scholarly journals Application of the ANFIS to analysis of results from soil testings

2014 ◽  
Vol 13 (2) ◽  
pp. 007-015
Author(s):  
Ewa Daniszewska

The article was analyzed in order to test applicability and capability of the ANFIS tool used for interpretation of results of triaxial shear tests on loamy soils sampled near Olsztyn. The ANFIS system in the Matlab software programme was used to model and determine relationships between the shear stress and soil resistance parameters in a triaxial shear test apparatus. It has been demonstrated that the achieved shear strength parameters are significantly affected by the variables tested during the triaxial experiments and physical parameters of a given soil sample, but also by the loading increment rate during the tests. It is extremely important to adjust the rate of loading during a test according to the preliminary characterization of a tested ground sample so as to have some control over the obtained ground strength parameters. The neuro-fuzzy model has been constructed based on a set of values obtained after a series of experimental tests, including values of ground shear strength parameters. The database used for the neuro-fuzzy modelling consisted of 6 different ground parameters for each of the 12 shear stress rates applied during the triaxial tests. The learnability was verified on a database composed of the test results – a neuro-fuzzy model was built from learning sets and its accuracy was verified by sets of tests to which the model was applied for the first time. The results obtained from the ANFIS model did not diverge substantially from the ones obtained directly by performing the physical tests. The ANFIS proved to be highly universal and easy to operate. It accounted for the multi-faceted nature of interrelationships between ground parameters.

2021 ◽  
Vol 33 (2) ◽  
Author(s):  
John Kuna Raj

Three broad zones can be differentiated at the weathering profile; an upper, 9.4 m thick, pedological soil (zone I), an intermediate, 31.7 m thick, saprock (zone II) and the bottom bedrock (zone III). The saprock (zone II) comprises gravelly silty sands that distinctly preserve the minerals, textures and structures of the original granite and can be separated into sub-zones II A, II B, II C, and II D, based on differences in preservation of relict structures and content of litho-relicts (core-boulders). To characterize the undrained strength of saprock, samples were collected from sub-zones II A, II B, II C and II D and their physical and soil index properties determined before unconsolidated undrained triaxial tests were carried out on remolded samples. Three to four individual samples from each sub-zone were compressed under confining pressures of 138 kPa, 207 kPa, 276 kPa and/or 345 kPa. Plots of pf = [(σ1 + σ3)/2] versus qf = [(σ1 - σ3)/2] were then used to calculate apparent cohesions of 41.9 kPa, 100.3 kPa, 76.1 kPa and 73.9 kPa, and friction angles of 32.2o, 28.1o, 26.6o and 27.8o, for the samples from sub-zones II A, II B, II C, and II D, respectively. Regression analyses show apparent cohesions to decrease with increasing clay contents, and degrees of saturation; features indicating the influence of negative pore water (or suction) pressures. Regression analyses also show apparent friction angle to increase with increasing sand contents; a feature attributed to greater inter-locking and resistance to displacement of these particles. It is concluded that the undrained shear strength parameters of saprock are characterized by an average apparent cohesion of 54.6 kPa, and friction angle of 30.5o; the parameters influenced by the degree of saturation as well as clay and sand contents.


2021 ◽  
Vol 43 (2) ◽  
Author(s):  
Binh Thai Pham ◽  
Mahdis Amiri ◽  
Manh Duc Nguyen ◽  
Trinh Quoc Ngo ◽  
Kien Trung Nguyen ◽  
...  

In recent years, machine learning techniques have been developed and used to build intelligent information systems for solving problems in various fields. In this study, we have used Optimized Inference Intelligence System namely ANFIS-PSO which is a combination of Adaptive Neural-Fuzzy Inference System (ANFIS) and Particle Swarm Optimization (PSO) for the estimation of shear strength parameters of the soils (Cohesion “C” and angle of internal friction “φ”). These parameters are required for designing the foundation of civil engineering structures. Normally, shear parameters of soil are determined either in the field or in the laboratory which require time, expertise and equipments. Therefore, in this study, we have applied a hybrid model ANFIS-PSO for quick and cost-effective estimation of shear parameters of soil based on the other six physical parameters namely clay content, natural water content, specific gravity, void ratio, liquid limit and plastic limit. In the model study, we have used data of 1252 soft soil samples collected from the different highway project sites of Vietnam. The data was randomly divided into 70:30 ratios for the model training and testing, respectively. Standard statistical measures: Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and Correlation Coefficient (R) were used for the performance evaluation of the model. Results of the model study indicated that performance of the ANFIS-PSO model is very good in predicting shear parameters of the soil: cohesion (RMSE = 0.075, MAE = 0.041, and R = 0.831) and angle of internal friction (RMSE = 0.08, MAE = 0.058, and R = 0.952).


