Search

Preciously assessing the creep mechanical response of sand–geomembrane interfaces is vital for the design of relevant engineering applications, which is inevitable to be influenced by temperature and stress statuses. In this paper, based on the self-developed temperature-controlled large interface shear apparatus, a series of long-term creep shear tests on textured geomembrane–silica sand interfaces in different temperatures, normal pressure, and creep shear pressure were conducted, and a database compiled from the physical creep shear test results is constructed. By adopting the database, three disparate machine learning algorithms of the Back Propagation Artificial Neural Network (BPANN), the Support Vector Machine (SVM) and the Extreme Learning Machine (ELM) were adopted to assess the long-term creep mechanical properties of sand–geomembrane interfaces while also considering the influence of temperature. Then, the forecasting results of the different algorithms was compared and analyzed. Furthermore, by using the optimal machine learning model, sensitivity analysis was carried out. The research indicated that the BPANN model has the best forecasting performance according to the statistics criteria of the Root-Mean-Square Error, the Correlation Coefficient, Wilmot's Index of Agreement, and the Mean Absolute Percentage Error among the developed models. Temperature is the most important influence factor on the creep interface mechanical properties, followed with time. The research findings can support the operating safety of the related engineering facilities installed with the geomembrane. [ABSTRACT FROM AUTHOR]

With the development of data collection and storage capabilities in recent decades, abundant data have been accumulated in geotechnical engineering fields, providing opportunities for the usage of machine learning approaches. Thus, a rising number of scholars are adopting machine learning techniques to settle geotechnical issues. In this paper, the application of three popular machine learning algorithms, support vector machine (SVM), artificial neural network (ANN), and decision tree (DT), as well as other representative algorithms in geotechnical engineering, is reviewed. Meanwhile, the applicability of diverse machine learning algorithms in settling specific geotechnical engineering issues is compared. The main findings are as follows: ANN, SVM, and DT have been widely adopted to solve a variety of geotechnical engineering issues, such as the classification of soil and rock types, predicting the properties of geotechnical materials, etc. Based on the collected relevant research, the performance of random forest (RF) in sorting soil types and assessing landslide susceptibility is satisfying; SVM has high precision in classifying rock types and forecasting rock deformation; and backpropagation ANNs and Hopfield ANNs are recommended to forecast rock compressive strength and soil settlement, respectively. [ABSTRACT FROM AUTHOR]

The presence of internal fissures holds immense sway over the gas permeability of sustainable cement mortar, which in turn dictates the longevity and steadfastness of associated edifices. Nevertheless, predicting the gas permeability of sustainable cement mortar that contains internal cracks poses a significant challenge due to the presence of numerous influential variables and intricate interdependent mechanisms. To solve the deficiency, this research establishes an innovative machine learning algorithm via the integration of the Mind Evolutionary Algorithm (MEA) with the Adaptive Boosting Algorithm-Back Propagation Artificial Neural Network (ABA-BPANN) ensemble algorithm to predict the gas permeability of sustainable cement mortar that contains internal cracks, based on the results of 1452 gas permeability tests. Firstly, the present study employs the MEA-tuned ABA-BPANN model as the primary tool for gas permeability prediction in cement mortar, a comparative analysis is conducted with conventional machine learning models such as Particle Swarm Optimisation Algorithm (PSO) and Genetic Algorithm (GA) optimised ABA-BPANN, MEA optimised Extreme Learning Machine (ELM), and BPANN. The efficacy of the MEA-tuned ABA-BPANN model is verified, thereby demonstrating its proficiency. In addition, the sensitivity analysis conducted with the aid of the innovative model has revealed that the gas permeability of durable cement mortar incorporating internal cracks is more profoundly affected by the dimensions and quantities of such cracks than by the stress conditions to which the mortar is subjected. Thirdly, puts forth a novel machine-learning model, which enables the establishment of an analytical formula for the precise prediction of gas permeability. This formula can be employed by individuals who lack familiarity with machine learning skills. The proposed model, namely the MEA-optimised ABA-BPANN algorithm, exhibits significant potential in accurately estimating the gas permeability of sustainable cement mortar that contains internal cracks in varying stress environments. The study highlights the algorithm's ability to offer essential insights for designing related structures. [ABSTRACT FROM AUTHOR]

