排序方式： 共有90条查询结果，搜索用时 31 毫秒
71.
Binh Thai Pham Ataollah Shirzadi Dieu Tien Bui Indra Prakash M.B. Dholakia 《国际泥沙研究》2018,33(2):157-170
In this paper, a hybrid machine learning ensemble approach namely the Rotation Forest based Radial Basis Function (RFRBF) neural network is proposed for spatial prediction of landslides in part of the Himalayan area (India). The proposed approach is an integration of the Radial Basis Function (RBF) neural network classifier and Rotation Forest ensemble, which are state-of-the art machine learning algorithms for classification problems. For this purpose, a spatial database of the study area was established that consists of 930 landslide locations and fifteen influencing parameters (slope angle, road density, curvature, land use, distance to road, plan curvature, lineament density, distance to lineaments, rainfall, distance to river, profile curvature, elevation, slope aspect, river density, and soil type). Using the database, training and validation datasets were generated for constructing and validating the model. Performance of the model was assessed using the Receiver Operating Characteristic (ROC) curve, area under the ROC curve (AUC), statistical analysis methods, and the Chi square test. In addition, Logistic Regression (LR), Multi-layer Perceptron Neural Networks (MLP Neural Nets), Naïve Bayes (NB), and the hybrid model of Rotation Forest and Decision Trees (RFDT) were selected for comparison. The results show that the proposed RFRBF model has the highest prediction capability in comparison to the other models (LR, MLP Neural Nets, NB, and RFDT); therefore, the proposed RFRBF model is promising and should be used as an alternative technique for landslide susceptibility modeling. 相似文献
72.
Bui Xuan-Nam Nguyen Hoang Le Hai-An Bui Hoang-Bac Do Ngoc-Hoan 《Natural Resources Research》2020,29(2):571-591
Air over-pressure (AOp) is one of the products of blasting operations for rock fragmentation in open-pit mines. It can cause structural vibration, smash glass doors, adversely affect the surrounding environment, and even be fatal to humans. To assess its dangerous effects, seven artificial intelligence (AI) methods for predicting specific blast-induced AOp have been applied and compared in this study. The seven methods include random forest, support vector regression, Gaussian process, Bayesian additive regression trees, boosted regression trees, k-nearest neighbors, and artificial neural network (ANN). An empirical technique was also used to compare with AI models. The degree of complexity and the performance of the models were compared with each other to find the optimal model for predicting blast-induced AOp. The Deo Nai open-pit coal mine (Vietnam) was selected as a case study where 113 blasting events have been recorded. Indicators used for evaluating model performances include the root-mean-square error (RMSE), determination coefficient (R2), and mean absolute error (MAE). The results indicate that AI techniques provide better performance than the empirical method. Although the relevance of the empirical approach was acceptable (R2?=?0.930) in this study, its error (RMSE?=?7.514) is highly significant to guarantee the safety of the surrounding environment. In contrast, the AI models offer much higher accuracies. Of the seven AI models, ANN was the most dominant model based on RMSE, R2, and MAE. This study demonstrated that AI techniques are excellent for predicting blast-induced AOp in open-pit mines. These techniques are useful for blasters and managers in controlling undesirable effects of blasting operations on the surrounding environment.
相似文献73.
Zhang Xiliang Nguyen Hoang Bui Xuan-Nam Tran Quang-Hieu Nguyen Dinh-An Bui Dieu Tien Moayedi Hossein 《Natural Resources Research》2020,29(2):711-721
Natural Resources Research - Blasting is a useful technique for rocks fragmentation in open-pit mines, underground mines, as well as for civil engineering work. However, the negative impacts of... 相似文献
74.
Fang Qiancheng Nguyen Hoang Bui Xuan-Nam Nguyen-Thoi Trung 《Natural Resources Research》2020,29(2):791-806
Natural Resources Research - In this paper, blast-induced ground vibration (BIGV) was considered as the primary objective, and a new artificial intelligence system was proposed to predict BIGV with... 相似文献
75.
A general thermo-hydro-mechanical framework for the modelling of internal erosion is proposed based on the theory of mixtures applied to two-phase porous media. The erodible soil is partitioned in two phases: one solid phase and one fluid phase. The solid phase is composed of nonerodible grains and erodible particles. The fluid phase is composed of water and fluidized particles. Within the fluid phase, species diffuse. Across phases, species transfer. The modelling of internal erosion is contributed directly by mass transfer from the solid phase towards the fluid phase. The constitutive relations governing the thermomechanical behaviour, generalised diffusion, and transfer are structured by the dissipation inequality. The particular case of soil suffusion is investigated with a focus on constitutive laws. A new constitutive law for suffusion is constructed based on thermodynamic conditions and experimental investigations. This erosion law is linearly related to the power of seepage flow and to the erosion resistance index. Owing to its simplicity, this law tackles the overall trend of the suffusion process and permits the formulation of an analytical solution. This new model is then applied to simulate laboratory experiments, by both analytical and numerical methods. The comparison shows that the newly developed model, which is theoretically consistent, can reproduce correctly the overall trend of the cumulated eroded mass when the permeability evolution is small. In addition, the results are provided for four different materials, two different specimen sizes, and various hydraulic loading paths to demonstrate the applicability of the new proposed law. 相似文献
76.
