Implementation of Artificial Neural Networks to Automate SASW Inversion: Fid-Bau Portal

Fachinformationsdienst BAUdigital

A platform for research: civil engineering, architecture and urbanism

Implementation of Artificial Neural Networks to Automate SASW Inversion

Shirazi, H. / Nazarian, S. / Abdallah, I.

One of the complicated aspects of the spectral-analysis-of-surface-waves (SASW) method is the inversion procedure. Artificial neural network (ANN) models can potentially substitute the inversion process. For this purpose, numerous models of different neural network types and architectures were developed with different software packages. Previous studies have shown the estimation of the subgrade properties is the most challenging aspect of implementing the ANN models. This paper focuses on training models for the subgrade layer. The results from this study were used to develop more sophisticated models to estimate all pavement stiffness parameters.

Access

Check availability in my library

Order at Subito €

Page navigation

Document information

Export, share and cite

Implementation of Artificial Neural Networks to Automate SASW Inversion

Shirazi, H. / Nazarian, S. / Abdallah, I.

One of the complicated aspects of the spectral-analysis-of-surface-waves (SASW) method is the inversion procedure. Artificial neural network (ANN) models can potentially substitute the inversion process. For this purpose, numerous models of different neural network types and architectures were developed with different software packages. Previous studies have shown the estimation of the subgrade properties is the most challenging aspect of implementing the ANN models. This paper focuses on training models for the subgrade layer. The results from this study were used to develop more sophisticated models to estimate all pavement stiffness parameters.

Implementation of Artificial Neural Networks to Automate SASW Inversion

Shirazi, H. / Nazarian, S. / Abdallah, I.

One of the complicated aspects of the spectral-analysis-of-surface-waves (SASW) method is the inversion procedure. Artificial neural network (ANN) models can potentially substitute the inversion process. For this purpose, numerous models of different neural network types and architectures were developed with different software packages. Previous studies have shown the estimation of the subgrade properties is the most challenging aspect of implementing the ANN models. This paper focuses on training models for the subgrade layer. The results from this study were used to develop more sophisticated models to estimate all pavement stiffness parameters.

Access

Check availability in my library

Order at Subito €

Page navigation

Document information

Export, share and cite

Document information

Title:

Implementation of Artificial Neural Networks to Automate SASW Inversion

Contributors:

Shirazi, H. (author) / Nazarian, S. (author) / Abdallah, I. (author)

Conference:

GeoCongress 2006 ; 2006 ; Atlanta, Georgia, United States

Published in:

GeoCongress 2006 ; 1-6

Publication date:

2006-02-21

ISBN:

DOI:

https://doi.org/10.1061/40803(187)95

Type of media:

Conference paper

Type of material:

Electronic Resource

Language:

English

Keywords:

Geotechnical engineering , Numerical models , Information management , Computer applications , Stiffness , Neural networks , Parameters , Computer software

Similar titles

Implementation of Artificial Neural Networks to Automate SASW Inversion

Shirazi, H. / Nazarian, S. / Abdallah, I. et al. | British Library Conference Proceedings | 2006

Time-Frequency Analysis for Impact Echo-SASW (IE-SASW) Method

Kim, D. S. / Kim, N. R. / Seo, W. S. | British Library Online Contents | 2004

Neural Networks for Backcalculation of Moduli from SASW Test

Williams, T. P. / Gucunski, N. | British Library Online Contents | 1995

Neural Networks for Backcalculation of Moduli from SASW Test

Williams, Trefor P. | Online Contents | 1995

Artificial Neural Network–Based Inversion for Leaky Rayleigh Wave Dispersion Curve from Non-contact SASW Testing of Multi-layer Pavements

Al-Adhami, Hiba / Gucunski, Nenad | Springer Verlag | 2021