Compressive strength modelling of cenosphere and copper slag-based geopolymer concrete using deep learning model

Area of Science:

• Materials Science
• Civil Engineering
• Artificial Intelligence

Background:

• Geopolymer concrete (GPC) offers a sustainable alternative to conventional concrete by utilizing industrial by-products.
• Reducing the environmental impact of construction materials is crucial for global sustainability efforts.
• Cenosphere and copper slag are industrial by-products with potential for use in GPC formulations.

Purpose of the Study:

• To predict the 28-day compressive strength of cenosphere-based geopolymer concrete incorporating copper slag.
• To evaluate the efficacy of Artificial Neural Networks (ANN) in forecasting GPC properties.
• To advance sustainable construction practices through accurate material performance prediction.

Main Methods:

• Development and application of Artificial Neural Networks (ANN) models.
• Experimental determination of compressive strength for geopolymer concrete with varying cenosphere and copper slag content.
• Validation of ANN model predictions against experimental results.

Main Results:

• The developed ANN model achieved high accuracy (over 98.6%) in predicting the compressive strength.
• The model demonstrated significant capability and flexibility in forecasting the strength of the modified GPC.
• Successful assimilation of ANN for performance prediction of eco-friendly concrete.

Conclusions:

• Artificial Neural Networks provide a reliable and accurate method for predicting the compressive strength of cenosphere-based geopolymer concrete with copper slag.
• Accurate strength prediction facilitates rational design processes, promoting the use of sustainable construction materials.
• This approach supports the development of eco-friendly construction alternatives with reduced environmental impact.