Sina Hashemi Salanghouch, Ahmad Ali Fakhimi,
Volume 24, Issue 4 (10-2024)
Abstract
Friction angle of soil is a critical parameter in the geotechnical engineering and has a direct impact on the design of various structures, such as retaining walls, slopes, and piles. This parameter plays a crucial role in determining the overall safety and performance of these structures, making it a key player in the geotechnical analysis and design. In recent years, there have been some impressive advancements in the field of artificial neural networks and deep learning models. These advancements have transformed these models into the highly effective tools for predicting the properties and behavior of soil. By using a powerful deep learning model, it is now possible to save a considerable amount of time and money when it comes to estimating and predicting soil properties. In this particular study, a convolutional neural network was developed to predict the peak friction angle of Firuzkuh sand using some soil images and the dry density as the input parameters. The network itself consisted of five consecutive convolutional layers, as well as a pyramid pooling module that utilized four different pooling sizes arranged in parallel. In addition, two fully connected layers were incorporated into the network's design, which enabled it to satisfactorily process the input parameters of the images and the dry densities with respect to the speed and precision. This network converts the soil image into a scalar (number) by using these 5 convolutional layers, the pyramid pooling module and a fully connected layer. Then, this scalar is concatenated with the dry density of the soil, is passed through a fully connected layer, and the peak friction angle of the soil is obtained as an output. For data generation, a total of ten samples of Firuzkuh sand were prepared. These samples had different gradation curves, which are referred to as S1 to S10 specimens. Each soil specimen was compacted at three different dry densities. The peak friction angle associated with the 30 different densities for the 10 different particle size distributions (S1 to S10 specimens) was determined using the direct shear test apparatus. The direct shear test box was 100 ×100 × 25 mm in size. For network training and testing, the soil specimens were spread on a flat surface and 50 photos in different light environments with varying distances of the camera from the soil surface, were taken from each specimen. Since in the network training process, three dry densities were considered for each sample, a total of 1500 images were prepared for the network database. Of these, 1125 photos were used for training and 375 photos were saved for testing the network. The network was trained for 1000 epochs on the training data, and the mean square error after 1000 epochs was reduced to 1.84. The outcome of the assessment conducted on the designed convolutional neural network in this study, using 375 test data, revealed that the network can predict the peak friction angle of Firuzkuh sand by incorporating the image and dry density of the soil as input variables. The total normalized relative error was 3.0%, while the maximum normalized relative error was 10%. This indicates that the network has the ability to quickly predict the peak friction angle of the Firuzkuh sand with a good accuracy.
Ehsan Saeedi, Arash Razmkhah, Mohsen Kamalian, Faradjollah Askari,
Volume 24, Issue 6 (11-2024)
Abstract
It is common to apply physical modeling for a more precise investigation of phenomena in geotechnical engineering. The reconstitution of specimens is an appropriate way to study soil behavioral parameters in laboratories due to the restrictions of acceptable undisturbed sample preparation. Reconstitution of the sand sample is one of the most well-known challenges of physical modeling. One of the most significant aspects of physical modeling geotechnical engineering is the repeatability of bed preparation. The reconstitution of sample and bed preparation in physical modeling are divided into two general approaches, depending on the type of porosity control employed. Methods where the porosity is adjusted after deposition, is only appropriate for dense beds with diverse layers. This category includes the methods of tamping and vibration. Another methods where the porosity is controlled during deposition, which aim at obtaining any porosity within the maximum-minimum porosity limits of the material that is pluviation technique. Because of the favorable conditions and prompt modeling it enables, the preparation of layers by the pluviation technique is one of the most reliable bed preparation methods. The pluviation technique can be divided into three categories, air pluviation, vacuum pluviation, and water pluviation. In addition, each category is divided into three minor subgroups that monitor sand-rain outflow intensity as follows, controlling the deposition intensity of sand output from single or multiple nozzles of various shapes, controlling the deposition intensity of the sand output from single or multiple sieves, controlling the deposition intensity of the sand output from longitudinal aperture (curtain pluviation). The effective parameters on pluviation system are deposition intensity and fall height. Deposition intensity, itself, is affected by aperture width, traveling pluviator speed, and the number of opening. The sand reconstitution technique must properly provide real sample conditions in a wide range of soil density (loose to dense), the uniform void ratio in the entire reconstructed specimen, fully saturated conditions for undrained status, the samples should be well mixed without particle size segregation, regardless of particle size gradation and simulation of the studied depositional fabric characteristic.
In this research, a novel approach focusing on a traveling sand pluviator with two apertures was developed for the reconstitution of large-scale samples. Experiments on Iran’s Firuzkuh sand (#161) _Silica sand with fine-grained content of about 1% that is known as the standard sand in Iran and has been the most widely used sand for laboratory studies_ evaluated the effects of opening width, traveling pluviator speed, fall height, and number of openings on deposition intensity and relative density. The results showed that a decrease in deposition intensity is correlated with a decrease in aperture width and an increase in traveling pluviator speed, which significantly enhances relative density. With changes in the effective parameters, a broad range of relative densities could be obtained—from 12 to 93 percent. Comparisons between the findings of the experiments revealed that double-aperture pluviation plate, given the increases in sand outlet and deposition intensity, had a density equivalent to that of single-aperture pluviation plate whit; moreover, each aperture behaved as separate, resulting in prompt sand bed preparation. The findings also revealed that increase in fall height leads to increase in relative density.
