Modelling Compressive Strength of Concrete Containing Crushed Glass and Natural Gravel Using Artificial Neural Network

Abstract

ABSTRAC'T

This research modelled the 28-day compressive strength of concrete contaimng crushed gins, and Bida Natural Gravel (B G) based on deep learning algorithm using the "1ATLAB neural network toolbox. A total of240 (150mm · 150mm x 150mm) cubes were cast from 80 mixes generated randomly using Scheffe's simple" lattice approach. The compressive strength "as the mcao 28-day strength of three cubes for each of the experimental points. The resulting batch for each mix was used as input data while the laboratory results for compressive strength was the output data for the ANN-model. Tbc developed model will be able to predict the 28-day compressive strength of concrete containing 0% • 25°0 crushed glass as partial replacement for fine aggregate, water• cement ratio ranging from 0.45 0.65 and concrete grade M 15 M25. Fhe architecture of the network contained 6 mput parameters: water to cement rauo, water. cement. sund, crushed glass and BNG. 20 neurons in the hidden layer and compressive strength in the outer layer. The performance of the developed model was examined using Mean Square Error (MSE) and Correlation Coefficient (R). Results showed that 6:20: 1 model architecture for compressive strength bad an MSE values for training, validation and testing are: 0.15, 4.14. 1.15. 0.86 respectively. Regression values for training, validation and testing arc: 80%, 65%. 85°'0 and 75%. The study concluded that a shallow Neural Network architecture with 20 neurons in the hidden layer is sufficient for predicting the 2R-day compressive strength of concrete.