ABOUT THE INTERNATIONAL CONCRETE ABSTRACTS PORTAL

  • The International Concrete Abstracts Portal is an ACI led collaboration with leading technical organizations from within the international concrete industry and offers the most comprehensive collection of published concrete abstracts.

International Concrete Abstracts Portal

  


Title: Predicting the Compressive Strength Based in NDT Using Deep Learning

Author(s): José A. Guzmán-Torres, Francisco J. Domínguez-Mota, Gerardo Tinoco-Guerrero, Elia M. Alonso-Guzmán, and Wilfrido Martínez-Molina

Publication: Symposium Paper

Volume: 350

Issue:

Appears on pages(s): 90-102

Keywords: concrete; compressive strength; deep learning; data science

DOI: 10.14359/51734315

Date: 11/1/2021

Abstract:
Artificial Intelligence has one of the most efficient methods for solving engineering and materials problems because of its impressive performance and can reach higher accuracy. The Deep Learning theory is an approach based on Deep Neural Networks for establishing numerical analysis and value predictions. This paper proposes a fresh approach, using a Deep Learning model for predicting the compressive strength in a particular concrete just based on non-destructive test measurements (NDTs). The model proposed is an attractive alternative to estimate the resistance of compressive strength in any structure, just taking data like ultrasonic pulse velocity, electrical resistivity, and resonance frequencies. The present work employs data science techniques to find the correlation values between the NDTs and the compressive strength effort and realized broad numerical exploration about concrete performance. An amount of 285 specimens of concrete were monitored during this research. The model proposed contains 600 neurons and uses a Rectified Linear Unit and Sigmoid as activation functions where the NDTs were established as the input data. The dataset was segmented into two groups: train and test. In order to evaluate the model, the authors tested it in a validation set with different concrete features, achieving an accuracy of 94%.