2002 ◽  
Vol 39 (5) ◽  
pp. 1075-1087 ◽  
Author(s):  
Faten Saihi ◽  
Serge Leroueil ◽  
Pierre La Rochelle ◽  
Ivan French

The role of the degree of microstructure on the behaviour of clayey soils has been the focus of many studies. However, none so far have quantified the evolution of the shear strength parameters for a given soil for degrees of microstructure going from an intact condition to complete remoulding. In the present study, a series of compression triaxial tests have been performed on specimens of the naturally highly structured Saint-Jean-Vianney clay under the following conditions: intact, destructured by straining outside the limit state curve, and reconstituted and reconsolidated after complete remoulding. The results show that the limit state curve is influenced by the level of destructuration reached before testing, and moreover, that the shear strength parameters at large deformation are influenced by the level of destructuration at the beginning of the test. The compression tests infer that the soil seems to retain the memory of its initial microstructure, at least for consolidation volumetric strains up to 14%. The observed behaviour has implications for the understanding and modelling of natural clays; it also explains to some extent the difference in strength parameters used in stability analyses of embankments on soft clays and natural slopes in clay.Key words: clay, microstructure, destructuration, shear strength, large deformation shear strength, triaxial test.


2021 ◽  
Vol 43 (2) ◽  
pp. 189-198
Author(s):  
Binh Thai Pham ◽  
Mahdis Amiri ◽  
Manh Duc Nguyen ◽  
Trinh Quoc Ngo ◽  
Kien Trung Nguyen ◽  
...  

In recent years, machine learning techniques have been developed and used to build intelligent information systems for solving problems in various fields. In this study, we have used Optimized Inference Intelligence System namely ANFIS-PSO which is a combination of Adaptive Neural-Fuzzy Inference System (ANFIS) and Particle Swarm Optimization (PSO) for the estimation of shear strength parameters of the soils (Cohesion “C” and angle of internal friction “φ”). These parameters are required for designing the foundation of civil engineering structures. Normally, shear parameters of soil are determined either in the field or in the laboratory which require time, expertise and equipments. Therefore, in this study, we have applied a hybrid model ANFIS-PSO for quick and cost-effective estimation of shear parameters of soil based on the other six physical parameters namely clay content, natural water content, specific gravity, void ratio, liquid limit and plastic limit. In the model study, we have used data of 1252 soft soil samples collected from the different highway project sites of Vietnam. The data was randomly divided into 70:30 ratios for the model training and testing, respectively. Standard statistical measures: Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and Correlation Coefficient (R) were used for the performance evaluation of the model. Results of the model study indicated that performance of the ANFIS-PSO model is very good in predicting shear parameters of the soil: cohesion (RMSE = 0.075, MAE = 0.041, and R = 0.831) and angle of internal friction (RMSE = 0.08, MAE = 0.058, and R = 0.952).


1979 ◽  
Vol 16 (1) ◽  
pp. 140-151 ◽  
Author(s):  
R. A. Widger ◽  
D. G. Fredlund

A common occurrence in cuts or fills of swelling soils is their reduction in strength with time. At the time of compaction, the clay generally has a high matrix suction. Correspondingly, it has a high strength and will stand at relatively steep side slopes. With time, the soil generally tends towards saturation and the matrix suction reduces towards zero. There is a reduction in total strength and if the gravitational forces are too large, the slope fails.During the past several years, numerous cut and fill slopes have been observed in the Regina area of Saskatchewan. Many of these slopes have remained stable for 4–6 years and then failed. There has been a 20 year history of observations on the Belle Plaine overpass west of Regina. Field and laboratory investigations have been conducted.With a knowledge of the geometry of the slope and failure plane, the simplified Bishop method of stability analysis was used to perform a 'back-analysis' to assess the shear strength parameters. The shear strength parameters from the laboratory program are compared with those calculated from the stability analyses. The analyses indicate that the peak shear strength parameters from triaxial tests on the softened Regina clay (i.e., c' = 5 kPa and [Formula: see text]), with the appropriate pore water pressures, give a factor of safety of 1 for the failed surface. The effect of spring thawing appears to be to produce the condition of most serious pore water pressures.


