A neural network framework for mechanical behavior of unsaturated soils

2003 ◽  
Vol 40 (3) ◽  
pp. 684-693 ◽  
Author(s):  
Ghassem Habibagahi ◽  
Alireza Bamdad
Keyword(s):  
Neural Network ◽  
Mechanical Behavior ◽  
Unsaturated Soils ◽  
Axial Strain ◽  
Volumetric Strain ◽  
Constitutive Law ◽  
Soil Conditions ◽  
Neural Network Approach ◽  
Network Simulations ◽  
Multilayer Perceptron Network

In this paper, a neural network approach is used to describe the mechanical behavior of unsaturated soils. A sequential architecture was chosen for the network, that is, a multilayer perceptron network with feedback capability. The input layer consisted of nine neurons, where six of them represented the initial soil conditions and the remaining three neurons were continuously updated for each increment of axial strain based on outputs from the previous increment. The output layer consisted of three neurons representing values of deviatoric stress, volumetric strain, and change in suction at the end of each increment. Next, a database was developed from triaxial test results available in the literature. The database was used to train and test the network. Neural network simulations were compared with experimental results. The comparison indicates the good performance of the proposed network for predicting the mechanical behavior of unsaturated soils. Moreover, the trained network was employed to simulate other stress paths not present in the database to model the so-called "collapse phenomena." The results were promising.Key words: unsaturated soil, neural network, stress–strain, collapse, modeling, constitutive law.

scholarly journals Measuring unsaturated soil deformations during triaxial testing using a photogrammetry-based method

2016 ◽  
Vol 53 (3) ◽  
pp. 472-489 ◽  
Author(s):  
Lin Li ◽  
Xiong Zhang ◽  
Gang Chen ◽  
Robert Lytton
Keyword(s):  
Unsaturated Soil ◽  
Unsaturated Soils ◽  
Axial Strain ◽  
Volumetric Strain ◽  
3D Models ◽  
Triaxial Tests ◽  
Triaxial Testing ◽  
Distribution Analysis ◽  
Soil Deformation ◽  
Full Field

When characterizing an unsaturated soil using the triaxial test apparatus, it is required to measure the soil deformation during loading. Recently, a photogrammetry-based method has been developed for total and localized volume change measurements on unsaturated soils during triaxial testing. In this study, more in-depth discussions on the photogrammetry-based method are addressed, such as system setup, the measurement procedure, accuracy self-check, data post-processing, and differences from conventional image-based methods. Also, an application of the photogrammetry-based method on unsaturated soil deformation measurements is presented through a series of undrained triaxial tests with different loading paths. After testing, three-dimensional (3D) models of the tested soils at different loading steps were constructed based on the 3D coordinates of measurement targets on the soil surface. Clear barreling processes for soils during deviatoric loading were observed through the constructed 3D models at different axial strain levels. Soil volume changes and volumetric strain nonuniformities during isotropic and deviatoric loadings were extracted based upon detailed analyses of different soil layers. Through a full-field strain distribution analysis, a shear band evolution process was captured for the soil during deviatoric loading at a low confining stress. The photogrammetry-based method proved to be very powerful for in-depth soil deformation characteristics investigation.

Hydromechanical behaviour of overconsolidated unsaturated soil in undrained conditions

2019 ◽  
Vol 56 (11) ◽  
pp. 1609-1621 ◽  
Author(s):  
Shengshen Wu ◽  
Annan Zhou ◽  
Jie Li ◽  
Jayantha Kodikara ◽  
Wen-Chieh Cheng
Keyword(s):  
Effective Stress ◽  
Unsaturated Soils ◽  
Axial Strain ◽  
Triaxial Compression ◽  
Volumetric Strain ◽  
Degree Of Saturation ◽  
Triaxial Tests ◽  
Conventional Triaxial Compression ◽  
Hydromechanical Behaviour ◽  
Undrained Conditions

