Title

Artificial Intelligence to Investigate Modulus of Elasticity of Recycled Aggregate Concrete

Abstract

Modulus of elasticity (MOE) is one of the main factors that affect the deformation characteristics and serviceability of concrete in the hardened state. The use of recycled concrete aggregate (RCA) in concrete production can lead to a significant reduction in the MOE. An artificial neural network (ANN) was employed to quantify the effect of coarse RCA on the concrete's MOE. A database summarizing over 480 data series obtained from 52 technical publications was developed and analyzed using ANN. Concrete mixture proportions and aggregate properties were considered input parameters. The rate of reduction in 28-day MOE was considered the output parameter. An additional data set of 43 concrete mixtures obtained from laboratory investigation of concrete with well-known properties was used to validate the established model. Several combinations of input parameters and ANN architectures were considered in the analysis. Results indicated that the performance of the system was acceptable, with a coefficient of correlation ranging from 0.71 to 0.95 for the training, validation, and testing of the model with a mean square error limited to 0.008. The developed model was incorporated for a case study on a typical concrete used for rigid pavement construction. Contour graphs were developed to showcase the effect of up to 100% coarse RCA replacement on the variations in the MOE of concrete made with 0.40 water-cementitious materials ratio (w/cm) and 323 kg/m3 (545 lb/yd 3 ) of a binary cement, designated for rigid pavement construction. The results indicated that depending on the RCA quality, a reduction of 10 to 30% in the MOE of pavement concrete made with 50% RCA can be expected. However, the reduction in the MOE will be limited to 10% when RCA with water absorption limited to 2.5% and an oven-dry specific gravity of over 2500 kg/m3 (156 lb/ft3) is used.

Department(s)

Electrical and Computer Engineering

Second Department

Civil, Architectural and Environmental Engineering

Comments

The authors gratefully acknowledge the financial support provided by the Missouri Department of Transportation and the RE-CAST Tier 1 University Transportation Center at Missouri S&T. Support from the National Science Foundation, the Missouri University of Science and Technology Intelligent Systems Center, and the Mary K. Finley Endowment is also gratefully acknowledged. This research was sponsored by the Army Research Laboratory (ARL), and it was accomplished under Cooperative Agreement Number W911NF-18-2-0260.

Keywords and Phrases

Artificial intelligence; Machine learning; Modulus of elasticity; Neural networks; Recycled concrete aggregate; Sustainable infrastructure

International Standard Serial Number (ISSN)

0889-325X

Document Type

Article - Journal

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2019 American Concrete Institute (ACI), All rights reserved.

Share

 
COinS