The paper proposes a method to simulate the mechanical behavior of compact rock considering hydromechanics by combining physical experiments and numerical analysis. The effectiveness of the constructed method is validated by the comparison between the numerical and physical results of triaxial shear experiments on sandstone in seepage conditions. Based on the validated method, the stability of underground water-sealed oil and gas storage caverns in surrounding compact sandstone during excavation is analyzed. The main findings are as follows: The intrinsic permeability of compact sandstone has a power function relationship with the porosity; the combination of the porous media elastic model and the modified Drucker–Prager plasticity model can preciously represent the mechanical properties of compact sandstone; the proposed method can accurately replicate the hydromechanical response of compact sandstone in seepage conditions; the effects of hydromechanical effects have significant impacts on the stability of surround compact sandstone during the excavation of underground water sealed oil and gas storage caverns, which causes the obvious increase in stress, deformation and plastic deformation zones of the surrounding compact sandstone and remarkable decrease in the stability safety factor. [ABSTRACT FROM AUTHOR]

The peak shear strength of clayey soil-geomembrane interfaces is a vital parameter for the design of relevant engineering infrastructure. However, due to the large number of influence factors and the complex action mechanism, accurate prediction of the peak shear strength for clayey soil-geomembrane interfaces is always a challenge. In this paper, a machine learning model was established by combining Mind Evolutionary Algorithm (MEA) and the ensemble algorithm of Adaptive Boosting Algorithm (ADA)-Back Propagation Artificial Neural Network (BPANN) to predict the peak shear strength of clayey soil-geomembrane interfaces based on the results of 623 laboratory interface direct shear experiments. By comparing with the conventional machine learning algorithms, including Particle Swarm Optimisation Algorithm (PSO) and Genetic Algorithm (GA) tuned ADA-BPANN, MEA tuned Support Vector Machine (SVM) and Random Forest (RF), the superior performance of MEA tuned ADA-BPANN has been validated, with higher predicting precision, shorter training time, and the avoidance of local optimum and overfitting. By adopting the proposed novel model, sensitivity analysis was carried out, which indicates that normal pressure has the largest influence on the peak shear strength, followed by geomembrane roughness. Furthermore, an analytical equation was proposed to assess the peak shear strength that allows the usage of machine learning skills for the practitioners with limited machine learning knowledge. The present research highlights the potential of the MEA tuned ADA-BPANN model as a useful tool to assist in preciously estimating the peak shear strength of clayey soil-geomembrane interfaces, which can provide benefits for the design of relevant engineering applications. • The ensemble artificial intelligence algorithms in predicting the peak shear strength of interfaces is compared. • An analytical equation for estimating the peak shear strength is proposed. • Physical experiments are conducted to validate the effectiveness of the proposed analytical equation. [ABSTRACT FROM AUTHOR]

In this paper, to investigate the impact of environmental loadings on the short-term and creep mechanical characteristics of different types of clayey soil-Geocomposite Drainage Layers (GDL) interfaces, a series of rapid loading and creep shear tests were conducted on Mercia Mudstone Clay-GDL interfaces and Kaolin Clay-GDL interfaces subjected to drying-wetting cycles, thermal cycles and elevated temperature, etc, using a bespoke temperature and stress-controlled large direct shear apparatus. The experimental results indicate that, compared with the original specimens, the interfaces subjected to drying-wetting cycles, thermal cycles and elevated temperature, have lower peak shear strength and creep shear resistance. For example, under 25 kPa normal stress, the peak shear strength of original Mercia Mudstone Clay-GDL interfaces and Kaolin Clay-GDL interfaces falls by 11.91% and 10.11%, respectively, when subjected to 1 drying-wetting cycle. This can be ascribed to the weakening of interlocking effects and skin friction between soil and GDL caused by the softening of drainage core and geotextile fibres of GDL. The peak shear strength of clayey soil-GDL interfaces subjected to one drying-wetting cycle is lower than that subjected to one thermal cycle because of the reduction in the peak shear strength of clayey soil above GDL during drying-wetting cycles. The impact of drying alone on the decrease in the peak shear strength of clayey soil-GDL interfaces during drying cycles with heating is small, and the main influence factor is the elevated temperature. • Rapid loading direct shear tests and creep shear tests on clayey soil -GDL interfaces subjected to environmental loadings were performed. • In-depth understanding of the mechanical responses of clayey soil-GDL interfaces under environmental loadings is demonstrated. • The impacts of environmental factors on the short-term mechanical characteristics of clayey soil-GDL interfaces are analysed. • The impacts of environmental factors on the creep mechanical characteristics of clayey soil-GDL interfaces are analysed. [ABSTRACT FROM AUTHOR]

