Predicting the Compressive Strength of Concrete Specimen using Artificial Intelligence

Abstract

Concrete is a widely used construction material, and accurately predicting its compressive strength is essential to ensure structural integrity and safety of the structure. The compressive strength of concrete is an important property that decides its load-bearing capacity. The compressive strength of concrete can be determined by conducting a compressive strength test using a universal testing machine. However, this test is time-consuming and expensive. Further, it requires at least seven days of curing to get the idea about compressive strength of concrete. Machine learning can be used to predict the compressive strength of concrete. Machine learning is a subset of artificial intelligence that can be used to learn and derive patterns from data and finally make predictions. This project focuses on developing multiple machine learning models to predict the compressive strength of concrete cube specimen and compare their performance based on various metrics. This study uses 1030 data tests from concrete compressive quality tests obtained from University of California, Irvine, to illustrate the utilize of AI forecast models. The obtained results of the recreation appear that these artificial intelligence methods can build predictive models with great precision.