Summary of Physics-informed Neural Network For Concrete Manufacturing Process Optimization, by Sam Varghese et al.
Physics-Informed Neural Network for Concrete Manufacturing Process Optimization
by Sam Varghese, Rahul Anand, Gaurav Paliwal
First submitted to arxiv on: 24 Aug 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 In this paper, researchers explore the application of Physics Informed Neural Networks (PINNs) in optimizing concrete manufacturing processes. The authors demonstrate how PINNs can outperform traditional machine learning models like Linear Regression, Random Forest, Gradient Boosting, and Deep Neural Network in predicting the strength of concrete given input materials and cost optimizations. Notably, PINNs exhibit improved performance even with reduced dataset sizes, reducing loss values by 26.3% compared to Deep Neural Networks when using 40% less data. The study also investigates the use of heuristic optimization methods like Particle Swarm Optimization (PSO) in predicting raw material requirements for concrete manufacturing with minimal cost. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Concrete manufacturing projects are a common task for consulting agencies, but it’s challenging for machine learning models to capture the complex relationships between input materials and resulting strength. This paper shows how Physics Informed Neural Networks (PINNs) can help optimize concrete production. PINNs outperform other machine learning models in predicting concrete strength and cost optimizations, even with limited data. The study also explores using Particle Swarm Optimization (PSO) to find the best combination of raw materials for making concrete at a low cost. |
Keywords
» Artificial intelligence » Boosting » Linear regression » Machine learning » Neural network » Optimization » Random forest
