. The paper shows that the PINN works well by testing it on several examples, including predicting temperatures for thin walls and cubes. |
Keywords
* Artificial intelligence * Loss function * Machine learning * Neural network * Temperature
