Prediction of shear strength of concrete produced by using pozzolanic materials and partly replacing NFA by MS using ANN

• Published in: Journal of engineering, design and technology design and technology, 2021-04, Vol.19 (2), p.578-587
• Main Authors: Mane, Kiran Mansingrao, Kulkarni, D K, Prakash, K B
• Format: Article
• Language: English
• Subjects: Accuracy; Artificial neural networks; Blast furnace practice; Blast furnace slags; Cement; Concrete; Design optimization; Environmental impact; Fly ash; Industrial wastes; Material properties; Mean square errors; Metakaolin; Model accuracy; Neural networks; Pozzolans; Principal components analysis; Regression analysis; Sand; Sand & gravel; Shear strength; Shear tests; Silica fume; Silicon dioxide
• ISSN: 1726-0531; 1758-8901
• DOI: 10.1108/JEDT-12-2019-0346

PurposeThe use of huge quantity of natural fine aggregate (NFA) and cement in civil construction work which have given rise to various ecological problems. The industrial waste like blast furnace slag (GGBFS), fly ash, metakaolin and silica fume can be partly used as a replacement for cement and manufactured sand obtained from crusher and partly used as fine aggregate. The purpose of this paper is to predict the shear strength of concrete using artificial neural network (ANN) for concrete made by using different pozzolans and partly replacing NFA by manufactured sand (MS) which can reduce the time and experimental cost.Design/methodology/approachIn this work, MATLAB software model is developed using neural network toolbox to predict the shear strength of concrete made by using pozzolanic materials and partly replacing NFA by manufactured sand (MS). Shear strength was experimentally calculated, and results obtained from experiment were used to develop the ANN model. A total of 131 results values were used to modeling formation, and from that 30% data record was used for testing purpose and 70% data record was used for training purpose. In total, 25 input materials properties were used to find the 28 days shear strength of concrete obtained from partly replacing cement with pozzolans and partly replacing NFA by manufactured sand (MS).FindingsThe results obtained from ANN model provide very strong accuracy to predict shear strength of concrete obtained from partly replacing cement with pozzolans and NFA by manufactured sand.Originality/valueThis research study is on determining shear strength of concrete using ANN. The use of this study is to predict the shear strength of concrete using ANN for concrete made by using different pozzolans and partly replacing NFA by manufactured sand (MS) which can reduce the time and experimental cost.