The application of data science and machine learning techniques in predicting the compressive strength of confined concrete - Research report - prediction of compressive strength using ML

Aug 6, 2026

Upload by Ivy

Machine learning (ML) techniques are integrated into materials and industrial decision-making to model complex non-linear relationships governing material performance. A large experimental dataset of fiber reinforced polymer (FRP) confined concrete specimens is used, where measured responses are correlated with mechanical and structural properties. After normalization, multiple ML algorithms are trained on experimental values and evaluated for predictive ability across and beyond the input range. Results indicate ML as an effective computational complement to costly experiments and time-consuming simulations in engineering sciences.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

1 General

Data-driven methods and ML categories

2 Data Handling

Database

Input parameters and confined specimens

Technical Annals Vol 1, No 5 (2024) Technical Annals | | The application of data science and machine learning techniques in predicting the compressive strength of confined concrete
Christos Papakonstantinou, Maria Valasaki, Filippos Sofos, Theodoros Karakasidis
doi: 10. 12681/ta.37190
Copyright © 2024, Christos Papakonstantinou, Maria Valasaki, Filippos Sofos, Theodoros Karakasidis

This work is licensed under a Creative Commons Attribution-NonCommercialShareAlike 4.0. | | --- | --- | | To cite this article:
Papakonstantinou, C. , Valasaki, M. , Sofos, F. , & Karakasidis, T. (2024) . The application of data science and machine learning techniques in predicting the compressive strength of confined concrete. Technical Annals, 1(5) . [https://doi.org/10.12681/ta.37190](https://doi.org/10.12681/ta.37190) | | | | | [https://epublishing.ekt.gr](https://epublishing.ekt.gr | e-Publisher: EKT | Downloaded at: 20/02/2025 10:20:26)[ |](https://epublishing.ekt.gr | e-Publisher: EKT | Downloaded at: 20/02/2025 10:20:26)[ e-Publisher:](https://epublishing.ekt.gr | e-Publisher: EKT | Downloaded at: 20/02/2025 10:20:26)[ EKT |](https://epublishing.ekt.gr | e-Publisher: EKT | Downloaded at: 20/02/2025 10:20:26)[ Downloaded at:](https://epublishing.ekt.gr | e-Publisher: EKT | Downloaded at: 20/02/2025 10:20:26)[ 20/02/2025 10:20:26](https://epublishing.ekt.gr | e-Publisher: EKT | Downloaded at: 20/02/2025 10:20:26) The application of data science and machine learning techniques in predicting the compressive strength of confined concrete C. G. Papakonstantinou 1[0000-1111-2222-3333], M. Valasaki 1[0000-0002-2597-8027] F. Sofos2[0000-0001-5036-2120], T. Karakasidis2[0000-0001-9580-0702] 1Department of Civil Engineering, University of Thessaly, Volos, Greece 2Department of Physics, University of Thessaly, Volos, Greece [cpapak@uth.gr](cpapak@uth.gr) Abstract. The integration of machine learning (ML) techniques into industrial and manufacturing applications has seen great growth in recent years. Various numerical and analytical models have been proposed, based either on experimental results or simulation results, and have helped to understand phenomena that take place during the life cycle of a material. In this direction, a large experimental data set to determine the compressive strength of fiber reinforced polymer (FRP) confined concrete specimens has been used as a basis in this work. The obtained measurements are correlated with the mechanical and structural properties of the material and fed into a ML model. The model is trained on the experimental values and can provide predictions for conditions within or outside the value range of the input data. Various ML algorithms are implemented and studied for their prediction accuracy, and the results show that ML can be an important computational tool, which can act as a complement to expensive experiments or time-consuming simulations in engineering sciences. Keywords: Machine Learning, Data Science, Confined Concrete, Compressive Strength, FRP. 1 General Property extraction in materials science has seen a significant shift in the last decade towards the adoption of techniques based on data science. The large amount of experimental data generated and stored in various databases has enabled scientists and engineers to incorporate this information into innovative statistical techniques and methods. This integration aims to propose new methodologies and materials with enhanced properties, which is especially crucial for technological and scientific advancement. The majority of data-driven methods are based on concepts from artificial intelligence (AI) and machine learning (ML) . The term ML refers to the implementation of a computational model of complex non-linear data-driven relationships and AI is the framework for decision-making and actions based on ML [1] . ML uses statistical approaches to analyze data with the help of appropriate algorithm

FAQs

What dataset is used to model confined concrete compressive strength?

An experimental dataset of fiber reinforced polymer (FRP) confined concrete specimens is used, including specimens confined with carbon, glass, and aramid materials across a range of concrete strengths.

How do the authors build the ML workflow for prediction?

The workflow normalizes experimental data, trains ML algorithms using experimental values, and applies linear and non-linear approximations to map input parameters to compressive strength outputs.

What do the results suggest about ML in engineering applications?

The study finds that ML can serve as an important computational tool, complementing expensive experiments and time-consuming simulations for predicting engineering material behavior.

Aug 6, 2026

Upload by Ivy