Summary
A comparative study of optimization techniques for identifying soil parameters in geotechnical engineering was first presented. The identification methodology with its 3 main parts, error ...function, search strategy, and identification procedure, was introduced and summarized. Then, current optimization methods were reviewed and classified into 3 categories with an introduction to their basic principles and applications in geotechnical engineering. A comparative study on the identification of model parameters from a synthetic pressuremeter and an excavation tests was then performed by using 5 among the mostly common optimization methods, including genetic algorithms, particle swarm optimization, simulated annealing, the differential evolution algorithm and the artificial bee colony algorithm. The results demonstrated that the differential evolution had the strongest search ability but the slowest convergence speed. All the selected methods could reach approximate solutions with very small objective errors, but these solutions were different from the preset parameters. To improve the identification performance, an enhanced algorithm was developed by implementing the Nelder‐Mead simplex method in a differential algorithm to accelerate the convergence speed with strong reliable search ability. The performance of the enhanced optimization algorithm was finally highlighted by identifying the Mohr‐Coulomb parameters from the 2 same synthetic cases and from 2 real pressuremeter tests in sand, and ANICREEP parameters from 2 real pressuremeter tests in soft clay.
This study adopts the Bayesian neural network (BNN) integrated with a strong non-linear fitting capability and uncertainty, which has not previously been used in geotechnical engineering, to propose ...a modelling strategy in developing prediction models for soil properties. The compression index C
c
and undrained shear strength s
u
of clays are selected as examples. Variational inference (VI) and Monte Carlo dropout (MCD), two theoretical frameworks for solving and approximating BNN, respectively, are employed and compared. The results indicate that the BNN focused on identifying patterns in datasets, and the predicted C
c
and s
u
show excellent agreement with the actual values. The reliability of the predicted results using BNN is high in the area of dense datasets. In contrast, the BNN demonstrates low reliability in the predicted result in the area of sparse datasets. Additionally, a novel parametric analysis method in combination with the cumulative distribution function is proposed. The analysis results indicate that the BNN-based models are capable of capturing the relationships of input parameters to the C
c
and s
u
. BNN, with its strong prediction capability and reliable evaluation, therefore, shows great potential to be applied in geotechnical design.
Fractured media have been extensively studied due to their significant impact on hydraulic properties of subsurface systems. However, accurately modeling and simulating flow and transport in complex ...3D fractured media still remains a challenge. For this purpose, this work aims to develop a new 3D modeling approach and investigate flow and mass transport in fractured media. First, a modeling approach is presented for generating 3D complex structures and high quality finite element grids. This approach allows for the presence of a range of complex geometries, including curved fracture, multiple fractures and the coexistence of fracture‐inclusions. The resulting models and grids are of high quality, enabling accurate simulation and analysis of complex systems. Furthermore, stress‐dependent aperture and roughness are integrated in the computational scheme using Barton–Bandis law. The Galerkin finite element method is used for numerical discretization, then pressure and concentration are calculated in a unified formulation. Later, numerical tests are performed to analyze the role of 3D fractures in flow and mass transport. Simulation results show that fractures have a larger impact on pressure distribution and flow rate compared to inclusions. Fracture roughness increases the aperture then the effective conductivity is improved as well. Curved fractures may reduce flow rate more than planar fractures due to the tortuosity effect. The variation of equivalent permeability tensor is analyzed with varying orientation, roughness, and number of fractures. The impact of stress and fracture roughness causes a variation of fracture permeability and a high pressure gradient on the fracture‐matrix interface, resulting in different patterns of concentration evolution. Overall, this investigation provides insights into the role of 3D fractures in subsurface flow and transport, with implications for various applications.
The olfactory organ of vertebrates receives chemical cues present in the air or water and, at the same time, they are exposed to invading pathogens. Nasal-associated lymphoid tissue (NALT), which ...serves as a mucosal inductive site for humoral immune responses against antigen stimulation in mammals, is present also in teleosts. IgT in teleosts is responsible for similar functions to those carried out by IgA in mammals. Moreover, teleost NALT is known to contain B-cells and teleost nasal mucus contains immunoglobulins (Igs). Yet, whether nasal B cells and Igs respond to infection remains unknown. We hypothesized that water-borne parasites can invade the nasal cavity of fish and elicit local specific immune responses. To address this hypothesis, we developed a model of bath infection with the Ichthyophthirius multifiliis (Ich) parasite in rainbow trout, Oncorhynchus mykiss, an ancient bony fish, and investigated the nasal adaptive immune response against this parasite. Critically, we found that Ich parasites in water could reach the nasal cavity and successfully invade the nasal mucosa. Moreover, strong parasite-specific IgT responses were detected in the nasal mucus, and the accumulation of IgT+ B-cells was noted in the nasal epidermis after Ich infection. Strikingly, local IgT+ B-cell proliferation and parasite-specific IgT generation were found in the trout olfactory organ, providing new evidence that nasal-specific immune responses were induced locally by a parasitic challenge. Overall, our findings suggest that nasal mucosal adaptive immune responses are similar to those reported in other fish mucosal sites and that an antibody system with a dedicated mucosal Ig performs evolutionary conserved functions across vertebrate mucosal surfaces.
