Fig 2 - uploaded by Xia-Ting Feng
Content may be subject to copyright.
Source publication
Based on genetic algorithm and genetic programming, a new evolutionary algorithm is developed to evolve mathematical models for predicting the behavior of complex systems. The input variables of the models are the property parameters of the systems, which include the geometry, the deformation, the strength parameters, etc. On the other hand, the ou...
Contexts in source publication
Context 1
... model parameters. One can easily note that these internal model parameters are the coef- ficients of each term of the mathematical expressions. As these coefficients are not yet known, one has to search for the optimal coefficients by employing various means, and the present study uses the genetic algorithm. In a typical genetic algorithm Fig. 2, individuals are either represented by strings of binary digits or with symbols. Each individual is represented by a binary string in the present study. Genetic operators will then work on the bits of the strings to find the best permutation and combination of the bits of a string that defines the characteristic of the individual ...
Context 2
... individual is represented by a binary string in the present study. Genetic operators will then work on the bits of the strings to find the best permutation and combination of the bits of a string that defines the characteristic of the individual solution. As in genetic programming, the operators include repro- duction, crossover, and mutation Fig. ...
Similar publications
A probabilistic dynamic approach is used for the slope stability analysis. In this approach, the effect of both the soil spatial variability and the variability of the Ground-Motion (GM) time history on the dynamic responses (amplification, permanent displacement) are studied and discussed. The soil shear modulus G is considered as an isotropic non...
Citations
... 45 Equations (5)- (8) have been introduced to directly estimate the factor of safety for a dry, homogeneous finite slope ( = 0). Sah et al. 22 and Yang et al. 47 proposed Equations (5) and (6), respectively, considering friction angles less than 45 • and slope angles less than 53 • . Chien and Tsai 16 introduced a simple iterative equation (Equation 7) for calculating the factor of safety under static conditions, utilizing the stability chart concept, considering slope angles between 15 • and 60 • . ...
This paper introduces a novel closed‐form equation (surrogate model) for approximating the Morgenstern–Price estimate of the factor of safety of homogeneous dry finite slopes with circular failure surfaces. Unlike typically used methods, the proposed equation does not require the definition of a critical failure surface, splitting the soil mass into slices, or the iterative reduction of soil resistance to the limit state. It can be easily programmed into calculators or computers and accurately determines the minimum factor of safety based on the shear strength parameters and slope geometry—meaning that it is ideally suited for integration into reliability calculations. The equation is determined parametrically for various soil parameters and slope geometry using the Morgenstern–Price method and compares favorably with conventional techniques, such as slope stability charts, limit equilibrium, and strength reduction methods (SRM). From a practical perspective, the proposed equation greatly simplifies the analysis of the slope stability as the creation of a numerical model is not required and is suited to use in the feasibility stage of a project, for example, for large linear infrastructure projects with differing slope geometries or in situations where a quick assessment is desired.
... An artificial neural network was utilised by [31] to estimate the FOS and slope stability (SS) from 46 slope instances obtained by Sah et al. [32]. FOS was computed employing genetic programming and support vector machines, respectively [33][34]. ...
Slope instability is a widespread environmental concern that affects all geographical regions. It is crucial to consider slope instability in mining, civil, tunnelling, and geotechnical engineering projects. A catastrophic event involving slope instability can lead to severe economic losses, casualties, and property damage. This study introduces the predictive modelling of slope stability using hybrid machine learning approaches. Firstly, a total of 404 events of slope stability were gathered using easily accessible input attributes. Secondly, principal component analysis (PCA) has been applied to reduce the dimension of the slope stability dataset. Thirdly, gaussian mixture model (GMM) was employed to categorize the PCA obtained dataset into distinct clusters. Fourthly, the parameters of extreme gradient boosting (XGBoost) were optimized using whale optimization algorithm (WOA). Lastly, the performance of the suggested model was assessed using several performance indices. The results indicate that the proposed hybrid PCA-GMM based WOA-XGBoost model exhibits the highest level of reliability. The proposed unsupervised-supervised machine learning method using a metaheuristic algorithm technique can considerably reduce slope-related disastrous incidents while rendering mining operations safer and more sustainable.
... On the other hand, data-driven methods, which use statistical and machine learning (ML) methods to develop functional relationships between input and output, have been widely used by researchers to predict slope stability and FS; these methods were mostly applied to small data sets (e.g., Sah et al. 1994;Yang et al. 2004;Sakellariou and Ferentinou 2005;Li and Wang 2010;Das et al. 2011;Manouchehrian et al. 2014;Hoang and Pham 2016;Feng et al. 2018;Lin et al. 2018;Qi and Tang 2018;Zhou et al. 2019;Mahmoodzadeh et al. 2021;Lin et al. 2022). For example, Sah et al. (1994) performed maximum likelihood analysis using data from slope case histories, and empirical equations were developed for the direct estimation of FS. ...
