Prediction of Concrete Compressive Strength using Machine Learning and Deep Learning Algorithms

Abstract

This document presents a comprehensive analysis project focused on predicting the compressive strength of concrete. The study utilizes a dataset comprising various concrete mix constituents and curing conditions. The objective is to employ four distinct machine learning algorithms: Support Vector Machine (SVM), Decision Tree (DT), Linear Regression, Random Forest (RF), and neural networks, to forecast concrete strength accurately. This predictive modeling is of significant importance in the fields of civil engineering and construction materials science, where precise estimation of concrete strength is crucial for ensuring structural integrity and longevity of infrastructure. By reliably predicting concrete strength, engineers and construction professionals can optimize design parameters, enhance material selection processes, and ultimately bolster the resilience and durability of buildings, bridges, roads, and other vital structures. The inclusion of neural networks expands the scope of the analysis, leveraging their ability to capture complex patterns and relationships within the data, thereby potentially improving the accuracy of concrete strength predictions.