Authors: Benjamin A. Young , Alex Hall , Laurent Pilon , Puneet Gupta , Gaurav Sant
DOI: 10.1016/J.CEMCONRES.2018.09.006
Keywords:
Description: Abstract The use of statistical and machine learning approaches to predict the compressive strength concrete based on mixture proportions, account its industrial importance, has received significant attention. However, previous studies have been limited small, laboratory-produced data sets. This study presents first analysis a large set (>10,000 observations) measured strengths from actual (job-site) mixtures their corresponding proportions. Predictive models are applied examine relationships between design variables strength, thereby develop an estimate (28-day) strength. These also laboratory-based measurements published by Yeh et al. (1998) performance across both sets is compared. Furthermore, illustrate value such beyond simply prediction, they used optimal that minimize cost embodied CO2 impact while satisfying imposed target strengths.
.The resource attribute category is marked as computer automatic recognition, which may not be accurate. You can try clicking the link to view the resource details.