In this paper, a bespoke stress and temperature controlled direct shear apparatus to test soil-geosynthetics interfaces is introduced. By adopting the apparatus, a series of 'rapid loading' shear tests and creep tests were conducted on the Clay – Geosynthetic Drainage layer (GDL) interfaces to assess the functionality of the apparatus. The experimental results indicate that, the modified apparatus can allow the shear deformation behaviour of soil-geosynthetics interfaces under environmental stress during thermal and drying-wetting cycles to be investigated, with a reliable performance. The resistance of Clay-GDL interfaces to shear deformation under the rapid loading of shear stress decreases after drying-wetting cycle and at elevated temperature. In the creep tests, the interfaces subjected to drying-wetting cycles and thermal cycles fail under a lower shear stress level than that of the interfaces without experiencing drying-wetting cycles and thermal cycles, respectively. The impacts of drying cycles on the horizontal displacement is significantly larger than that of wetting cycles. The first drying cycle has the largest impacts on the horizontal displacement than those of the following drying cycles. The impacts of drying alone on the horizontal displacement of Clay-GDL interfaces during drying cycles are small, and the main influence factor is the elevated temperature. • A bespoke stress and temperature controlled direct shear apparatus on soil-geosynthetics interfaces is introduced. • The performance of the modified apparatus was validated by carrying out repetitive tests. • The shear resistance of Clay-Geosynthetic Drainage Layer interfaces decreases after drying-wetting cycle. • The impacts of drying cycle on the creep horizontal displacement is significantly larger than that of wetting cycle. [ABSTRACT FROM AUTHOR]

In this paper, a database developed from the existing literature about permeability of rock was established. Based on the constructed database, a Support Vector Machine (SVM) model with hyperparameters optimised by Mind Evolutionary Algorithm (MEA) was proposed to predict the permeability of rock. Meanwhile, the Genetic Algorithm- (GA-) and Particle Swarm Algorithm- (PSO-) SVM models were constructed to compare the improving effects of MEA on the foretelling accuracy of machine learning models with those of GA and PSO, respectively. The following conclusions were drawn. MEA can increase the predictive accuracy of the constructed machine learning models remarkably in a few iteration times, which has better optimisation performance than that of GA and PSO. MEA-SVM has the best forecasting performance, followed by PSO-SVM, while the estimating precision of GA-SVM is lower than them. The proposed MEA-SVM model can accurately predict the permeability of rock indicating the model having a satisfactory generalization and extrapolation capacity. [ABSTRACT FROM AUTHOR]

An innovative method is proposed to prepare artificial columnar jointed rock masses (CJRM) with different columnar dip angles, and laboratory physical model tests are conducted to investigate anisotropic permeability and porosity characteristics of the prepared artificial CJRM. In the physical model experiment, permeability and porosity of artificial CJRM with different columnar dip angles is measured during three times cyclic loading and unloading of confinement pressure. Based on the results of the laboratory model tests, the Equivalent Continuum Media Model was applied to analyse anisotropic permeability of CJRM. The main conclusions are summarized as follows. In the first loading phase of confinement pressure, the impacts of confinement pressure on the anisotropic permeability of artificial CJRM, porosity, and the major and minor principle permeability coefficients (PPCs) are significant, while in the following stages of confinement pressure loading and unloading, the change of them is small, with stable value. Permeability of artificial CJRM gradually increases with rise of columnar dip angle, and the permeability anisotropy of artificial CJRM under low confinement pressure is higher than that under low confinement pressure. [ABSTRACT FROM AUTHOR]

