Predictions of concrete compressive strength based a hybrid algorithm of GA-BP

DOI

10.2991/icmea-17.2018.60How to use a DOI?

Keywords

Attribute reduction rule;GA-BP,Time threshold;Concrete compressive strength

Abstract

The concrete quality is of great significance for the safety of buildings. This paper conducted the research on this subject in the actual concrete mixing plant, with concrete compressive strength (CCS) being the indicator of concrete quality. Firstly, in order to make the quality evaluation models feasible, the rough set theory method based attribute reduction rule (ARR) was introduced to build the equivalent quality evaluation models with fewer measurable factors. Then, along with the consumptions of raw materials, the correlation coefficients of the consumption amounts, including sand ratio, water-cement ratio, and water-binder ratio,were determined as the input parameters of GA-BP. The prediction accuracy, stability and reliability (RMSE:1.39; X : 3.20%; S:2.18% ) were better than those of the contrast schemes. Furtherly, the research shew that the rules of some factors, such as personnel, material properties, equipment status, and environment, are step functions of time, so the time threshold was introduced into GA-BP models to reduce the influence of these factors on the model, the algorithm of determining the optimal time threshold was given. In the case study, the appropriate time threshold improved the accuracy of GA-BP. Finally, the proposed models and the algorithms were applied in the actual plant operations to estimate CCS on line, the satisfied results were achieved.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Rendong Shi
AU  - Wei Zhong
AU  - Hong Zhang
AU  - Huangbin Chen
AU  - Xu Ji
PY  - 2018/02
DA  - 2018/02
TI  - Predictions of concrete compressive strength based a hybrid algorithm of GA-BP
BT  - Proceedings of the 4th Annual International Conference on Material Engineering and Application (ICMEA 2017)
PB  - Atlantis Press
SP  - 265
EP  - 270
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmea-17.2018.60
DO  - 10.2991/icmea-17.2018.60
ID  - Shi2018/02
ER  -