Modeling time-dependent mechanical behavior of hard rock considering excavation-induced damage and complex 3D stress states

To investigate the long-term stability of deep rocks,a three-dimensional(3D)time-dependent model that accounts for excavation-induced damage and complex stress state is developed.This model comprises three main components:a 3D viscoplastic isotropic constitutive relation that considers excavation damage and complex stress state,a quantitative relationship between critical irreversible deformation and complex stress state,and evolution characteristics of strength parameters.The proposed model is implemented in a self-developed numerical code,i.e.CASRock.The reliability of the model is validated through experiments.It is indicated that the time-dependent fracturing potential index(xTFPI)at a given time during the attenuation creep stage shows a negative correlation with the extent of excavationinduced damage.The time-dependent fracturing process of rock demonstrates a distinct interval effect of the intermediate principal stress,thereby highlighting the 3D stress-dependent characteristic of the model.Finally,the influence of excavation-induced damage and intermediate principal stress on the time-dependent fracturing characteristics of the surrounding rocks around the tunnel is discussed.

Effect of slope angle on fractured rock masses under combined influence of variable rainfall infiltration and excavation unloading

Intense precipitation infiltration and intricate excavation processes are crucial factors that impact the stability and security of towering and steep rock slopes within mining sites.The primary aim of this research was to investigate the progression of cumulative failure within a cracked rock formation,considering the combined effects of precipitation and excavation activities.The study was conducted in the Huangniuqian eastern mining area of the Dexing Copper Mine in Jiangxi Province,China.An engineering geological investigation was conducted,a physical model experiment was performed,numerical calculations and theoretical analysis were conducted using the matrix discrete element method(Mat-DEM),and the deformation characteristics and the effect of the slope angle of a fractured rock mass under different scenarios were examined.The failure and instability mechanisms of the fractured rock mass under three slope angle models were analyzed.The experimental results indicate that as the slope angle increases,the combined effect of rainfall infiltration and excavation unloading is reduced.A novel approach to simulating unsaturated seepage in a rock mass,based on the van Genuchten model(VGM),has been developed.Compared to the vertical displacement observed in a similar physical experiment,the average relative errors associated with the slope angles of 45,50,and 55were 2.094%,1.916%,and 2.328%,respectively.Accordingly,the combined effect of rainfall and excavation was determined using the proposed method.Moreover,the accuracy of the numerical simulation was validated.The findings contribute to the seepage field in a meaningful way,offering insight that can inform and enhance existing methods and theories for research on the underlying mechanism of ultra-high and steep rock slope instability,which can inform the development of more effective risk management strategies.

Rockburst criterion and evaluation method for potential rockburst pit depth considering excavation damage effect

Excavation-induced disturbances in deep tunnels will lead to deterioration of rock properties and formation of excavation damaged zone(EDZ).This excavation damage effect may affect the potential rockburst pit depth.Taking two diversion tunnels of Jinping II hydropower station for example,the relationship between rockburst pit depth and excavation damage effect is first surveyed.The results indicate that the rockburst pit depth in tunnels with severe damage to rock masses is relatively large.Subsequently,the excavation-induced damage effect is characterized by disturbance factor D based on the Hoek-Brown criterion and wave velocity method.It is found that the EDZ could be further divided into a high-damage zone(HDZ)with D=1 and weak-damage zone(WDZ),and D decays from one to zero linearly.For this,a quantitative evaluation method for potential rockburst pit depth is established by presenting a three-element rockburst criterion considering rock strength,geostress and disturbance factor.The evaluation results obtained by this method match well with actual observations.In addition,the weakening of rock mass strength promotes the formation and expansion of potential rockburst pits.The potential rockburst pit depth is positively correlated with HDZ and WDZ depths,and the HDZ depth has a significant contribution to the potential rockburst pit depth.