... The database with reported FS values contains 46 case histories of circular failures and 14 case histories of wedge failures. Yang et al. (2004) used genetic algorithms and genetic programming with the same database that Sah et al. (1994) used and developed an improved empirical equation for predicting FS for circular failures. More recently, Manouchehrian et al. (2014) compiled a new database with 103 case histories of circular failures 1 Ph.D. Candidate, Dept. of Civil and Environmental Engineering, Pennsylvania State Univ., University Park, PA 16802. ...
... In this study, the stability charts were digitized to generate FS values and linear interpolation was used to obtain FS values between curves. Yang et al. (2004) developed an empirical equation for the direct calculation of FS values. The equation was developed using genetic algorithms and genetic programming based on 46 case histories of circular failure slopes with a correlation coefficient of 0.927. ...
Slope stability prediction is an important task in geotechnical engineering which can be achieved through physics-based or data-driven approaches. Physics-based approaches rely on geotechnical knowledge from soil mechanics, such as limit equilibrium analysis and shear strength theories, to evaluate the stability condition of slopes, and they are often limited to slope-specific analysis. Data-driven approaches predict slope stability conditions based on learned relationships between influencing factors and slope stability conditions from past observations of slope failures (i.e., case histories); they rely on big data which are difficult to obtain. This study examines three easy-to-implement and effective methods to integrate geotechnical engineering domain knowledge into data-driven models for slope stability prediction: hybrid knowledge-data model, knowledge-based model initiation, and knowledge-guided loss function. These models were benchmarked against pure data-driven models and domain knowledge–based models, including a physics-based solution chart and a physics-based empirical model. A compilation of slope stability case histories from the literature was used as the benchmark database, and five-fold cross-validation was employed to evaluate model performance. The model validation results demonstrated that machine learning models outperformed domain knowledge–based models in terms of several evaluation metrics. The three proposed methods were found to outperform both domain knowledge–based models and pure data-driven models. Additionally, the hybrid knowledge-data models and knowledge-guided loss function were found to reduce discrepancies in the predicted slope stability conditions compared with reported factor-of-safety values, leading to a better alignment with the underlying physics related to slope stability. This study provides an initial assessment of the value of coupling domain knowledge and data-driven methods in geotechnical engineering applications using slope stability prediction as an example.
... (2010), Yang et al. (2004), Sakellariou and Ferentinou (2005), and Sah et al. (1994). The slope geometry properties were the slope height ( ) and the slope angle ( ). ...
Earthwork assets, including cut slopes and embankments, are essential components of the infrastructure supporting road and rail transportation networks. Asset owners must assess the stability of these slopes as they deteriorate, to prevent unwanted slope failures. Assessing the stability of individual earthworks within a portfolio using slope stability analyses can be expensive and time-consuming. Hence, a Bayesian logistic regression model was developed to evaluate the probability of slope failure, using training data from published case histories of slope failures. The Bayesian model was then used to assess the probability of failure for the more specific case of clay cut slopes within a railway earthwork asset portfolio owned by Network Rail (NR). The portfolio includes earthworks at various stages of degraded strength and with different drainage conditions. The results from models with material properties that were equivalent to those for the deteriorated strength of clays compared most closely with clay cut slope failures within the NR dataset. Steeper slopes (>35 degrees) had the highest probability of failure, regardless of the drainage condition. However, for shallower slopes, the poorly-drained slopes had a ≈20% higher probability of failure than the well-drained slopes.
... Lu and Rosenbaum [31] adopted an artificial neural network to estimate the FOS and SS on 46 slope cases collected by Sah et al. [32]. Based on the same database, Samui [33] and Yang et al. [34] used a support vector machine (SVM) and genetic programming to determine FOS, respectively. Amirkiyaei and Ghasemi [35] constructed two tree-based models to assess circular-type failure slopes based on 87 cases. ...
