Forecasting Compressive Strength of M30 Grade Self-Compacting Concrete Utilizing Artificial Neural Networks with Agricultural Waste Incorporation (original) (raw)

2024, Nanotechnology Perceptions

The aim of the current experimental study was to evaluate the properties of two agricultural waste products, rice husk ash (RHA) and sugarcane bagasse ash (SCBA), when they were partially substituted for ordinary Portland cement (OPC) in self-compacting concrete that was intended to have an M30 grade strength. Throughout the trials, the water-to-powder ratio (w/p) remained constant at 0.45. RHA was initially added to OPC in different ratios, from 2% to 10% by weight of cement. Finding the ideal percentage of RHA substitution that could be attained while preserving the desirable qualities was the goal. After that, a replacement range of 5% to 15% of SCBA was investigated by combining SCBA with the determined optimal RHA percentage.The Evaluation of the self-compacting concrete specimens modified with RHA and SCBA's fresh properties as well as their compressive strength characteristics were included in the inquiry. An Artificial Neural Network (ANN) model was used for deep learning in order to predict the compressive strength as the dependent variable. Decision trees and Random Forest Regressor were used for machine learning in order to compare and evaluate the accuracy of various modelling algorithms. Essentially, the goal of the study was to ascertain the ideal ratios of RHA and SCBA to OPC in order to preserve the intended characteristics of the concrete. In order to obtain precise forecasts and insights, this involved investigating new characteristics and compressive strength values. To do this, ANN, Random Forest Regressor, and Decision Tree algorithms were combined.

Sign up for access to the world's latest research.

checkGet notified about relevant papers

checkSave papers to use in your research

checkJoin the discussion with peers

checkTrack your impact