Evaluation of slope stability through rock mass classification and kinematic analysis of some major slopes along NH-1A from Ramban to Banihal, North Western Himalayas

The network of Himalayan roadways and highways connects some remote regions of valleys or hill slopes,which is vital for India’s socio-economic growth.Due to natural and artificial factors,frequency of slope instabilities along the networks has been increasing over last few decades.Assessment of stability of natural and artificial slopes due to construction of these connecting road networks is significant in safely executing these roads throughout the year.Several rock mass classification methods are generally used to assess the strength and deformability of rock mass.This study assesses slope stability along the NH-1A of Ramban district of North Western Himalayas.Various structurally and non-structurally controlled rock mass classification systems have been applied to assess the stability conditions of 14 slopes.For evaluating the stability of these slopes,kinematic analysis was performed along with geological strength index(GSI),rock mass rating(RMR),continuous slope mass rating(CoSMR),slope mass rating(SMR),and Q-slope in the present study.The SMR gives three slopes as completely unstable while CoSMR suggests four slopes as completely unstable.The stability of all slopes was also analyzed using a design chart under dynamic and static conditions by slope stability rating(SSR)for the factor of safety(FoS)of 1.2 and 1 respectively.Q-slope with probability of failure(PoF)1%gives two slopes as stable slopes.Stable slope angle has been determined based on the Q-slope safe angle equation and SSR design chart based on the FoS.The value ranges given by different empirical classifications were RMR(37-74),GSI(27.3-58.5),SMR(11-59),and CoSMR(3.39-74.56).Good relationship was found among RMR&SSR and RMR&GSI with correlation coefficient(R 2)value of 0.815 and 0.6866,respectively.Lastly,a comparative stability of all these slopes based on the above classification has been performed to identify the most critical slope along this road.

Numerical analysis of downward progressive landslides in long natural slopes with sensitive clay

Landslides occurring in sensitive clay often result in widespread destruction,posing a significant risk to human lives and property due to the substantial decrease in undrained shear strength during deformation.Assessing the consequences of these landslides is challenging and necessitates robust numerical methods to comprehensively investigate their failure mechanisms.While studies have extensively explored upward progressive landslides in sensitive clays,understanding downward progressive cases remains limited.In this study,we utilised the nodal integration-based particle finite element method(NPFEM)with a nonlinear strain-softening model to analyse downward progressive landslides in sensitive clay on elongated slopes,induced by surcharge loads near the crest.We focused on elucidating the underlying failure mechanisms and evaluating the effects of different soil parameters and strainsoftening characteristics.The simulation results revealed the typical pattern for downward landslides,which typically start with a localised failure in proximity to the surcharge loads,followed by a combination of different types of failure mechanisms,including single flow slides,translational progressive landslides,progressive flow slides,and spread failures.Additionally,inclined shear bands occur within spread failures,often adopting distinctive ploughing patterns characterised by triangular shapes.The sensitive clay thickness at the base,the clay strength gradient,the sensitivity,and the softening rate significantly influence the failure mechanisms and the extent of diffused displacement.Remarkably,some of these effects mirror those observed in upward progressive landslides,underscoring the interconnectedness of these phenomena.This study contributes valuable insights into the complex dynamics of sensitive clay landslides,shedding light on the intricate interplay of factors governing their behaviour and progression.

Effects of freeze-thaw cycles on sandstone in sunny and shady slopes

A growing rock engineering activity in cold regions is facing the threat of freeze-thaw(FT)weathering,especially in high mountains where the sunny-shady slope effects strongly control the difference in weathering behavior of rocks.In this paper,an investigation of the degradation of petrophysical characteristics of sandstone specimens subjected to FT cycle tests to simulate the sunny-shady slope effects is presented.To this aim,non-destructive and repeatable testing techniques including weight,ultrasonic waves,and nuclear magnetic resonance methods on standard specimens were performed.For the sunny slope specimens,accompanied by the enlargement of small pores,100 FT cycles caused a significant decrease in P-wave velocity with an average of 23%,but a consistent rise of 0.18%in mass loss,34%in porosity,67%in pore geometrical mean radius,and a remarkable 14.5-fold increase in permeability.However,slight changes with some abnormal trends in physical parameters of the shady slope specimens were observed during FT cycling,which can be attributed to superficial granular disaggregation and pore throat obstruction.Thermal shocks enhance rock weathering on sunny slopes during FT cycles,while FT weathering on shady slopes is restricted to the small pores and the superficial cover.These two factors are primarily responsible for the differences in FT weathering intensity between sunny and shady slopes.The conclusions derived from the interpretation of the experimental results may provide theoretical guidance for the design of slope-failure prevention measures and the selection of transportation routes in cold mountainous regions.

