Stability Prediction of Residual Soil and Rock Slope Using Artificial Neural Network

Paliwal, Mahesh; Goswami, Himkar; Ray, Arunava; Bharati, Ashutosh Kumar; Rai, Rakesh; Khandelwal, Manoj

doi:10.1155/2022/4121193

Cited by 8 publications

(7 citation statements)

References 28 publications

(34 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results are compromising and the ANN model approximated the factor of safety close to the actual values. In their research on slope stability risk analysis, Prashant K. Nayak et al ( 2020) (Paliwal et al, 2022) noted that it is crucial for every mining engineer to offer a reasonable slope safety factor. The study area's slope face has been separated into cells in this work, each with a homogeneous aspect, a slope angle, rock characteristics, and joint set orientations.…”

Section: Hybrid Approachmentioning

confidence: 99%

Estimation of slope stability using ensemble-based hybrid machine learning approaches

Ragam,

Kushal Kumar,

Ajith

et al. 2024

Front. Mater.

View full text Add to dashboard Cite

Mining is one of the most daunting occupations gain the sector since it entails risk at any point in the operation. In its operation, the main focus is on slope stability. To avoid slope failures, work should be performed in line with both the regulations and the safety criteria. Slope stability is essential in mining activities owing to slope failure putting productivity and safety at risk. Prediction of slope failure is difficult because of the complexity of traditional engineering techniques. Through study, recent technologies have helped mining companies predict slope problems quickly and effectively. In this current research, an ensemble of machine learning intelligence algorithms was used to estimate and assess the Factor of Safety (FOS). In Ostapal Chromicte Mine, India, 79 experimental and failure slope occurrences were tracked to gather in-the-moment field data. The available data were split into training and testing sets at random to build algorithms. The five influenced factors such as the unit weight, the friction angle, the cohesiveness, the mining depth, as well as the slope angle used as input variables to estimate the FOS. Selected machine learning techniques such as Multiple Linear Regression (MLR), Decision Tree, Random Forest (RF), eXtreme Gradient Boosting (XGBoost) and ensemble hybrid model combining eXtreme Gradient Boosting and Random Forest (XGBoost-RF) were developed to evaluate the FOS. The validity and efficiency of created models can be evaluated using standard evaluation parameters such as coefficient of determination (R2), root mean square error (RMSE), mean square error (MSE), normalized root mean square error (NRMSE), mean absolute percentage error (MAPE) and mean absolute deviation (MAD). The most precise model to assess the FOS across all models was discovered to be the XGBOOST-RF ensemble model, which had a high R2 of 0.931, MSE of 0.009, NRMSE of 0.069, MAD of 0.037, MAPE of 3.581 and an RMSE of 0.098.

show abstract

Section: Hybrid Approachmentioning

confidence: 99%

Estimation of slope stability using ensemble-based hybrid machine learning approaches

Ragam,

Kushal Kumar,

Ajith

et al. 2024

Front. Mater.

View full text Add to dashboard Cite

show abstract

“…Gupta et al [18] used the graph method combined with rock microstructure analysis to analyze the stability of cutting slopes. Paliwal et al [19] coded artificial neural network algorithms and developed an Android application to instantly predict the stability of residual soil and the rock slope. Ngapouth et al [20] used a combination of geometric, kinematic, and seismic methods to analyze the stability of cut slopes affected by falling particles and block settlement.…”

Section: Introductionmentioning

confidence: 99%

Stability Analysis of an Unstable Slope in Chongqing Based on Multiple Analysis Methods

Li¹,

Hu³

et al. 2023

Processes

View full text Add to dashboard Cite

The failure of an unstable slope has the characteristics of sudden disaster, rapid sliding speed, and a wide range of influence. This study selected an unstable slope in Chongqing as the evaluation object, divided it into the strong-deformation zone and weak-deformation zone, and analyzed its formation mechanism and deformation failure mode. Macroscopic qualitative analysis was processed by the geological exploration method, the slope stability and the sliding thrust were quantitatively analyzed by the limit equilibrium method, and the sensitivity analysis was calculated and conducted on its shear strength parameters by laboratory tests and a field large shear test. The historical formation process of the slope was deduced, and suggestions for the prevention and control of unstable slopes were proposed. Studies show that the deformation mechanism of an unstable slope is a push type, its deformation is mainly concentrated in the southern area of the rear edge, and the width of the slope ground tensile crack is 1~30 cm, with a visible depth of 3~30 mm and an extension of 3~12 m. The shear strength of potential sliding zone soil in the weak-deformation zone is: cpw = 35.70 kPa, φpw = 14.80°, and in the strong-deformation zone it is: cps = 32.54 kPa, φps = 13.54°. The results show that the formation of a steep cliff by the artificial mining of sandstone is the main cause of slope deformation, the action of groundwater is the main triggering factor for slope deformation, and the inclined rock mass at the front edge is the key block for the deformation. The strong-deformation zone of the slope is in an unstable state under rainstorm, and the weak-deformation zone of the slope is basically-stable under rainstorm. Unstable slopes are prone to slide during a rainstorm period, which threatens the lives and properties of the residents and road traffic safety around the slope. The research results provide an important theoretical basis and data support for the accurate judgment and stability analysis of instability failure modes and for the further effective prevention and control of unstable slopes.

show abstract

“…Geophysical Problems and Possible Solutions in Soil Classification Based on Eurocode 8 were discussed (15). Artificial neural networks have previously been used to predict the stability of soil and rock slope (16), to estimate the consolidation coefficient (17), to predict the swelling strength of large soils (18) and to estimate rock tension using deep neural networks (19).…”

Section: Introductionmentioning

confidence: 99%

Site Classification using Feed Forward Backpropagation Artificial Neural Networks

Efeoğlu

2023

IJMSIT

View full text Add to dashboard Cite

Strong rock is less affected by the waves propagating during an earthquake. For this reason, structures on strong rocks are less affected by earthquakes. Identifying strong rocks is important for a safe residential area. There are different earthquake codes declaring the characteristics of strong rocks. In this study, site classification was made according to four different earthquake Provisions Nehrp, TBDY, Rm, E code. Feed Forward Backpropagation Artificial Neural Networks was used for site classification. Shear wave velocity (V30), Ground dominant period (To) and H/V ratio were selected as input parameters to this network. Performance analysis was performed to determine which regulation of the Feed Forward Backpropagation Artificial Neural Networks algorithm made the classification more successful. The cross-validation method was used for the analysis. Accuracy, Precision Recall, Kappa, Area under the ROC Curve (AUC) and Root Mean Squared Error (RMS) error values were calculated. As a result, 98% accuracy value was obtained after cross validation in strong rock detection according to E-Code-8 regulation. According to this regulation, all metric values calculated in strong rock detection are higher than other regulations. In addition, hard rock was detected with the least error rate according to this regulation.

show abstract

Stability Prediction of Residual Soil and Rock Slope Using Artificial Neural Network

Cited by 8 publications

References 28 publications

Estimation of slope stability using ensemble-based hybrid machine learning approaches

Estimation of slope stability using ensemble-based hybrid machine learning approaches

Stability Analysis of an Unstable Slope in Chongqing Based on Multiple Analysis Methods

Site Classification using Feed Forward Backpropagation Artificial Neural Networks

Contact Info

Product

Resources

About