Hybrid ultrasonic-neural prediction of the compressive strength of environmentally friendly concrete screeds with high volume of waste quartz mineral dust

摘要

The article presents the hybrid ultrasonic-neural assessment of the compressive strength of low-strength concrete screeds modified using high volume of mineral dusts sourced from industrial wastes. Quartz and quartz-feldspar dusts were selected to replace up to the 60% of the cement mass. The principal aim of this study is to carry out a systematic investigation of the effect of the addition of selected dusts on the compressive strength of such modified concrete screeds. The ultrasonic pulse velocity (UPV) technique was used for this purpose. After UPV analysis, about 13 different compositions were tested after 28 days for their compressive strengths (ranging from about 4 to 16 MPa). The relationship between the ultrasound velocity and compressive strength of the low-strength concrete screeds was found to be not acceptable. Finally, the artificial neural networks (ANNs) were employed to predict the compressive strength based on the composition of the concrete and UPV velocity. The obtained values of linear correlation coefficient (R) equal to 0.93, 0.91 and 0.94 respectively for learning, testing and validation phase were satisfactory for reliable evaluation of the compressive strength of environmentally friendly low-strength concrete screeds modified using high volume of waste quartz mineral dusts. (C) 2018 Elsevier Ltd. All rights reserved.