Investigation on structural behavior for steel & tubes with light weight concrete using HLN aid of MKHO

Abstract

Composite CST with lightweight concrete as infill for three light concrete grades such as M20 to M40 with different loading conditions. The optimal solutions as standard concrete and natural aggregate, waste material from the quarry are collected and added for replacement of natural sand in construction. While causing the experiment, cost and time will be extended, and the structural lightweight concrete mixes attain these can be designed. In present study, lightweight concrete materials are used to prepare the concrete mix with different proportion by replacement of quarry dust instead of sand and analysed the mechanical and other properties using machine learning techniques. The materials used in the present study were cured at the interval of 7 and 28 days, to train the Neural Network (NN) with Hidden layer neuron (HLN) maximization process Modified Krill Herd Optimization (MKHO) model used and these are initially considered. All the ideal results in the planned system demonstrate how the achieved mistake values among the different trail mixes and the predicted value of various mix proportion are obtained as zero and equivalent to zero. Based on the present study results, optimal model exactness is around 98.78% with other machine learning models.