Numerical Simulation of Surrounding Rock Deformation and Grouting Reinforcement of Cross-Fault Tunnel under Different Excavation Methods

Tunnel construction is susceptible to accidents such as loosening, deformation, collapse, and water inrush, especiallyunder complex geological conditions like dense fault areas. These accidents can cause instability and damageto the tunnel. As a result, it is essential to conduct research on tunnel construction and grouting reinforcementtechnology in fault fracture zones to address these issues and ensure the safety of tunnel excavation projects. Thisstudy utilized the Xianglushan cross-fault tunnel to conduct a comprehensive analysis on the construction, support,and reinforcement of a tunnel crossing a fault fracture zone using the three-dimensional finite element numericalmethod. The study yielded the following research conclusions: The excavation conditions of the cross-fault tunnelarray were analyzed to determine the optimal construction method for excavation while controlling deformationand stress in the surrounding rock. The middle partition method (CD method) was found to be the most suitable.Additionally, the effects of advanced reinforcement grouting on the cross-fault fracture zone tunnel were studied,and the optimal combination of grouting reinforcement range (140°) and grouting thickness (1m) was determined.The stress and deformation data obtained fromon-site monitoring of the surrounding rock was slightly lower thanthe numerical simulation results. However, the change trend of both sets of data was found to be consistent. Theseresearch findings provide technical analysis and data support for the construction and design of cross-fault tunnels.

Subsurface multi-physical characterization of mountain excavation and city construction in loess plateau with a fiber-optic sensing system

Mountain excavation and city construction(MECC)projects being launched in the Loess Plateau in China involve the creation of large-scale artificial land.Understanding the subsurface evolution characteristics of the artificial land is essential,yet challenging.Here,we use an improved fiber-optic monitoring system for its subsurface multi-physical characterization.The system enables us to gather spatiotemporal distribution of various parameters,including strata deformation,temperature,and moisture.Yan’an New District was selected as a case study to conduct refined in-situ monitoring through a 77 m-deep borehole and a 30 m-long trench.Findings reveal that the ground settlement involves both the deformation of the filling loess and the underlying intact loess.Notably,the filling loess exhibits a stronger creep capability compared to underlying intact loess.The deformation along the profile is unevenly distributed,with a positive correlation with soil moisture.Water accumulation has been observed at the interface between the filling loess and the underlying intact loess,leading to a significant deformation.Moreover,the temperature and moisture in the filling loess have reached a new equilibrium state,with their depths influenced by atmospheric conditions measuring at 31 m and 26 m,respectively.The refined investigation allows us to identify critical layers that matter the sustainable development of newly created urban areas,and provide improved insights into the evolution mechanisms of land creation.

Application of excavation compensation method for enhancing stability and efficiency in shallow large-span rock tunnels

Engineering shallow,large-span rock tunnels challenges deformation control and escalates construction costs.This study investigates the excavation compensation method(ECM)and its associated technologies to address these issues.Utilizing five key technologies,the ECM effectively modulates radial stress post-excavation,redistributes stress in the surrounding rock,and eliminates tensile stress at the excavation face.Pre-tensioning measures further enhance the rock’s residual strength,establishing a new stability equilibrium.Field tests corroborate the method’s effectiveness,demonstrating a crown settlement reduction of 3–8 mm,a nearly 50%decrease compared to conventional construction approaches.Additionally,material consumption and construction duration were reduced by approximately 30%–35%and 1.75 months per 100 m,respectively.Thus,the ECM represents a significant innovation in enhancing the stability and construction efficiency of large-span rock tunnels,marking a novel contribution to the engineering field.

