Stability prediction of Himalayan residual soil slope using artificial neural network
- Ray, Arunava, Kumar, Vikash, Kumar, Amit, Rai, Rajesh, Khandelwal, Manoj, Singh, T.
- Authors: Ray, Arunava , Kumar, Vikash , Kumar, Amit , Rai, Rajesh , Khandelwal, Manoj , Singh, T.
- Date: 2020
- Type: Text , Journal article
- Relation: Natural Hazards Vol. 103, no. 3 (2020), p. 3523-3540
- Full Text:
- Reviewed:
- Description: In the past decade, advances in machine learning (ML) techniques have resulted in developing sophisticated models that are capable of modelling extremely complex multi-factorial problems like slope stability analysis. The literature review indicates that considerable works have been done in slope stability using ML, but none of them covers the analysis of residual soil slope. The present study aims to develop an artificial neural network (ANN) model that can be employed for evaluating the factor of safety of Shiwalik Slopes in the Himalayan Region. Data obtained from numerical analysis of a residual soil slope were used to develop two ANN models (ANN1 and ANN2 utilising eleven input parameters, and scaled-down number of parameters based on correlation coefficient, respectively). A four-layer, feed-forward back-propagation neural network having the optimum number of hidden neurons is developed based on trial-and-error method. The results derived from ANN models were compared with those achieved from numerical analysis. Additionally, several performance indices such as coefficient of determination (R2), root mean square error, variance account for, and residual error were employed to evaluate the predictive performance of the developed ANN models. Both the ANN models have shown good prediction performance; however, the overall performance of the ANN2 model is better than the ANN1 model. It is concluded that the ANN models are reliable, valid, and straightforward computational tools that can be employed for slope stability analysis during the preliminary stage of designing infrastructure projects in residual soil slope. © 2020, Springer Nature B.V.
- Authors: Ray, Arunava , Kumar, Vikash , Kumar, Amit , Rai, Rajesh , Khandelwal, Manoj , Singh, T.
- Date: 2020
- Type: Text , Journal article
- Relation: Natural Hazards Vol. 103, no. 3 (2020), p. 3523-3540
- Full Text:
- Reviewed:
- Description: In the past decade, advances in machine learning (ML) techniques have resulted in developing sophisticated models that are capable of modelling extremely complex multi-factorial problems like slope stability analysis. The literature review indicates that considerable works have been done in slope stability using ML, but none of them covers the analysis of residual soil slope. The present study aims to develop an artificial neural network (ANN) model that can be employed for evaluating the factor of safety of Shiwalik Slopes in the Himalayan Region. Data obtained from numerical analysis of a residual soil slope were used to develop two ANN models (ANN1 and ANN2 utilising eleven input parameters, and scaled-down number of parameters based on correlation coefficient, respectively). A four-layer, feed-forward back-propagation neural network having the optimum number of hidden neurons is developed based on trial-and-error method. The results derived from ANN models were compared with those achieved from numerical analysis. Additionally, several performance indices such as coefficient of determination (R2), root mean square error, variance account for, and residual error were employed to evaluate the predictive performance of the developed ANN models. Both the ANN models have shown good prediction performance; however, the overall performance of the ANN2 model is better than the ANN1 model. It is concluded that the ANN models are reliable, valid, and straightforward computational tools that can be employed for slope stability analysis during the preliminary stage of designing infrastructure projects in residual soil slope. © 2020, Springer Nature B.V.
Random finite element method prediction and optimisation for open pit mine slope stability analysis
- Authors: Dyson, Ashley
- Date: 2020
- Type: Text , Thesis , PhD
- Full Text:
- Description: Inherent soil variability can have significant effects on the stability of open-pit mine slopes. In practice, the spatial variability of materials is not commonly considered as a routine component of slope stability analysis. The process of quantifying spatially variable parameters, as well as the modelling of their behaviour is often a complex undertaking. Currently, there are no large-scale commercial software packages containing in-built methods for modelling spatial variability within the Finite Element environment. Furthermore, conventional Limit Equilibrium Methods (LEM) incorporating spatial variability are unable to consider the stress/strain characteristics of these materials. The following research seeks to accurately model the slope mechanics of spatially variable soils, adopting The Random Finite Element Method (RFEM) developed by Griffiths and Fenton (2004) to determine slope failure mechanisms and safety factors. Techniques are developed to produce a set of optimised Random Finite Element Method simulations using the Monte Carlo Method. Additionally, random field analysis techniques are investigated to compare and categorise soil parameter fluctuation, providing a direct relationship between random field properties and slope failure surfaces. Optimisation and analysis techniques are implemented to examine the effects of cross-sectional geometries and input parameter distributions on failure mechanisms, safety factors and probabilities of failure. Cross-sectional RFEM analysis is performed in the Finite Element Method (FEM) software package Abaqus, with the techniques of this research demonstrated for a large open-pit brown coal mine located in the state of Victoria, Australia. The outcome of this research is a comprehensive procedure for optimised RFEM simulation and analysis.
