Approximation of Elasticity Modulus of Groundnut Shell Ash Based Self-Consolidating High-Performance Concrete (SCHPC) Using Artificial Neural Network (ANN)

Abstract

The focus of this study is the prediction of Elasticity Modulus (ME) of Self-Consolidating high-performance concrete (SCHPC) incorporated with Groundnut Shell Ash (GSA) with Artificial Neural Networks (ANN). The present research utilized GSA as a SCM in the development of SCHPC with GSA (0, 10, 20, 30 and 40%) to produce concrete (SCHPC0, SCHPC10, SCHPC20, SCHPC30 and SCHPC40) and a designed concrete mix of 41 N/mm2 was employed in accordance with ACI and EFNARC guidelines. The compressive strength, tensile strength, Elasticity Modulus and microstructure densifications of SCHPC were the major parameters measured. The Elasticity Modulus was modelled with curing age, percentage substitution of GSA, tensile strength and compressive strength as input while output layer has only one neuron which represents modulus rupture as the target value, in this case, the Modulus Elasticity of GSA Blended SCHPC. Adequacy of adopted models was determined using coefficient of determination (R2) and Mean Square Error (MSE). phase transformation and microstructural analysis of SCHPC showed microstructure densification with an improved interface obtained from SCHPC10 and SCHPC20.The adopted model (back propagation 4-8-4-1) adequately predicted the EM properties of SCHPC (R2: 0.67–0.96; MSE: 0.28–4.81).