Search | Korea Science

Armaghani, Danial J.;Mamou, Anna;Maraveas, Chrysanthos;Roussis, Panayiotis C.;Siorikis, Vassilis G.;Skentou, Athanasia D.;Asteris, Panagiotis G.
- Geomechanics and Engineering
- /
- v.25 no.4
- /
- pp.317-330
- /
- 2021
This paper reports the results of advanced data analysis involving artificial neural networks for the prediction of the unconfined compressive strength of granite using only two non-destructive test indexes. A data-independent site-independent unbiased database comprising 182 datasets from non-destructive tests reported in the literature was compiled and used to train and develop artificial neural networks for the prediction of the unconfined compressive strength of granite. The results show that the optimum artificial network developed in this research predicts the unconfined compressive strength of weak to very strong granites (20.3-198.15 MPa) with less than ±20% deviation from the experimental data for 70% of the specimen and significantly outperforms a number of available models available in the literature. The results also raise interesting questions with regards to the suitability of the Pearson correlation coefficient in assessing the prediction accuracy of models.
https://doi.org/10.12989/gae.2021.25.4.317 인용 KSCI

Liu, Haifeng;Wu, Baisheng;Li, Zhengguang
- Structural Engineering and Mechanics
- /
- v.43 no.3
- /
- pp.273-285
- /
- 2012
Structural reanalysis is frequently used to reduce the computational cost during the process of design or optimization. The supports can be regarded as the design variables in various types of structural optimization problems. The location, number, and type of supports may be varied in order to yield a more effective design. The paper is focused on structural static reanalysis problem with added supports where some node displacements along axes of the global coordinate system are specified. A new approach is proposed and exact solutions can be provided by the approach. Thus, it belongs to the direct reanalysis methods. The information from the initial analysis has been fully exploited. Numerical examples show that the exact results can be achieved and the computational time can be significantly reduced by the proposed method.
https://doi.org/10.12989/sem.2012.43.3.273 인용 KSCI