A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Shear behaviors and peak friction angle predictions of three critical geomembrane–soil interfaces
https://orcid.org/http://orcid.org/0000-0001-9935-6442
The interface shear behavior is quite beneficial for explaining the stress–strain response of geosynthetics. A series of interface direct shear tests are carried out between three distinct geomembranes and soils to understand their interfacial characteristics. To better comprehend varying trends of the interface shear parameters, three novel prediction models based on machine learning are further developed for the peak friction angles of geomembrane–soil interfaces. The results show that the shear stress–shear displacement curves are more susceptible to the variations of soils’ relative densities, particularly at the geomembrane–coarse sand interface. A conclusion of engineering significance is that coarse sand (D50 = 0.84 mm) is the most suitable material for the bedding layer of the composite geomembrane under σn ≥ 100 kPa and crushed stone (D50 = 7 mm) performs best in the perforated geomembranes-soil interface among the three types of soils. Upon comparing three predicting models for peak friction angles, a novel conclusion is gained that the gradient boosting regressor combined with Bayesian optimization is the most precise model. Then, a comprehensive formula for the peak friction angles containing normal stress, relative density, mean particle size and mean particle regularity is established.
Shear behaviors and peak friction angle predictions of three critical geomembrane–soil interfaces
https://orcid.org/http://orcid.org/0000-0001-9935-6442
The interface shear behavior is quite beneficial for explaining the stress–strain response of geosynthetics. A series of interface direct shear tests are carried out between three distinct geomembranes and soils to understand their interfacial characteristics. To better comprehend varying trends of the interface shear parameters, three novel prediction models based on machine learning are further developed for the peak friction angles of geomembrane–soil interfaces. The results show that the shear stress–shear displacement curves are more susceptible to the variations of soils’ relative densities, particularly at the geomembrane–coarse sand interface. A conclusion of engineering significance is that coarse sand (D50 = 0.84 mm) is the most suitable material for the bedding layer of the composite geomembrane under σn ≥ 100 kPa and crushed stone (D50 = 7 mm) performs best in the perforated geomembranes-soil interface among the three types of soils. Upon comparing three predicting models for peak friction angles, a novel conclusion is gained that the gradient boosting regressor combined with Bayesian optimization is the most precise model. Then, a comprehensive formula for the peak friction angles containing normal stress, relative density, mean particle size and mean particle regularity is established.
Shear behaviors and peak friction angle predictions of three critical geomembrane–soil interfaces
https://orcid.org/http://orcid.org/0000-0001-9935-6442
The interface shear behavior is quite beneficial for explaining the stress–strain response of geosynthetics. A series of interface direct shear tests are carried out between three distinct geomembranes and soils to understand their interfacial characteristics. To better comprehend varying trends of the interface shear parameters, three novel prediction models based on machine learning are further developed for the peak friction angles of geomembrane–soil interfaces. The results show that the shear stress–shear displacement curves are more susceptible to the variations of soils’ relative densities, particularly at the geomembrane–coarse sand interface. A conclusion of engineering significance is that coarse sand (D50 = 0.84 mm) is the most suitable material for the bedding layer of the composite geomembrane under σn ≥ 100 kPa and crushed stone (D50 = 7 mm) performs best in the perforated geomembranes-soil interface among the three types of soils. Upon comparing three predicting models for peak friction angles, a novel conclusion is gained that the gradient boosting regressor combined with Bayesian optimization is the most precise model. Then, a comprehensive formula for the peak friction angles containing normal stress, relative density, mean particle size and mean particle regularity is established.
Shear behaviors and peak friction angle predictions of three critical geomembrane–soil interfaces
Acta Geotech.
Feng, Yanfang (author) / Wang, Dongxing (author)
Acta Geotechnica ; 19 ; 3139-3160
2024-05-01
22 pages
Article (Journal)
Electronic Resource
English
Comprehensive formula , Geomembrane–soil interface , Machine learning , Peak friction angle , Prediction models Engineering , Geoengineering, Foundations, Hydraulics , Solid Mechanics , Geotechnical Engineering & Applied Earth Sciences , Soil Science & Conservation , Soft and Granular Matter, Complex Fluids and Microfluidics
Shear behaviors and peak friction angle predictions of three critical geomembrane–soil interfaces
| Springer Verlag | 2024
Peak Friction Behavior of Smooth Geomembrane-Particle Interfaces
| British Library Online Contents | 1999
Shear Strength between Soil/Geomembrane and Geotextile/Geomembrane Interfaces
| British Library Conference Proceedings | 2014