Evolution model and failure mechanisms of rainfall-induced cracked red clay slopes:insights from Xinshao County,China

Red clay landslides are widely distributed worldwide,resulting in severe loss of life and property.Although rainfall-induced red clay slopes have received extensive attention,the role of cracks in the evolutionary process of red clay slopes and their connection to failure mechanisms is still poorly understood.A comprehensive approach integrating field investigation,laboratory tests,and numerical simulations was conducted to study the 168 red clay landslides in Xinshao County,China.The results show that red clay is prone to forming cracks at high moisture content due to its low swelling and high shrinkage properties.The failure mode of red clay slopes can be summarized in three stages:crack generation,slope excavation,and slope failure.Furthermore,the retrospective analysis and numerical simulations of the typical landslide in Guanchong indicated that intense rainfall primarily impacts the shallow layer of soil within approximately 0.5 m on the intact slope.However,cracks change the pattern of rainfall infiltration in the slope.Rainwater infiltrates rapidly through the preferential channels induced by the cracks rather than uniformly and slowly from the slope surface.This results in a significant increase in both the depth of infiltration and the saturated zone area of the cracked slope,reaching 3.8 m and 36.2 m^(2),respectively.Consequently,the factor of safety of the slope decreases by 13.4%compared to the intact slope,ultimately triggering landslides.This study can provide valuable insights into understanding the failure mechanisms of red clay slopes in China and other regions with similar geological settings.

Bio-cementation for tidal erosion resistance improvement of foreshore slopes based on microbially induced magnesium and calcium precipitation

In most coastal and estuarine areas,tides easily cause surface erosion and even slope failure,resulting in severe land losses,deterioration of coastal infrastructure,and increased floods.The bio-cementation technique has been previously demonstrated to effectively improve the erosion resistance of slopes.Seawater contains magnesium ions(Mg^(2+))with a higher concentration than calcium ions(Ca^(2+));therefore,Mg^(2+)and Ca^(2+)were used together for bio-cementation in this study at various Mg^(2+)/Ca^(2+)ratios as the microbially induced magnesium and calcium precipitation(MIMCP)treatment.Slope angles,surface strengths,precipitation contents,major phases,and microscopic characteristics of precipitation were used to evaluate the treatment effects.Results showed that the MIMCP treatment markedly enhanced the erosion resistance of slopes.Decreased Mg^(2+)/Ca^(2+)ratios resulted in a smaller change in angles and fewer soil losses,especially the Mg^(2+)concentration below 0.2 M.The decreased Mg^(2+)/Ca^(2+)ratio achieved increased precipitation contents,which contributed to better erosion resistance and higher surface strengths.Additionally,the production of aragonite would benefit from elevated Mg^(2+)concentrations and a higher Ca^(2+)concentration led to more nesquehonite in magnesium precipitation crystals.The slopes with an initial angle of 53°had worse erosion resistance than the slopes with an initial angle of 35°,but the Mg^(2+)/Ca^(2+)ratios of 0.2:0.8,0.1:0.9,and 0:1.0 were effective for both slope stabilization and erosion mitigation to a great extent.The results are of great significance for the application of MIMCP to improve erosion resistance of foreshore slopes and the MIMCP technique has promising application potential in marine engineering.