Slope instability can lead to catastrophic consequences. However, predicting slope stability effectively is still challenging because of the complex mechanisms and multiple influencing factors. In recent years, machine learning (ML) has received great attention in slope stability prediction due to its strong nonlinear prediction ability. In this study, an optimum-path forest algorithm based on k-nearest neighbor (OPFk-NN) was used to predict the stability of slopes. First, 404 historical slopes with failure risk were collected. Subsequently, the dataset was used to train and test the algorithm based on randomly divided training and test sets, respectively. The hyperparameter values were tuned by combining ten-fold cross-validation and grid search methods. Finally, the performance of the proposed approach was evaluated based on accuracy, F1-score, area under the curve (AUC), and computational burden. In addition, the prediction results were compared with the other six ML algorithms. The results showed that the OPFk-NN algorithm had a better performance, and the values of accuracy, F1-score, AUC, and computational burden were 0.901, 0.902, 0.901, and 0.957 s, respectively. Moreover, the failed slope cases can be accurately identified, which is highly critical in slope stability prediction. The slope angle had the most important influence on prediction results. Furthermore, the engineering application results showed that the overall predictive performance of the OPFk-NN model was consistent with the factor of safety value of engineering slopes. This study can provide valuable guidance for slope stability analysis and risk management.
... Crossover and mutation operations in genetic algorithm(Yang et al., 2004). ...
In this work, we present a method to optimize the moonpool profile (its dimensions and position in the hull), minimizing water motion inside moonpool, for a specific drillship hull in operation condition, when in head seas (β = 180.0°), for both a regular wave or a random sea. The optimization is important to reduce downtime and increase security when operating by minimization of relative water motion inside moonpool. The optimization algorithm known as Genetic Algorithm (GA) is used with an in-house software created. Results reveal the algorithm ability to find profiles that follows the optimization requirements defined by the user.
... In addition, the crossover and mutation probabilities method were adapted (Xie et al. 2008). Furthermore, due to structural evolution and parameter optimization, a two-stepped self-optimizing method with respect to a genetic algorithm (GA) was studied (Yang et al. 2004). This thesis tried to evaluate the safety factor using Geostudio 2007 program with Bishop's method. ...
The earth dam analysis under the strong seismic load like a destructive earthquake is one of the major topics with respect to the dynamical assessment. Damage control and the structural behaviour during an earthquake is a very important issue for an earthen dam. In this study, a comprehensive review is presented based on literature for dynamic analysis of earth dams. In this context, some significant factors are discussed such as plane stress, plane strain, data monitoring, application of finite-element method or finite-difference method, reinforcement, free vibration analysis, seismic cracks, liquefaction on dams, utilization of shaking table and centrifuge tests based on the small-scale physical modelling in order to validate any numerical analysis. To explain these parameters, case studies are discussed. It is observed that the earth dam structures had the integrated response to increasing the acceleration or displacement at the crest. Consequently, the interaction between the dam and reservoir also the foundation was a very effective factor to establish the nonlinear behaviour. It seems that the reinforced techniques are an essential approach to improve the structural response during an earthquake.
... This is accomplished by the establishment of an input-output relationship for complex systems. Artificial intelligence approaches such as artificial neural networks (ANNs) [7], [8], evolutionary algorithms [9], [10], and support vector machines [11], [12] have been applied to slope stability problems. Li et al. [13] developed an extreme learning neural network technique for the stability evaluation of three-layered soil slopes. ...
Every year, landslides result in immense casualties and considerable financial losses globally. They are classified as one of the most critical categories of natural disasters. Factors such as rainfall and earthquakes can trigger landslides. Generally, practicing engineers use numerical simulations, visual inspections, and in some cases stability charts to assess slopes. However, these techniques are usually not user-friendly for quick assessment of slopes. This study ingeniously creates two recurrent neural network IOS-based mobile applications for the safety assessment of rock slopes. The first App evaluates the safety of slopes considering the earthquake effect, and the second App evaluates the pore water pressure effect on slope safety. Numerical methods were first used to evaluate the stability number of thousands of slope cases considering various geometric and rock mass properties, as well as external factors. The datasets are then employed in the prediction models. The Keras-based RNN models were converted into Core ML formats and then used to develop IOS mobile applications. The Apps can successfully assess the safety of rock slopes while maintaining good accuracy and convenience. Furthermore, the Apps may help reduce future risks and losses associated with landslides by providing quick access to data which can aid early response action.