- Description: Doctor of Philosophy
- Authors: Dyson, Ashley
- Date: 2020
- Type: Text , Thesis , PhD
- Full Text:
- Description: Inherent soil variability can have significant effects on the stability of open-pit mine slopes. In practice, the spatial variability of materials is not commonly considered as a routine component of slope stability analysis. The process of quantifying spatially variable parameters, as well as the modelling of their behaviour is often a complex undertaking. Currently, there are no large-scale commercial software packages containing in-built methods for modelling spatial variability within the Finite Element environment. Furthermore, conventional Limit Equilibrium Methods (LEM) incorporating spatial variability are unable to consider the stress/strain characteristics of these materials. The following research seeks to accurately model the slope mechanics of spatially variable soils, adopting The Random Finite Element Method (RFEM) developed by Griffiths and Fenton (2004) to determine slope failure mechanisms and safety factors. Techniques are developed to produce a set of optimised Random Finite Element Method simulations using the Monte Carlo Method. Additionally, random field analysis techniques are investigated to compare and categorise soil parameter fluctuation, providing a direct relationship between random field properties and slope failure surfaces. Optimisation and analysis techniques are implemented to examine the effects of cross-sectional geometries and input parameter distributions on failure mechanisms, safety factors and probabilities of failure. Cross-sectional RFEM analysis is performed in the Finite Element Method (FEM) software package Abaqus, with the techniques of this research demonstrated for a large open-pit brown coal mine located in the state of Victoria, Australia. The outcome of this research is a comprehensive procedure for optimised RFEM simulation and analysis.
- Description: Doctor of Philosophy
Analytical and numerical approaches to evaluate the effect of time-dependent and time-independent soil characteristics on the stability of deep excavations
- Authors: Ghadrdan, Mohsen
- Date: 2021
- Type: Text , Thesis , PhD
- Full Text:
- Description: Excavating the ground for different purposes, such as extracting valuable materials or undertaking urban construction, may cause concerns regarding the stability of the formed slopes, which can affect the environment, the economy, and human lives. Slope stability analysis in large-scale and deep excavations such as open-pit mines is challenging due to uncertainties regarding varying material parameters, complex field conditions and lack of or insufficient data such as pore water pressure distribution, in-situ stress conditions, and discontinuities. Despite different advanced analytical and numerical slope stability techniques having been developed, slope stability analysis may produce unreliable conclusions due to these uncertainties and challenges. This study’s objective is to investigate the effect of different factors associated with slope stability through a case study of the Yallourn brown coal open pit mine in Australia. In this study, the two most common slope stability methods—the Limit Equilibrium Method (LEM) and the Finite Element Method (FEM)—were employed. A comprehensive study was conducted to determine how the generation and dissipation of Negative Excess Pore-Water Pressure (NEPWP) affect slope stability assessments. Additionally, due to the complex geological stratigraphy of the site, different scenarios for geological layering were defined and investigated for the slope stability analyses. Moreover, the sensitivity of the slope stability assessment to not only different material characteristics but also different formulations and assumptions of LEM and FEM are presented.
- Description: Doctor of Philosophy
- Authors: Ghadrdan, Mohsen
- Date: 2021
- Type: Text , Thesis , PhD
- Full Text:
- Description: Excavating the ground for different purposes, such as extracting valuable materials or undertaking urban construction, may cause concerns regarding the stability of the formed slopes, which can affect the environment, the economy, and human lives. Slope stability analysis in large-scale and deep excavations such as open-pit mines is challenging due to uncertainties regarding varying material parameters, complex field conditions and lack of or insufficient data such as pore water pressure distribution, in-situ stress conditions, and discontinuities. Despite different advanced analytical and numerical slope stability techniques having been developed, slope stability analysis may produce unreliable conclusions due to these uncertainties and challenges. This study’s objective is to investigate the effect of different factors associated with slope stability through a case study of the Yallourn brown coal open pit mine in Australia. In this study, the two most common slope stability methods—the Limit Equilibrium Method (LEM) and the Finite Element Method (FEM)—were employed. A comprehensive study was conducted to determine how the generation and dissipation of Negative Excess Pore-Water Pressure (NEPWP) affect slope stability assessments. Additionally, due to the complex geological stratigraphy of the site, different scenarios for geological layering were defined and investigated for the slope stability analyses. Moreover, the sensitivity of the slope stability assessment to not only different material characteristics but also different formulations and assumptions of LEM and FEM are presented.
- Description: Doctor of Philosophy
- «
- ‹
- 1
- ›
- »