Investigating the rheological characteristics of alkali-activated concrete using contemporary artificial intelligence approaches

• DOI: 10.1515/rams-2024-0006
• Publication Date: 2024-04-12T13:10:57Z
• Authors: Muhammad Nasir Amin; Ahmed A. Alawi Al...; Roz-Ud-Din Nassar; Omar Algassem; Suleman Ayub Khan; Ahmed Farouk Deif...
• Keywords: Artificial neural network; Composite material; Technology; Artificial intelligence; High-performance Cement-based Materials; Self-Compacting Concrete; Naturwissenschaften; Fiber Reinforced Concrete in Civil Engineering; Compressive strength; TP1-1185; 02 engineering and technology; 0201 civil engineering; Engineering; Machine learning; Multilayer perceptron; Geopolymer and Alternative Cementitious Materials; alkali-activated concrete; Civil and Structural Engineering; Perceptron; T; Chemical technology; Technik; 624; Computer science; Materials science; rheological properties; Sonstiges; Mechanisms and Mitigation of Autogenous Shrinkage in Concrete; Physical Sciences; Rheology; multilayer perceptron neural networks; Alkali-Activated Materials

Abstract Using artificial intelligence-based tools, this research aims to establish a direct correlation between the alkali-activated concrete (AAC) mix design factors and their performances. More specifically, the machine learning system was fed new property data obtained from AAC mixes used in laboratory experiments. The rheological parameters (yield stress [static/dynamic] and plastic viscosity) of AAC were predicted using the multilayer perceptron neural network (MLPNN) and bagging ensemble (BE) models. In addition, the R 2 values, k-fold analyses, statistical checks, and the dissimilarity between the experimental and predicted compressive strength were employed to assess the performance of the created models. Also, the SHapley additive exPlanation (SHAP) approach was used for examining the relevance of influencing parameters. The BE approach was found to be significantly accurate in all prediction models, with R 2 greater than 0.90, and MLPNN models were found to be moderately precise, with R 2 slightly below 0.90. However, the error assessment through statistical checks and k-fold analysis also validated the higher precision of BE models over the MLPNN models. Building models that can calculate rheological properties of AAC for different values of input parameters could save a lot of time and money compared to doing the tests in a laboratory. In order to ascertain the required amounts of raw materials of AAC, investigators, as well as businesses, may find the SHAP study helpful.