Hydromechanical behaviour of an unsaturated silt with various suctions and different overconsolidated ratios (OCRs) was investigated through a series of undrained triaxial tests (constant water contents, CW). All the samples were prepared from the slurry state. Different OCRs (= 1, 2, 4, and 8 in net stress) were achieved by unloading the samples to 400, 200, 100, and 50 kPa from an initial confining net pressure of 400 kPa. Then the samples were dried to various suctions (0, 100, 200, 300, and 400 kPa). Unsaturated samples with different OCRs were then sheared at CW conditions following the conventional triaxial compression (CTC) paths. Full hydromechanical responses including the changes in deviator stress, stress ratio, volumetric strain, suction, and degree of saturation with axial strain were monitored and are presented in this paper. Some key findings include (i) the critical state for unsaturated soils with different OCRs can be well defined by Bishop’s effective stress; (ii) the peak strength in Bishop’s effective stress increases with increase of OCR, but decreases with increase of suction in the undrained condition; and (iii) the volume change of unsaturated soils in undrained conditions is related to OCRs and the volume of pore air.

A fuzzy neural network approach for modeling the growth kinetics of FeB and Fe2B layers during the boronizing process

2018 ◽  
Vol 106 (6) ◽  
pp. 603 ◽  
Author(s):  
Bendaoud Mebarek ◽  
Mourad Keddam
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Fuzzy Neural Network ◽  
Treatment Time ◽  
Calculation Model ◽  
Average Error ◽  
Network Approach ◽  
Neural Network Approach ◽  
Fuzzy Neural ◽  
Kinetics Of

In this paper, we develop a boronizing process simulation model based on fuzzy neural network (FNN) approach for estimating the thickness of the FeB and Fe2B layers. The model represents a synthesis of two artificial intelligence techniques; the fuzzy logic and the neural network. Characteristics of the fuzzy neural network approach for the modelling of boronizing process are presented in this study. In order to validate the results of our calculation model, we have used the learning base of experimental data of the powder-pack boronizing of Fe-15Cr alloy in the temperature range from 800 to 1050 °C and for a treatment time ranging from 0.5 to 12 h. The obtained results show that it is possible to estimate the influence of different process parameters. Comparing the results obtained by the artificial neural network to experimental data, the average error generated from the fuzzy neural network was 3% for the FeB layer and 3.5% for the Fe2B layer. The results obtained from the fuzzy neural network approach are in agreement with the experimental data. Finally, the utilization of fuzzy neural network approach is well adapted for the boronizing kinetics of Fe-15Cr alloy.

Assessment of Self-Heating Susceptibility of Indian Coal Seams – A Neural Network Approach

2014 ◽  
Vol 59 (4) ◽  
pp. 1061-1076 ◽  
Author(s):  
D.C. Panigrahi ◽  
S.K. Ray
Keyword(s):  
Neural Network ◽  
Spontaneous Combustion ◽  
Potential Method ◽  
Oxidation Potential ◽  
Wet Oxidation ◽  
Experimental Conditions ◽  
Neural Network Approach ◽  
Indian Coal ◽  
Petrographic Analyses ◽  
Artificial Neural Network Ann

Abstract The paper addresses an electro-chemical method called wet oxidation potential technique for determining the susceptibility of coal to spontaneous combustion. Altogether 78 coal samples collected from thirteen different mining companies spreading over most of the Indian Coalfields have been used for this experimental investigation and 936 experiments have been carried out by varying different experimental conditions to standardize this method for wider application. Thus for a particular sample 12 experiments of wet oxidation potential method were carried out. The results of wet oxidation potential (WOP) method have been correlated with the intrinsic properties of coal by carrying out proximate, ultimate and petrographic analyses of the coal samples. Correlation studies have been carried out with Design Expert 7.0.0 software. Further, artificial neural network (ANN) analysis was performed to ensure best combination of experimental conditions to be used for obtaining optimum results in this method. All the above mentioned analysis clearly spelt out that the experimental conditions should be 0.2 N KMnO4 solution with 1 N KOH at 45°C to achieve optimum results for finding out the susceptibility of coal to spontaneous combustion. The results have been validated with Crossing Point Temperature (CPT) data which is widely used in Indian mining scenario.

A neural network approach to anomaly detection in spectra

1997 ◽  
Author(s):  
Daniel Benzing ◽  
Kevin Whitaker ◽  
Dedra Moore ◽  
Daniel Benzing ◽  
Kevin Whitaker ◽  
...  
Keyword(s):  
Neural Network ◽  
Anomaly Detection ◽  
Network Approach ◽  
Neural Network Approach
Sign in / Sign up

Export Citation Format

Share Document