Implementation of deep neural networks and statistical methods to predict the resilient modulus of soils

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11310%2F23%3A10476937" target="_blank" >RIV/00216208:11310/23:10476937 - isvavai.cz</a>

Výsledek na webu

<a href="https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=nZTJOGcSSw" target="_blank" >https://verso.is.cuni.cz/pub/verso.fpl?fname=obd_publikace_handle&handle=nZTJOGcSSw</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1080/10298436.2023.2257852" target="_blank" >10.1080/10298436.2023.2257852</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Implementation of deep neural networks and statistical methods to predict the resilient modulus of soils

Popis výsledku v původním jazyce

The Resilient Modulus (Mr) is perhaps the most relevant and widely used parameter to characterise the soil behaviour under repetitive loading for pavement applications. Accordingly, it is a crucial parameter controlling the mechanistic-empirical pavement design. Nonetheless, determining the Mr by laboratory tests is not always possible due to the high consumption of time and financial resources. Thus, developing new indirect approaches for estimating the MR is necessary. Precisely, this article investigates the application of Deep Neural Networks (DNNs) and statistical methods to predict the Mr of soils. For that purpose, the Long-Term Pavement Performance (LTPP) database was implemented. It includes 64 701 datasets resulting from coarse-grained and fine-grained soil samples considering a wide range of grain size distribution and subjected to different stress levels. The input parameters were the bulk stress, octahedral shear stress, and the percentage of soil particles passing through the different sieves (3&quot;, 2&quot;, 3/2&quot;, 1&quot;, 3/4&quot;, 1/2&quot;, 3/8&quot;, No. 4, No. 10, No. 40, No. 80, and No. 200) and the output was the Mr. The results suggest that while conventional mathematical models are unable to predict the influence of the grain size distribution and stress level on the Mr, the proposed DNNs were able to reproduce very accurate predictions. Notably, the proposed computational models have been uploaded to a GitHub repository and have become a valuable tool for forecasting the Mr when experimental measurements are not feasible.

Název v anglickém jazyce

Implementation of deep neural networks and statistical methods to predict the resilient modulus of soils

Popis výsledku anglicky

The Resilient Modulus (Mr) is perhaps the most relevant and widely used parameter to characterise the soil behaviour under repetitive loading for pavement applications. Accordingly, it is a crucial parameter controlling the mechanistic-empirical pavement design. Nonetheless, determining the Mr by laboratory tests is not always possible due to the high consumption of time and financial resources. Thus, developing new indirect approaches for estimating the MR is necessary. Precisely, this article investigates the application of Deep Neural Networks (DNNs) and statistical methods to predict the Mr of soils. For that purpose, the Long-Term Pavement Performance (LTPP) database was implemented. It includes 64 701 datasets resulting from coarse-grained and fine-grained soil samples considering a wide range of grain size distribution and subjected to different stress levels. The input parameters were the bulk stress, octahedral shear stress, and the percentage of soil particles passing through the different sieves (3&quot;, 2&quot;, 3/2&quot;, 1&quot;, 3/4&quot;, 1/2&quot;, 3/8&quot;, No. 4, No. 10, No. 40, No. 80, and No. 200) and the output was the Mr. The results suggest that while conventional mathematical models are unable to predict the influence of the grain size distribution and stress level on the Mr, the proposed DNNs were able to reproduce very accurate predictions. Notably, the proposed computational models have been uploaded to a GitHub repository and have become a valuable tool for forecasting the Mr when experimental measurements are not feasible.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10505 - Geology

Projekt

<a href="/cs/project/GC21-35764J" target="_blank" >GC21-35764J: Experimentální a numerické studium sdruženého termo-hydro-mechanického chování jílu s důrazem na cyklické zatěžování</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

International Journal of Pavement Engineering

ISSN

1029-8436

e-ISSN

1477-268X

Svazek periodika

24

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

19

Strana od-do

2257852

Kód UT WoS článku

001068220900001

EID výsledku v databázi Scopus

2-s2.0-85171858404