Search published articles


Showing 2 results for Settlement

M. R. Mosaddeghi, A. Hemmat, M. A. Hajabbasi,
Volume 7, Issue 1 (4-2003)
Abstract

Soil tilth is crucial to seedling emergence, plant growth, and crop yield. Soil tilth of unstable soil is very susceptible to change. Internal forces originating from matric suction can change soil physical properties. A laboratory study was conducted on pots of a surface silty clay loam soil of Khomeinishahr series (fine-loamy, mixed, thermic Typic Haplargids, USDA), located in Research Farm of Isfahan University of Technology. Soil surface subsidence, bulk density, cone index, and tensile strength were measured after first flood irrigation. Results showed that the seedbed (0-20 cm) with a bulk density of 1.2 Mg.m-3 will be changed to a massive soil with high values of bulk density, cone index, and tensile strength after soil wetting. Slaking, slumping and coalescence of the soil caused soil surface to subside about 1.5 cm in 20 cm soil layer. After irrigation, cone index and tensile strength increased abruptly with decreasing of moisture content. It is shown that the dominant source of strength (cone index and tensile strength) gain during drying is the effective stress due to matric suction. In the absence of external loads, physical state (tilth) of the soil returned back to the original state. Therefore, soil slaking and slumping and rearrangement of particles along with the internal forces are the factors leading to soil hardness.
M. Seifollahi, S. Abbasi, M.a. Lotfollahi-Yaghin, R. Daneshfaraz, F. Kalateh, M. Fahimi-Farzam,
Volume 26, Issue 2 (9-2022)
Abstract

Unpredictable settlement of earth dams has led researchers to develop new methods such as artificial neural networks, wavelet theory, fuzzy logic, and a combination of them. These methods do not require time-consuming analyses for estimation. In this research, the amount of settlement in rockfill dams with a central core has been estimated using artificial intelligence methods. The data of 35 rockfill dams with a central core were used to train and validate the models. The artificial neural network, wavelet transform model, and fuzzy-neural adaptive inference system are the proposed models which were used in the present study. According to the results, the best model for an artificial neural network had two hidden layers, the first layer of 18 neurons and the second layer of 7 neurons, with the Tansig-Tansig activation function, with a coefficient of determination R2=0.4969. The best model for the fuzzy-neural inference system had the ring function (Dsigmoid) as a membership function, with three membership functions and 142 repetitions with a coefficient of determination R2=0.2860. Also, combining wavelet-neural network conversion with the coif2 wavelet function due to the more adaptation this function has to the input variables, the better the performance, and this function, with a coefficient of determination R2=0.9447, had the highest accuracy compared to other models.


Page 1 from 1     

© 2024 CC BY-NC 4.0 | JWSS - Isfahan University of Technology

Designed & Developed by : Yektaweb