Development of Prediction Model to Predict the Compressive Strength of Eco-Friendly Concrete Using Multivariate...

Area of Science:

• Civil Engineering
• Materials Science
• Environmental Science

Background:

• Concrete production is a major source of global pollution, impacting sustainability through resource depletion, energy consumption, and greenhouse gas emissions.
• Reducing the environmental footprint of concrete is crucial for long-term viability in the construction industry.
• Developing eco-friendly concrete alternatives is essential to mitigate negative environmental impacts.

Purpose of the Study:

• To create a predictive model for the compressive strength of environmentally friendly concrete mixtures.
• To investigate the use of recycled aggregate concrete (RAC) and ground granulated blast-furnace slag (GGBFS) in sustainable concrete formulations.
• To evaluate the performance of a novel white-box machine learning model for predicting concrete compressive strength.

Main Methods:

• Development of a multivariate polynomial regression (MPR) model, a white-box machine learning approach.
• Utilization of concrete mixtures incorporating recycled aggregate concrete (RAC) and ground granulated blast-furnace slag (GGBFS).
• Comparative analysis of the proposed MPR model against linear regression (LR) and support vector machine (SVM) models.

Main Results:

• The multivariate polynomial regression (MPR) model demonstrated robust estimation capabilities for compressive strength.
• The MPR model outperformed both linear regression (LR) and support vector machine (SVM) models.
• Superior performance was indicated by higher R-squared (coefficient of determination) and lower RMSE (root mean absolute error) values.

Conclusions:

• The developed MPR model effectively predicts the compressive strength of eco-friendly concrete.
• This predictive capability supports the design of sustainable concrete mixtures incorporating RAC and GGBFS.
• The findings contribute to advancing environmentally conscious practices in the construction sector.