In this paper, a method is proposed to prepare rock-like materials with different thicknesses of hidden joints. Then, permeability and porosity of the self-prepared jointed specimens under different pore pressures during confining pressure loading and unloading are measured. The experimental results indicate that the gas permeability of the jointed specimens gradually decreases with the rise of pore pressure due to the existence of Klinkenberg effect, and Klinkenberg effect gradually decreases with the rise of hidden joint thickness. As the main seepage channels, hidden joints govern the seepage characteristics, and due to the existence of hidden joints, the intrinsic permeability is improved significantly. Besides, due to the existence of hidden joints, the intrinsic permeability and porosity are more sensitive to confining pressure loading than that of the intact specimen, and the sensitivity increases with the rise of hidden joint thickness. During confining pressure loading, there is a permanent deformation of the hidden joints and pores in the specimens, which results in both the intrinsic permeability and porosity being always lower than those in the loading process. Meanwhile, the permanent deformation rises with the increases of hidden joint thickness, which leads to the increases of gap of intrinsic permeability and porosity under loading and unloading processes. Additionally, after comparison of the fitting results, the sub-cubic law can reflect the relationship between flow rate and the thickness of non-persistent joints better than the cubic law. [ABSTRACT FROM AUTHOR]

• A method for preparing cement mortar with diverse numbers of internal cracks was proposed. • Permeability and porosity for the samples under diverse stress states were measured. • The stress-dependent permeability and porosity for the prepared samples was analysed. In this paper, gas permeability and porosity for the prepared cement mortar samples with diverse numbers of internal cracks under diverse pore pressure during confining pressure loading and unloading was measured. According to the outcomes of experiments, the following findings were obtained: Klinkenberg correction is appliable to the modification on gas permeability of cement mortar samples containing different number of internal cracks to obtain the intrinsic permeability, with the quadratic equation (Coefficient of Determination R2 is above than 0.92) having a better performance than that of Klinkenberg equation; Owing to the increase in the equivalent pore radius of seepage passages, Klinkenberg Effect of the cement mortar samples reduces when the number of internal cracks rises. When the number of internal cracks rises from 0 to 12, the slippage factor decreases over 90 %; When the number of internal cracks is high, the same changing extent in the number of internal cracks can lead to higher influence on the intrinsic permeability than that when the number of internal cracks is low. The variation magnitude of intrinsic permeability when the number of internal cracks increases from 6 to 12 is around 3–10 times higher than that when the number goes up from 0 to 6; When confining pressure increases, the sensitivity of intrinsic permeability to the changes in confining pressure reduces. The variation magnitude of intrinsic permeability when confining pressure is loaded from 0 MPa to 25 MPa is 5–10 times higher than that when confining pressure is loaded from 25 MPa to 45 MPa; Owing to the permanent deformation of pores and cracks, under the same confining pressure, the intrinsic permeability and porosity during the unloading stage are less than those during the loading stage, respectively; The sub-cubic law (R2 is above than0.90) is able to describe gas seepage in cement mortar specimens with different number of internal cracks more precisely compared to the cubic law. [ABSTRACT FROM AUTHOR]

Monzonitic granite is a low-permeability rock. Monzonitic granite formations are ideal for underground storage of oil due to their low permeability and high mechanical strength. In this study, a series of coupled hydromechanical triaxial tests are carried out using monzonitic granite specimens. The influence of confining and fluid pressures on stress, strain, and permeability is investigated. Failure characteristics under different confining and fluid pressures are discussed based on the analysis of macro fracture planes and micro scanning electron microscopy (SEM). The test results show that the change of permeability with stress and strain reflects the deformation stages of compaction, compression, crack propagation, coalesce, and failure of cracks. Due to the low porosity, the change of permeability is small in the initial phases of compaction and compression, whereas there is a significant increase in permeability when new cracks start to develop and coalesce. Confining pressures have a significant impact on the strength and permeability, particularly the crack damage stress of the rock. Compared with confining pressure, the effect of fluid pressure on rock strength and crack damage stress is small. For the monzonitic granite specimens tested, changing the confining pressure results in different failure modes, whereas the fluid pressure has a relatively small effect on the failure modes. [ABSTRACT FROM AUTHOR]