Coal pillar assessment is of broad importance to underground engineering structure, as the pillar failure can lead to enormous disasters. Because of the highly non-linear correlation between the pillar failure and its influential attributes, conventional forecasting techniques cannot generate accurate outcomes. To approximate the complex behavior of coal pillar, this paper elucidates a new idea to forecast the underground coal pillar stability using combined unsupervised-supervised learning. In order to build a database of the study, a total of 90 patterns of pillar cases were collected from authentic engineering structures. A state-of-the art feature depletion method, t-distribution symmetric neighbor embedding (t-SNE) has been employed to reduce significance of actual data features. Consequently, an unsupervised machine learning technique K-mean clustering was followed to reassign the t-SNE dimensionality reduced data in order to compute the relative class of coal pillar cases. Following that, the reassign dataset was divided into two parts: 70 percent for training dataset and 30 percent for testing dataset, respectively. The accuracy of the predicted data was then examined using support vector classifier (SVC) model performance measures such as precision, recall, and f₁-score. As a result, the proposed model can be employed for properly predicting the pillar failure class in a variety of underground rock engineering projects.

Present study computes the ultimate bearing capacity of an embedded strip footing situated on the rock slope subjected to seismic loading. Influences of embedment depth of strip footing, horizontal seismic acceleration coefficient, rock slope angle, Geological Strength Index, normalized uniaxial compressive strength of rock mass, disturbance factor, and Hoek-Brown material constant are studied in detail. To perform the analysis, the lower bound finite element limit analysis method in combination with the semidefinite programming is utilized. From the results of the present study, it can be found that the magnitude of the bearing capacity factor reduces quite substantially with an increment in the seismic loading. In addition, with the increment in slope angle, further reduction in the value of the bearing capacity factor is observed. On the other hand, with an increment in the embedment depth, an increment in the value of the bearing capacity factor is found. Stress contours are presented to describe the combined failure mechanism of the footing-rock slope system in the presence of static as well as seismic loadings for the different embedment depths.

The mechanical properties of expansive soil are very unstable, highly sensitive to water, and thus easy to cause major engineering accidents. In this paper, the expansive soil foundation pit project of the East Huada Square in the eastern suburb of Chengdu was studied, the moisture content of the expansive soil was considered as an important factor that affecting the mechanics properties of expansive soil and the stability of the non-equal-length double-row piles in the foundation pit support. Three groups of direct shear tests were carried out and the quantitative relationships between the moisture content and shear strength τ, cohesion c, internal friction angle φ were obtained. The effect of cohesion and internal friction angle on the maximum displacement and the maximum bending moment of piles were analyzed by the finite element software MIDAS/GTS (Geotechnical and Tunnel Analysis System). Results show that the higher the moisture content, the smaller the matrix suction, and the smaller the shear strength; the cohesion and the internal friction angle are exponentially related to the moisture content, and both are negatively correlated. The maximum displacement and the maximum bending moment of the non-equal length double-row piles decrease with the increase of the cohesion and the internal friction angle. When the cohesion is greater than 33 kPa or the internal friction angle is greater than 25.5°, the maximum displacement and maximum bending moment of the piles are relatively small, however, once crossing the points (the corresponding moisture content value is 24.4%), the maximum displacement and the maximum bending moment will increase significantly. Therefore, in order to ensure the stability and safety of the foundation pit support structure of the East Huada Square, the moisture content of the expansive soil should not exceed 24.4%.

This study proposes a method to analyze the distribution of coal porosity disturbances after the excavation of ultra-large-diameter water jet boreholes using a coal wetting and softening model. The high-pressure jet is regarded as a short-term high-pressure water injection process. The water injection range is the coal softening range. The time when the reference point of the borehole wall is shocked by the high-pressure water column is equivalent to the time of high-pressure water injection of the coal wall. The influence of roadway excavation with support and borehole diameter on the ultra-large-diameter jet drilling excavation is also studied. The coal core around the borehole is used to measure the gas permeability for determining the porosity disturbance distribution of the coal in the sampling plane to verify the correctness of the simulation results. Results show that the excavation borehole is beneficial to the expansion of the roadway excavation disturbance, and the expansion distance of the roadway excavation disturbance has a quadratic relationship with the borehole diameter. Wetting and softening of the coal around the borehole wall will promote the uniform distribution of the overall porosity disturbance and reduce the amplitude of disturbance fluctuations.