Deterministic and probabilistic analysis of great-depth braced excavations:A 32 m excavation case study in Paris

The Fort d’Issy-Vanves-Clamart(FIVC)braced excavation in France is analyzed to provide insights into the geotechnical serviceability assessment of excavations at great depth within deterministic and probabilistic frameworks.The FIVC excavation is excavated at 32 m below the ground surface in Parisian sedimentary basin and a plane-strain finite element analysis is implemented to examine the wall deflections and ground surface settlements.A stochastic finite element method based on the polynomial chaos Kriging metamodel(MSFEM)is then proposed for the probabilistic analyses.Comparisons with field measurements and former studies are carried out.Several academic cases are then conducted to investigate the great-depth excavation stability regarding the maximum horizontal wall deflection and maximum ground surface settlement.The results indicate that the proposed MSFEM is effective for probabilistic analyses and can provide useful insights for the excavation design and construction.A sensitivity analysis for seven considered random parameters is then implemented.The soil friction angle at the excavation bottom layer is the most significant one for design.The soil-wall interaction effects on the excavation stability are also given.

Stability of bedded rock slopes subjected to hydro-fluctuation and associated strength deterioration

Reservoir-induced earthquakes(RIEs)occur frequently in the Three Gorges Reservoir Area(TGRA)and the rock mass strength of the hydro-fluctuation belt(HFB)deteriorates severely due to the reservoirinduced seismic loads.Three models of typical bedded rock slopes(BRSs),i.e.gently(GIS),moderately(MIS),and steeply(SIS)inclined slopes,were proposed according to field investigations.The dynamic response mechanism and stability of the BRSs,affected by the rock mass deterioration of the HFB,were investigated by the shaking table test and the universal distinct element code(UDEC)simulation.Specifically,the amplification coefficient of the peak ground acceleration(PGA)of the slope was gradually attenuated under multiple seismic loads,and the acceleration response showed obvious“surface effect”and“elevation effect”in the horizontal and vertical directions,respectively.The“S-type”cubic function and“steep-rise type”exponential function were used to characterize the cumulative damage evolution of the slope caused by microseismic waves(low seismic waves)and high seismic waves,respectively.According to the dynamic responses of the acceleration,cumulative displacement,rock pressure,pore water pressure,damping ratio,natural frequency,stability coefficient,and sliding velocity of the slope,the typical evolution processes of the dynamic cumulative damage and instability failure of the slope were generalized,and the numerical and experimental results were compared.Considering the dynamic effects of the slope height(SH),slope angle(SA),bedding plane thickness(BPT),dip angle of the bedding plane(DABP),dynamic load amplitude(DLA),dynamic load frequency(DLF),height of water level of the hydro-fluctuation belt(HWLHFB),degradation range of the hydro-fluctuation belt(DRHFB),and degradation shape of the hydro-fluctuation belt(DSHFB),the sensitivity of factors influencing the slope dynamic stability using the orthogonal analysis method(OAM)was DLA>DRHFB>SA>SH>DLF>HWLHFB>DSHFB>DABP>BPT.

Design and Construction of Automatic Monitoring System for Open-pit Coal Mine Slopes

[Objectives]To monitor the stability of open-pit coal mine slopes in real time and ensure the safety of coal mine production.[Methods]The automatic monitoring system of coal mine slope was explored in depth,and the core functions of the system were designed comprehensively.According to the design function of the automatic monitoring system,the slope automatic monitoring system was constructed.Besides,in accordance with the actual situation of the slope,the monitoring frequency of slopes was set scientifically,and the key indicators such as rainfall,deep displacement and surface displacement of the slopes were monitored in an all-round and multi-angle way.[Results]During the monitoring period,the overall condition of the slope remained good,and no landslides or other geological disasters occurred.At the same time,the overall rainfall in the slope area remained low.In terms of monitoring data,the horizontal displacement and settlement of the slopes increased first and then tended to be stable.Specifically,the maximum horizontal displacement during the monitoring period was 22.74 mm,while the maximum settlement was 18.65 mm.[Conclusions]The automatic slope monitoring system has obtained remarkable achievements in practical application.It not only improves the accuracy and efficiency of slope stability monitoring,but also provides valuable reference experience for similar projects.

