Approximation of elasticity modulus of groundnut shell ash-based self-consolidating high-performance concrete using artificial neural network

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 (SCHPC 0 , SCHPC 10 , SCHPC 20 , SCHPC 30 and SCHPC 40 ) and a designed concrete mix of 41 N/mm 2 was employed in accordance with ACI and EFNARC guidelines. The design of SCC/SCHPC is majorly guided by EFNARC 2002 and 2005 . The ACI 363 is a guide for preparation and testing of High strength concrete. The compressive strength, tensile strength, Elasticity Modulus and microstructure densifications of SCHPC were the major parameters measured. The Elasticity Modulus was modeled 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 Elasticity Modulus of GSA Blended SCHPC. Adequacy of adopted models was determined using coefficient of determination ( R 2 ) and Mean Square Error (MSE). Phase transformation and micro-structural analysis of SCHPC showed microstructure densification with an improved interface obtained from SCHPC 10 and SCHPC 20 . The adopted model (back-propagation 4–8-4–1) adequately predicted the EM properties of SCHPC ( R 2 : 0.67–0.96; MSE: 0.28–4.81).