2019 ◽  
Vol 11 (19) ◽  
pp. 5397 ◽  
Author(s):  
Liang Jia ◽  
Jian Guo ◽  
Yanbin Jiang ◽  
Yong Fu ◽  
Zhidong Zhou ◽  
...  

Loess is a typical collapsible soil, which is widely distributed in the upper and middle areas around the Yellow River of China. The stabilization of loess with lime provides a significant improvement in the physical and the mechanical characteristics of the loess and is therefore widely used in the pavement base and subgrade. Therefore, a systematic investigation of Mohr-Coulomb failure envelope of lime stabilized loess needs to be conducted. In this pursuit, the present research envisages the investigation of the effects of the lime content, porosity and curing time on the strength parameters (friction angle (φ) and cohesion (c)), using a series of triaxial tests performed on lime stabilized loess specimens. The experimental results revealed that the friction angle (φ) was independent of the lime content, the porosity and the curing time of the specimen for a given lime stabilized loess, while the factors mentioned above had a significant effect on the cohesion (c) of the lime stabilized loess. For a relatively short curing time (7 days), the change in the lime content did not present an obvious effect on the cohesion (c) of the stabilized loess. However, when the curing time (28, 90 and 180 days) was longer, the increase of the lime content significantly enhanced the cohesion of the stabilized loess. When the lime content was constant, the cohesion (c) of the stabilized loess increased linearly with the decrease in the void ratio. A power function equation was proposed to assess the comprehensive influences of the factors like the lime content, porosity and curing time on cohesion (c). Finally, the Mohr-Coulomb failure envelopes were drawn based on the triaxial test for 47 specimens with various curing time and confining pressure, and the shear strength parameters obtained by the proposed equation were also compared with the experimental results.


2011 ◽  
Vol 295-297 ◽  
pp. 454-459 ◽  
Author(s):  
Zhen Ying Zhang ◽  
Da Zhi Wu

Basing on the new developed direct shear testing instrument and the tri-axial test instrument with large scale specimen, the shear strength parameters of municipal solid waste has been studied. The municipal solid waste is divided into three parts: the material that is easy to be biodegraded, reinforced material that is difficult to be biodegraded and the incompressible solid waste material. The proportions of these three parts are selected as 80%, 5% and 15%, respectively. A series of laboratory tests have been performed for different initial void ratios, different vertical pressures and different confining pressures applied on the test specimen. Testing results show that the initial void ratio is the main influence factor for the shear strength parameters of the municipal solid waste, the relationship between the shear stress and the shear strain is a strain hardening curve, the shear stress increases gradually with the shear strain. Besides, the principle effective stress increases with the axial strain and the confining pressure in a hardening increasing trend, and the principle effective stress decreases with the increase of the initial void ratio of the municipal solid waste. The shear strength shows a linear relationship to the vertical pressure applied on the test specimen, and it is in accordance with the law of coulomb. According to the testing results of the direct shear test and the tri-axial test, the shear strength parameters are obtained. The cohesion varies from 4.7 to 12.2kPa, and the internal friction angle varies from 14.5 to 28.2 degree.


2013 ◽  
Vol 709 ◽  
pp. 579-582
Author(s):  
Meng Hua Fan

It is difficult to determine the Mohr-Coulomb failure envelope visually, and it is strongly influenced by abnormal test data evaluating the shear strength parameters of soil via trend line and unable to adjust the scope of permissible error. So it is recommended to evaluate shear strength parameters of soil using Solver of Excel for direct shear tests and triaxial tests and you can control the allowable deviation. The mathematics model of nonlinear programming was established to evaluate shear strength parameters of soil from the results of direct shear test and triaxial shear test. The related Excel worksheet was created and the optimum results of the objective function were obtained by setting the Solver parameters dialog box accurately. The method is simple, inexpensive and rapid.


Sign in / Sign up

Export Citation Format

Share Document