Leveraging Embedding Vectors of Aggregate Images for Particle Size Distribution Estimation and Concrete Compressive Strength Prediction

Samuel Fringeli, Houda Chabbi Drissi, Killian Ruffieux, Julien Ston, Daia Zwicky

2025

Abstract

Accurate prediction of concrete properties, such as compressive strength, is essential for ensuring structural performance. Particle size distribution (PSD) and nature of aggregates are key components of concrete mixtures, significantly influencing their final compressive strength. This paper presents a novel approach that leverages embedding vectors extracted from images of aggregates using the DinoV2 model to efficiently predict compressive strength. DinoV2 is a state-of-the-art vision transformer that excels at generating high-quality embeddings for various visual tasks. In this study, the effectiveness of these embeddings is evaluated by using them to classify and estimate the PSD of aggregates on public datasets. Small neural models trained on these vectors achieved comparable accuracy to the best found fine-tuned ViT-16 model, demonstrating the potential of using embedding vectors for accurate PSD prediction. Building on these results, a new approach for predicting concrete compressive strength by combining embedding vectors with data on concrete mix components is explored. A small dataset of concrete mixtures was created. To mitigate the challenges of limited data, augmentation techniques were proposed to generate additional, realistic mix designs. An ablation study was performed, indicating promising results and highlighting the potential of this new approach for predicting other concrete properties.

Paper Citation

in Harvard Style

Fringeli S., Drissi H., Ruffieux K., Ston J. and Zwicky D. (2025). Leveraging Embedding Vectors of Aggregate Images for Particle Size Distribution Estimation and Concrete Compressive Strength Prediction. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 112-123. DOI: 10.5220/0013111800003890

in Bibtex Style

@conference{icaart25,
author={Samuel Fringeli and Houda Drissi and Killian Ruffieux and Julien Ston and Daia Zwicky},
title={Leveraging Embedding Vectors of Aggregate Images for Particle Size Distribution Estimation and Concrete Compressive Strength Prediction},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2025},
pages={112-123},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013111800003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - Leveraging Embedding Vectors of Aggregate Images for Particle Size Distribution Estimation and Concrete Compressive Strength Prediction
SN - 978-989-758-737-5
AU - Fringeli S.
AU - Drissi H.
AU - Ruffieux K.
AU - Ston J.
AU - Zwicky D.
PY - 2025
SP - 112
EP - 123
DO - 10.5220/0013111800003890
PB - SciTePress