Summary of Multi-fidelity Surrogate with Heterogeneous Input Spaces For Modeling Melt Pools in Laser-directed Energy Deposition, by Nandana Menon and Amrita Basak
Multi-fidelity surrogate with heterogeneous input spaces for modeling melt pools in laser-directed energy deposition
by Nandana Menon, Amrita Basak
First submitted to arxiv on: 19 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Numerical Analysis (math.NA)
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 approach to constructing a multi-fidelity (MF) surrogate for predicting melt pool geometry in laser-directed energy deposition (L-DED). The proposed Het-MFGP (heterogeneous multi-fidelity Gaussian process) combines models of varying complexity, operating on heterogeneous input spaces. This is achieved by mapping the high-dimensional space into a pseudo two-dimensional space and blending predictions using a Gaussian process-based co-kriging method. The resulting surrogate improves predictive accuracy while reducing computational requirements. The framework demonstrates the benefits of leveraging multimodal data and handling scenarios where certain input parameters are difficult to model or measure. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper develops a new way to predict melt pool shapes in laser-directed energy deposition (L-DED). It combines different models that work with varying amounts of information to make more accurate predictions. The approach, called Het-MFGP, is useful because it can handle situations where some important details are hard to measure or model. This leads to better and faster results for predicting melt pool geometry. |
