Open AccessPredicting the characteristics of pond ash concrete using artificial neural networks
Author(s) -
G. Swamy Yadav,
Dara Swetha Sudarshan,
G. Sahithi,
E. Laxmi Prasanna
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/872/1/012176
Subject(s) - pozzolana , compressive strength , fly ash , portland cement , compaction , environmental science , cement , curing (chemistry) , geotechnical engineering , properties of concrete , waste management , materials science , engineering , pozzolan , composite material
To improve the Engineering perspectives towards the eco-friendly environment, many efforts and researches made in the field of concrete. Adding many supplements to the concrete mix mostly results in durable concrete. Thermal power plants produce a large number of wastes like flyash, pond ash, and bottom ash. Flyash is already being used in cement industries to produce Portland Pozzolana Cement. Some researchers concluded that pond ash could also replace river sand in the concrete mix. Anticipating the compressive strength of pond ash concrete has consistently been trouble since the concrete is sensitive to its blend segments, techniques for blending, compaction, curing condition, and so forth. Scientists have given various strategies for foreseeing the properties of concrete. However, some others were not appropriate enough to predict the compressive strength of pond ash concrete. The point of this investigation is to assess the ability of the Artificial Neural Network Model (ANN) in predicting the compressive strength of pond ash concrete after 28 days of curing. Accordingly, considering specific Concrete characteristics as input factors by considering various rates 0% to 25% in steps of 1% increment of Pond Ash replaced in place of sand in Traditional Concrete of M30 Mix, Artificial Neural Network Model is built, and the properties of concrete predicted. Results demonstrated that ANN could be an alternative approach for anticipating the compressive strength properties of pond ash concrete.