Neural network modeling on evolution of hydration reaction for Portland cement
Sch. of Comput. Sci. & Technol., Shandong Univ., Jinan, China
IEEE Fifth International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA), 2010
@inproceedings{wang2010neural,
title={Neural network modeling on evolution of hydration reaction for Portland cement},
author={Wang, L. and Yang, B. and Chen, Y. and Zhao, X. and Chang, J. and Wang, H.},
booktitle={Bio-Inspired Computing: Theories and Applications (BIC-TA), 2010 IEEE Fifth International Conference on},
pages={664–668},
organization={IEEE},
year={2010}
}
The hydration reaction of Portland cement paste has an important impact on the formation of microstructure and development of strength. However, simulating the evolution of hydration reaction is very difficult because there are multi-phased, multi-sized and interrelated complex chemical and physical reactions during cement hydration. In this paper, a feedforward neural network model is built for predicting the evolution of degree of hydration. In order to reduce the computing time, GPUs are used for acceleration in parallel. Studies have shown that according to the established model, simulation curve of hydration is in good accordance with the observed experimental data.
June 20, 2011 by hgpu