Summary
In this paper, an enhanced backtracking search algorithm (so‐called MBSA‐LS) for parameter identification is proposed with two modifications: (a) modifying the mutation of original ...backtracking search algorithm (BSA) considering the contribution of current best individual for accelerating convergence speed and (b) novelly incorporating an efficient differential evolution (DE) as local search for improving the quality of population. The proposed MBSA‐LS is first validated with better performance than the original BSA and some other typical state‐of‐the‐art optimization algorithms on a benchmark of soil parameter identification in terms of effectiveness, efficiency, and robustness. Then, the efficiency of the MBSA‐LS is further illustrated by two representative cases: identifying soil parameters from both laboratory tests and field measurements. All comparisons demonstrate that the proposed MBSA‐LS algorithm can give accurate results in a short time. Finally, to conveniently solve the problems of parameter identification, a practical tool ErosOpt for parameter identification is developed by integrating the proposed MBSA‐LS and some other efficient algorithms for readers to conduct the parameter identification using optimisation algorithms.
It will be practically useful to know the mechanical properties of granular materials by only taking a photo of particles. This study attempts to deal with this challenge by developing a novel deep ...learning-based modelling strategy. In this strategy, the convolutional neural network (CNN) as image identification algorithm is first used to extract the particle information (particle size distribution PSD and morphology) based on the image of a granular sample, and the bidirectional long short-term memory (BiLSTM) neural network is employed to train the model of reproducing mechanical behaviours and induced fabric evolutions of the sample with corresponding particle information. The datasets of images of samples are generated using discrete element method, and the datasets of mechanical properties together with fabric evolutions are obtained through numerical tests on corresponding samples. As a preliminary attempt, two-dimensional biaxial samples and tests with initially isotropic fabric are considered for the sake of simplicity. The feasibility and reliability of the proposed modelling strategy are evaluated through training and testing. All results indicate that the first part of the model based on CNN is capable of accurately identifying PSD of a granular sample, as well as circularity and roundness of particles, using which as connecting parameters the mechanical behaviours together with induced fabric evolutions of granular materials are subsequently well captured by the second part of the model based on BiLSTM. This study provides a basis and a possible way to obtain immediately particle and packing information, mechanical properties and fabric evolutions by leveraging images of granular materials.
•A modelling framework from images of particles to mechanical properties was proposed.•CNN was employed to identify particle size distribution and particle morphology.•Mechanical behaviours and induced fabric anisotropy evolution were modelled using BiLSTM.
Machine learning (ML) may provide a new methodology to directly learn from raw data to develop constitutive models for soils by using pure mathematic skills. It has presented success and versatility ...in cases of simple stress paths due to its strong non-linear mapping capacity without limitations of constitutive formulations. However, current studies on the ML-based constitutive modeling of soils is still very limited. This study comprehensively reviews the application of ML algorithms in the development of constitutive models of soils and compares the performance of different ML algorithms. First, the basic principles of typical ML algorithms used in describing soil behaviors are briefly elaborated. The main characteristics and the limitations of such ML algorithms are summarized and compared. Then, the methodology of developing a ML-based soil model is reviewed from six aspects, such as adopted ML algorithms, data source, framework of the ML-based model, training strategy, generalization ability and application scope. Finally, five new ML-based models are developed using five typical ML algorithms (i.e. BPNN, RBF, LSTM, GRU and BiLSTM that can predict multi outputs together) based on same set of experimental results of sand, and compare each other in terms of the predictive accuracy and generalization ability. Results show the long short-term memory (LSTM) neural network and its variants are most suitable for developing constitutive models. Moreover, some useful suggestions for developing the ML-based soil model are also provided for the community.
Abstract
In order to clarify the micro‐mechanics of clay during compression, the behavior of clay subjected to one‐dimensional compression is investigated at the particle scale using discrete element ...method (DEM). The flaky clay particles in the simulation are approximated by clumps made of spheres. A new contact model is implemented to account for the double‐layer repulsive force, the van der Waals attractive force and the mechanical contact force. The effect of sphere arrangement in the particle clump is discussed. The DEM model is validated against experimental observations in terms of macroscopic compressibility, particle dip angle as well as the over consolidated behavior. The
e
‐log
σ
v
curve shows a concave‐to‐linear shape. The evolution of dip angle of clay particles indicates that particles tend to have an anisotropy with a preferential orientation towards horizontal direction. The increase of preconsolidation pressure decreases the initial compressibility due to the increase the number of mechanical contacts. The evolution of average coordination and sphere‐sphere contact shows that the majority of mechanical contacts are generated before the compressive stress reaches 100 kPa. Evolution of soil fabric is presented and discussed.
Uncertainty is a commonplace and significant issue in geotechnical engineering. Unlike conventional statistical and machine learning methods, this study presents a novel approach to correlating soil ...properties that takes uncertainty into account using an artificial neural network with Monte Carlo dropout (ANN_MCD). An uncertainty model for two important soil properties, creep index Cα, and hydraulic conductivity k, that control the long‐term performance of geotechnical structures is proposed in a function of three soil physical properties using ANN_MCD. Evaluation of the accuracy, uncertainty, and monotonicity of the predicted results for both Cα and k reveals the excellent performance of the proposed model, which is used to simulate the long‐term settling and excess pore pressure of an embankment on soft clays. The predicted results show good agreement with observations, within a 95% confidence interval. All results indicate that the proposed ANN_MCD‐based modelling approach can be used to rapidly correlate soil properties with an uncertainty evaluation and can be further combined with numerical modelling to analyze an engineering‐scale problem and conduct risk assessment.
PDF
