TechRxiv
Abambres and Lantsoght 2020.pdf (537.09 kB)

ANN-based Fatigue Strength of Concrete Under Compression

Download (537.09 kB)
preprint
posted on 20.07.2020 by Abambres M, Lantsoght E

When concrete is subjected to cycles of compression, its strength is lower than the statically determined concrete compressive strength. This reduction is typically expressed as a function of the number of cycles. In this work, we predict the reduced capacity as function of a given number of cycles by means of artificial neural networks (ANN). A 203-point experimental dataset gathered from the literature was used. The proposed ANN model results in a maximum relative error of 5.1% and a mean counterpart of 1.2% for the whole dataset. It’s shown that the proposed analytical model outperforms the existing design code expressions.

History

Email Address of Submitting Author

amgg@mailfence.com

Submitting Author's Institution

Num3ros

Submitting Author's Country

Portugal

Licence

Exports