... In the last few decades, a variety of methods have been developed to solve the uncertainty propagation of slopes based on reliability theory, including the traditional first-order reliability method (FORM) (e.g., Tang 1997, 2004;Low 2007;Cho 2007Cho , 2013Hong and Roh 2008;Ji 2014;Zeng and Jimenez 2014), first-order second moment method (FOSM) (e.g., Christian et al. 1994;Hassan and Wolff 1999;Duncan 2000;Xue and Gavin 2007;Suchomel and Masin 2010), second-order reliability methods (SORM) (e.g., Cho 2009;Low 2014), and Monte Carlo simulation (MCS) method (e.g., El-Ramly et al. 2002Griffiths and Fenton 2004;Hsu and Nelson 2006;Cho 2007Cho , 2010Huang et al. 2010Huang et al. , 2013Tang et al. 2015;Li et al. 2015a) and its advanced variants (e.g., Ching et al. 2009;Wang et al. 2010Wang et al. , 2011Li et al. 2015b). Moreover, there are also many novel or modified methods used to perform the reliability stability analysis of slopes, such as reliability analysis based on seismic displacement (Ji et al. 2020(Ji et al. , 2021 evolutionary algorithms (Yang et al. 2004), artificial neural networks (ANN) (Cho 2009;Shu and Gong 2016), support vector machines (SVM) Zhou et al. 2021), artificial bee colony algorithm (ABC) , Kriging model (Luo et al. 2012a;Yi et al. 2015), response surface methods (e.g., Wong 1985;Xu and Low 2006;Ji and Low 2012;Zhang et al. 2011Zhang et al. , 2013Jiang et al. 2014Jiang et al. , 2015Li and Chu 2015), and simplified HLRF (HasofereLindeRackwitzeFiessler) iterative algorithm (Ji et al. 2018(Ji et al. , 2019. ...
Reliability analysis provides a more effective method for slope stability evaluations and design because it can reflect the uncertainties of slopes. In this study, a generalized probability density evolution method (GPDEM) is proposed to evaluate the system stability reliability of multi-parameters complex slopes. This method is completely different with the traditional random reliability analytical method, which can combine a set of stochastic analysis and currently advanced deterministic slope stability analysis method using finite element method. The proposed method has great adaptability to complex slope cases with implicit perform functions and multiple parametric variables, and can directly reflect the reliability. In addition, a newly Galerkin finite element method based on Streamline-Upwind/Petrov–Galerkin (SUPG) scheme is proposed for the numerical solution of the GPDEM to increase the convergence rates. Several representative study cases of slope system reliability analysis are selected to certify the high precision and validity of GPDEM over the Monte Carlo simulation (MCS) and other simulation methods. The results demonstrate the novel method is promising for geotechnical engineering in terms of precision and efficiency, and can be used to analyze the failure probability of large and complex geotechnical engineering structures.
... Additionally, they sometimes require a well-fitted constitutive model and real mechanical parameters which are difficult to be determined precisely. Recently, soft computing methods have been successfully applied to predict slope stability as a complex, non-linear and multivariate problem (Cheng et al. 2007b;Ercanoglu and Gokceoglu 2002;Fattahi 2017;Gao 2015;Gelisli et al. 2015;Hoang and Pham 2016;Kahatadeniya et al. 2009;Kang et al. 2016Kang et al. , 2017Koopialipoor et al. 2019;Lu and Rosenbaum 2003;McCombie and Wilkinson 2002;Pradhan 2010;Qi and Tang 2018;Rukhaiyar et al. 2018;Saboya Jr et al. 2006;Sakellariou and Ferentinou 2005;Suman et al. 2016;Tun et al. 2016;Wang et al. 2005;Yang et al. 2004;Zolfaghari et al. 2005). Although, soft computing techniques have been successfully employed for prediction of slope stability, the main problem of most these techniques is that they are black box. ...
Slope stability analysis is an enduring research topic in the engineering and academic sectors. Accurate prediction of the factor of safety (FOS) of slopes, their stability and their performance is not an easy task. The current study aims at predicting the FOS on the geometrical and geotechnical input parameters [unit weight (γ), cohesion (C), slope angle (β), height (H), angle of internal friction (φ) and pore pressure ratio (ru)]. The Markov chain Monte Carlo (MCMC) methods have become a ubiquitous tool in Bayesian analysis. This paper implements MCMC methods for Bayesian analysis of models using the WinBUGS package, freely available software. The WinBUGS software is implemented to identify the most appropriate models for estimating the FOS among twenty (20) candidate models that have been proposed. The models were applied to available data given in open source literature. The unknown parameters of the models are considered as random variables. The WinBUGS software which uses Bayesian analysis of complex statistical models and MCMC techniques is employed to compute the posterior predictive distributions. The mean values of the model parameters obtained via MCMC simulations are considered for the model prediction performance evaluation. The performances of the proposed predictive models were examined according to two performance indices, i.e., coefficient of determination (R2) and mean square error. Overall, the results indicate that the proposed FOS model possesses satisfactory predictive performance.
