Investigation of ANN architecture for predicting the compressive strength of concrete containing GGBFS

• Published in: PloS one Vol. 16; no. 12; p. e0260847
• Main Authors: Tran, Van Quan, Mai, Hai-Van Thi, Nguyen, Thuy-Anh, Ly, Hai-Bang
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 03.12.2021; Public Library of Science (PLoS)
• Subjects: Accuracy; Aggregates; Algorithms; Architecture; Artificial intelligence; Biology and Life Sciences; Blast furnace slags; Civil engineering; Compressive Strength; Computer and Information Sciences; Concrete; Construction Materials - analysis; Engineering and Technology; Experiments; GGBS; Granulation; Humans; Industrial Waste - analysis; Materials; Materials Testing - methods; Mechanical properties; Modelling; Moisture content; Monte Carlo Method; Monte Carlo simulation; Neural networks; Neural Networks, Computer; Performance evaluation; Physical Sciences; Reproducibility of Results; Research and Analysis Methods; Sensitivity analysis; Shear strength; Slag; Statistical methods; Superplasticizers; Water content; Vietnam
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0260847

An extensive simulation program is used in this study to discover the best ANN model for predicting the compressive strength of concrete containing Ground Granulated Blast Furnace Slag (GGBFS). To accomplish this purpose, an experimental database of 595 samples is compiled from the literature and utilized to find the best ANN architecture. The cement content, water content, coarse aggregate content, fine aggregate content, GGBFS content, carboxylic type hyper plasticizing content, superplasticizer content, and testing age are the eight inputs in this database. As a result, the optimal selection of the ANN design is carried out and evaluated using conventional statistical metrics. The results demonstrate that utilizing the best architecture [8-14-4-1] among the 240 investigated architectures, and the best ANN model, is a very efficient predictor of the compressive strength of concrete using GGBFS, with a maximum R2 value of 0.968 on the training part and 0.965 on the testing part. Furthermore, a sensitivity analysis is performed over 500 Monte Carlo simulations using the best ANN model to determine the reliability of ANN model in predicting the compressive strength of concrete. The findings of this research may make it easier and more efficient to apply the ANN model to many civil engineering challenges.