Dynamic damage evolution of bank slopes with serrated structural planes considering the deteriorated rock mass and frequent reservoirinduced earthquakes

To investigate the dynamic damage evolution characteristics of bank slopes with serrated structural planes,the shaking table model test and the numerical simulation were utilized.The main findings indicate that under continuous seismic loads,the deformation of the bank slope increased,particularly around the hydro-fluctuation belt,accompanying by the pore water pressure rising.The soil pressure increased and then decreased showed dynamic variation characteristics.As the undulation angle of the serrated structural planes increased(30°, 45°, and 60°),the failure modes were climbing,climbinggnawing,and gnawing respectively.The first-order natural frequency was used to calculate the damage degree(Dd)of the bank slope.During microseisms and small earthquakes,it was discovered that the evolution of Dd followed the“S”shape,which was fitted by a logic function.Additionally,the quadratic function was used to fit the Dd during moderately strong earthquakes.Through the numerical simulation,the variation characteristics of safety factors(Sf)for slopes with serrated structural planes and slopes with straight structural planes were compared.Under continuous seismic loads,the Sf of slopes with straight structural planes reduce stalely,whereas the Sf for slopes with serrated structural planes was greater than the former and the reduction rate was increasing.

A method to interpret fracture aperture of rock slope using adaptive shape and unmanned aerial vehicle multi-angle nap-of-the-object photogrammetry

The aperture of natural rock fractures significantly affects the deformation and strength properties of rock masses,as well as the hydrodynamic properties of fractured rock masses.The conventional measurement methods are inadequate for collecting data on high-steep rock slopes in complex mountainous regions.This study establishes a high-resolution three-dimensional model of a rock slope using unmanned aerial vehicle(UAV)multi-angle nap-of-the-object photogrammetry to obtain edge feature points of fractures.Fracture opening morphology is characterized using coordinate projection and transformation.Fracture central axis is determined using vertical measuring lines,allowing for the interpretation of aperture of adaptive fracture shape.The feasibility and reliability of the new method are verified at a construction site of a railway in southeast Tibet,China.The study shows that the fracture aperture has a significant interval effect and size effect.The optimal sampling length for fractures is approximately 0.5e1 m,and the optimal aperture interpretation results can be achieved when the measuring line spacing is 1%of the sampling length.Tensile fractures in the study area generally have larger apertures than shear fractures,and their tendency to increase with slope height is also greater than that of shear fractures.The aperture of tensile fractures is generally positively correlated with their trace length,while the correlation between the aperture of shear fractures and their trace length appears to be weak.Fractures of different orientations exhibit certain differences in their distribution of aperture,but generally follow the forms of normal,log-normal,and gamma distributions.This study provides essential data support for rock and slope stability evaluation,which is of significant practical importance.

Investigation of the block toppling evolution of a layered model slope by centrifuge test and discrete element modeling

Primary toppling usually occurs in layered rock slopes with large anti-dip angles.In this paper,the block toppling evolution was explored using a large-scale centrifuge system.Each block column in the layered model slope was made of cement mortar.Some artificial cracks perpendicular to the block column were prefabricated.Strain gages,displacement gages,and high-speed camera measurements were employed to monitor the deformation and failure processes of the model slope.The centrifuge test results show that the block toppling evolution can be divided into seven stages,i.e.layer compression,formation of major tensile crack,reverse bending of the block column,closure of major tensile crack,strong bending of the block column,formation of failure zone,and complete failure.Block toppling is characterized by sudden large deformation and occurs in stages.The wedge-shaped cracks in the model incline towards the slope.Experimental observations show that block toppling is mainly caused by bending failure rather than by shear failure.The tensile strength also plays a key factor in the evolution of block toppling.The simulation results from discrete element method(DEM)is in line with the testing results.Tensile stress exists at the backside of rock column during toppling deformation.Stress concentration results in the fragmented rock column and its degree is the most significant at the slope toe.

