Title: Artificial Neural Network Model for Strength Prediction of Ultra-High-Performance Concrete

Author(s): Joaquín Abellán-García

Publication: Materials Journal

Volume: 118

Issue: 4

Appears on pages(s): 3-14

Keywords: activation function; artificial neural network (ANN); compressive strength; resilient backpropagation algorithm (Rprop); supplementary cementitious material (SCM); ultra-high-performance concrete (UHPC)

DOI: 10.14359/51732710

Date: 7/1/2021

Abstract:
Ultra-high-performance concrete (UHPC) is the outcome of the mixture of several constituents, leading to a highly complex material, which makes it more difficult to understand the effect of each component and their interactions on compressive strength. This research goal is developing an artificial neural network (ANN) approach to predict the compressive strength of UHPC, being able to incorporate supplementary cementitious materials (SCMs), and even different situations in relation to the aggregate: from pastes to incorporation of coarse aggregate. The one-hidden-layer ANN model was trained with 927 data by using the R-code language. The data was produced by collecting data from 210 experiments combined with 717 dosages from previous research. The Olden algorithm was used to analyze the relationships between the UHPC’s components and strength. The results indicated that the ANN is an efficient model for predicting the compressive strength of UHPC, regardless of the SCM used or maximum size of aggregate considered.