For research on granular materials, establishing a method to calculate continuum strain from particle displacements is necessary for understanding the material behaviour at macro-level and developing continuum constitutive models. Existing methods are generally based on constructing a mesh or background grid to calculate strain from particle motions. These methods offer rigorous ways to measure strain for granular materials; however, they suffer from several problems such as mesh distortion and lacking grid-to-particle strain mapping procedure, which hinders their capability of calculating strain accumulation during large deformation processes of granular media. To address this issue, this study proposes a new strain calculation method for discrete element simulations of granular materials. This method describes a particle assembly as an equivalent continuum system of material points, each of which corresponds to a particle centre and represents a continuous region with its initial volume/area presumably equal to the volume/area of Voronoi cells generated in accordance with the particle assembly configuration. Smooth Particle Hydrodynamics (SPH) interpolation functions are then employed to calculate strain for these material points. This SPH-based method does not require any mesh or background grid for computation, leading to advantages in calculating strain accumulation under large deformation. Simulations of granular materials in both uniform and heterogeneous gradations were carried out, and strain results obtained by the proposed method indicate good agreements with analytical and numerical solutions. This demonstrates its potential for strain calculations in discrete element simulations of granular materials involving large deformations and/or large displacements. 相似文献
77.
Zhang Xiliang Nguyen Hoang Choi Yosoon Bui Xuan-Nam Zhou Jian 《Natural Resources Research》2021,30(6):4735-4751
Natural Resources Research - Peak particle velocity (PPV) is an important criterion for assessing the risk level of ground vibration induced by mine blasting. Based on this criterion, many efforts... 相似文献
78.
X. S. Zhang H. Wong C. J. Leo T. A. Bui J. X. Wang W. H. Sun Z. Q. Huang 《Geotechnical and Geological Engineering》2013,31(2):479-492
The present paper describes a model of internal erosion of earth structures, based on rigorous thermodynamic principles and the theory of porous media. A particular focus of this paper is concerned with the initial stage of internal erosion, when the pore volume forms a continuous network, without the formation of macroscopic cavities or channels. The continuum approach is applicable in this case. The soil skeleton saturated by a pore fluid is treated as the superposition of three continua in interaction, with independent velocity fields. The pore fluid itself consists of a mixture of water and eroded particles. The erosion kinetics is based on the shear stress developed at the solid–fluid interface. The applicability of the model is illustrated by numerical simulations based on the finite element method. These simulations show how the phenomenon of piping can progressively arise, and preferentially in regions where hydraulic gradients are critical. Effects of mechanical degradations due to internal erosion are at the same time demonstrated. 相似文献
79.
Dieu Tien Bui Binh Thai Pham Quoc Phi Nguyen Nhat-Duc Hoang 《International Journal of Digital Earth》2016,9(11):1077-1097
This study represents a hybrid intelligence approach based on the differential evolution optimization and Least-Squares Support Vector Machines for shallow landslide prediction, named as DE–LSSVMSLP. The LSSVM is used to establish a landslide prediction model whereas the DE is adopted to search the optimal tuning parameters of the LSSVM model. In this research, a GIS database with 129 historical landslide records in the Quy Hop area (Central Vietnam) has been collected to establish the hybrid model. The receiver operating characteristic (ROC) curve and area under the curve (AUC) were used to assess the performance of the newly constructed model. Experimental results show that the proposed model has high performances with approximately 82% of AUCs on both training and validating datasets. The model’s results were compared with those obtained from other methods, Support Vector Machines, Multilayer Perceptron Neural Networks, and J48 Decision Trees. The result comparison demonstrates that the DE–LSSVMSLP deems best suited for the dataset at hand; therefore, the proposed model can be a promising tool for spatial prediction of rainfall-induced shallow landslides for the study area. 相似文献
80.
Dieu Tien Bui Chuyen Trung Tran Biswajeet Pradhan Inge Revhaug Razak Seidu 《国际地球制图》2015,30(2):202-217
The iGeoTrans is an iOS application designed for navigation purposes for iPhone, iPad and iPod Touch. This application uses Global Positioning System (GPS), Assisted GPS system, GLONASS, Wi-Fi and Cellular Network for positioning. The iGeoTrans has included datum transformations and map projections that enable users to convert the collected data between different coordinate systems for almost all areas in the world. In addition, other features are also included such as distance, area measurements, and GPS results could be exported to the AutoCad dxf format for GIS softwares. The average horizontal and vertical root mean square errors (RMSEs) for the static test are around 4.11 and 3.51?m, respectively. The horizontal RMSE for the dynamic outdoor test is around 2.72?m. The iGeoTrans application can be used to support surveying, mapping and geosciences fieldworks for any area in the world. 相似文献