Dynamic response and failure process of horizontal-layered fractured structure rock slope under strong earthquake

Rock slope with horizontal-layered fractured structure(HLFS)has high stability in its natural state.However,a strong earthquake can induce rock fissure expansion,ultimately leading to slope failure.In this study,the dynamic response,failure mode,and spectral characteristics of rock slope with HLFS under strong earthquake conditions were investigated based on the large-scale shaking table model test.On this basis,multiple sets of numerical calculation models were further established by UDEC discrete element program.Five influencing factors were considered in the parametric study of numerical simulations,including slope height,slope angle,bedding-plane spacing and secondary joint spacing as well as bedrock dip angle.The results showed that the failure process of rock slope with HLFS under earthquake action is mainly divided into four phases,i.e.,the tensile crack of the slope shoulder joints and shear dislocation at the top bedding plane,the extension of vertical joint cracks and increase of shear displacement,the formation of step-through sliding surfaces and the instability,and finally collapse of fractured rock mass.The acceleration response of slopes exhibits elevation amplification effect and surface effect.Numerical simulations indicate that the seismic stability of slopes with HLFS exhibits a negative correlation with slope height and angle,but a positive correlation with bedding-plane spacing,joint spacing,and bedrock dip angle.The results of this study can provide a reference for seismic stability evaluation of weathered rock slopes.

Predicting the friction angle of clays using a multi-layer perceptron neural network enhanced by yeo-johnson transformation and coral reefs optimization

The accurate prediction of the friction angle of clays is crucial for assessing slope stability in engineering applications.This study addresses the importance of estimating the friction angle and presents the development of four soft computing models:YJ-FPA-MLPnet,YJ-CRO-MLPnet,YJ-ACOC-MLPnet,and YJCSA-MLPnet.First of all,the Yeo-Johnson(YJ)transformation technique was used to stabilize the variance of data and make it more suitable for parametric statistical models that assume normality and equal variances.This technique is expected to improve the accuracy of friction angle prediction models.The friction angle prediction models then utilized multi-layer perceptron neural networks(MLPnet)and metaheuristic optimization algorithms to further enhance performance,including flower pollination algorithm(FPA),coral reefs optimization(CRO),ant colony optimization continuous(ACOC),and cuckoo search algorithm(CSA).The prediction models without the YJ technique,i.e.FPA-MLPnet,CRO-MLPnet,ACOC-MLPnet,and CSA-MLPnet,were then compared to those with the YJ technique,i.e.YJ-FPA-MLPnet,YJ-CRO-MLPnet,YJ-ACOC-MLPnet,and YJ-CSA-MLPnet.Among these,the YJ-CRO-MLPnet model demonstrated superior reliability,achieving an accuracy of up to 83%in predicting the friction angle of clay in practical engineering scenarios.This improvement is significant,as it represents an increase from 1.3%to approximately 20%compared to the models that did not utilize the YJ transformation technique.

Reliability analysis of slope stability by neural network,principal component analysis,and transfer learning techniques

The prediction of slope stability is considered as one of the critical concerns in geotechnical engineering.Conventional stochastic analysis with spatially variable slopes is time-consuming and highly computation-demanding.To assess the slope stability problems with a more desirable computational effort,many machine learning(ML)algorithms have been proposed.However,most ML-based techniques require that the training data must be in the same feature space and have the same distribution,and the model may need to be rebuilt when the spatial distribution changes.This paper presents a new ML-based algorithm,which combines the principal component analysis(PCA)-based neural network(NN)and transfer learning(TL)techniques(i.e.PCAeNNeTL)to conduct the stability analysis of slopes with different spatial distributions.The Monte Carlo coupled with finite element simulation is first conducted for data acquisition considering the spatial variability of cohesive strength or friction angle of soils from eight slopes with the same geometry.The PCA method is incorporated into the neural network algorithm(i.e.PCA-NN)to increase the computational efficiency by reducing the input variables.It is found that the PCA-NN algorithm performs well in improving the prediction of slope stability for a given slope in terms of the computational accuracy and computational effort when compared with the other two algorithms(i.e.NN and decision trees,DT).Furthermore,the PCAeNNeTL algorithm shows great potential in assessing the stability of slope even with fewer training data.