The urbanization and increasing rate of population demands effective means of transportation system (basement and tunnels) as well as high-rise building (resting on piled foundation) for accommodation. Therefore, it unavoidable to construct basements (i.e., excavation) nearby piled foundation. Since the basement excavation inevitably induces soil movement and stress changes in the ground, it may cause differential settlements to nearby piled raft foundation. To understand settlement and load transfer mechanism in the piled raft due to excavation-induced stress release, numerical parametric studies are carried out in this study. The effects of excavation depths (i.e., formation level) relative to piled raft were investigated by simulating the excavation near the pile shaft (i.e., H_e/L_p=0.67), next to (H_e/L_p=1.00) and below the pile toe (H_e/L_p=1.33). In addition, effects of sand density and raft fixity condition were investigated. The computed results have revealed that the induced settlement, tilting, pile lateral movement and load transfer mechanism in the piled raft depends upon the embedded depth of the diaphragm wall. Additional settlement of the piled raft due to excavation can be account for apparent loss of load carrying capacity of the piled raft (ALPC). The highest apparent loss of piled raft capacity ALPC (on the account of induced piled raft settlement) of 50% was calculated in in case of H_e/L_p = 1.33. Furthermore, the induced settlement decreased with increasing the relative density from 30% to 90%. On the contrary, the tilting of the raft increases in denser ground. The larger bending moment and lateral force was induced at the piled heads in fixed and pinned raft condition.

Kriging metamodel, as a flexible machine learning method for approximating deterministic analysis models of an engineering system, has been widely used for efficiently estimating slope reliability in recent years. However, the autocorrelation function (ACF), a key input to Kriging that affects the accuracy of reliability estimation, is usually selected based on empiricism. This paper proposes an adaption of the Kriging method, named as Genetic Algorithm optimized Whittle-Matérn Kriging (GAWMK), for addressing this issue. The non-classical two-parameter Whittle-Matérn (WM) function, which can represent different ACFs in the Matérn family by controlling a smoothness parameter, is adopted in GAWMK to avoid subjectively selecting ACFs. The genetic algorithm is used to optimize the WM model to adaptively select the optimal autocorrelation structure of the GAWMK model. Monte Carlo simulation is then performed based on GAWMK for a subsequent slope reliability analysis. Applications to one explicit analytical example and two slope examples are presented to illustrate and validate the proposed method. It is found that reliability results estimated by the Kriging models using randomly chosen ACFs might be biased. The proposed method performs reasonably well in slope reliability estimation.

This paper presents a study regarding the influence of various water levels on the characteristics of subgrade mud pumping through a self-developed test instrument. The characteristics of mud pumping are primarily reflected by axial strain, excess pore water pressure, and fine particle migration. The results show that the axial strain increases nonlinearly with an increase in cycles number; however, the increasing rate gradually decreases, thus, an empirical model for calculating the axial strain of the samples is presented. The excess pore water pressure increases rapidly first and then decreases slowly with an increase in cycles number. Furthermore, the dynamic stress within the soil first rapidly decreases and then eventually slows. The results indicate that the axial strain, excess pore water pressure, and the height and weight of the migrated fine particles decrease significantly with a low water level. In this study, when the water level is 50 mm lower than the subgrade soil surface, the issue of subgrade mud pumping no longer exist.

This study characterizes Proctor and geophysical properties in a broad range of grading and fines contents. The results show that soil index properties such as uniformity and fines plasticity control the optimum water content and peak dry unit trends, as well as elastic wave velocity. The capillary pressure at a degree of saturation less than S = 20% plays a critical role in determining the shear wave velocity for poorly graded sandy soils. The reduction in electrical resistivity with a higher water content becomes pronounced as the water phase is connected A parallel set of compaction and geophysical properties of sand-kaolinite mixtures reveal that the threshold boundaries computed from soil index properties adequately capture the transitions from sand-controlled to kaolinite-controlled behavior. In the transitional fines fraction zone between F_F ≈ 20 and 40%, either sand or kaolinite or both sand and kaolinite could dominate the geophysical properties and all other properties associated with soil compaction behavior. Overall, the compaction and geophysical data gathered in this study can be used to gain a first-order approximation of the degree of compaction in the field and produce degree of compaction maps as a function of water content and fines fraction.