Physics-Informed Neural Network for Concrete Manufacturing Process Optimization

TL;DR

This paper demonstrates how Physics-Informed Neural Networks (PINNs) can effectively optimize concrete manufacturing by accurately predicting strength and reducing data requirements, outperforming traditional models.

Contribution

The study introduces the application of PINNs for concrete strength prediction and cost optimization, showing improved performance with less data compared to traditional models.

Findings

PINNs reduced loss by 26.3% with 40% less data

PINNs outperformed traditional models in accuracy

Heuristic optimization with PSO effectively predicts raw material quantities

Abstract

Concrete manufacturing projects are one of the most common ones for consulting agencies. Because of the highly non-linear dependency of input materials like ash, water, cement, superplastic, etc; with the resultant strength of concrete, it gets difficult for machine learning models to successfully capture this relation and perform cost optimizations. This paper highlights how PINNs (Physics Informed Neural Networks) can be useful in the given situation. This state-of-the-art model shall also get compared with traditional models like Linear Regression, Random Forest, Gradient Boosting, and Deep Neural Network. Results of the research highlights how well PINNs performed even with reduced dataset, thus resolving one of the biggest issues of limited data availability for ML models. On an average, PINN got the loss value reduced by 26.3% even with 40% lesser data compared to the Deep Neural Network. In addition to predicting strength of the concrete given the quantity of raw materials, the paper also highlights the use of heuristic optimization method like Particle Swarm Optimization (PSO) in predicting quantity of raw materials required to manufacture concrete of given strength with least cost.