This paper proposes a new hybrid deep neural network and optimization approach for stochastic vibration analysis of graphene platelets reinforced functionally graded triply periodic minimal surface (GPLR-FG-TPMS) microplates with material properties uncertainties. A combination of the bidirectional long short-term memory model (BiLSTM), the Shrimp and Goby Association Search Algorithm (SGA) and Chebyshev

The clay filling layer can significantly influences the shear behavior of rock joints. In this study, a numerical model for the direct shear test on clay-rich filling rock masses under constant normal stress was developed using the Continuum Discontinuum Element Method (CDEM), and validated through compression-shear experiments. Subsequently, the influence mechanism of water content and various normal

The moving least squares (MLS) based numerical manifold method (abbreviated as MLS-NMM) inherits the individual merits of MLS and NMM, which not only gets rid of the shackles of meshes but also can unitedly solve both continuity and discontinuity problems. This paper presents an improved MLS-NMM model for saturated-unsaturated seepage in both homogeneous and heterogeneous porous media. In the improved

In this paper, a novel hybrid contact detection algorithm, AGS (Adaptive grid-based search) & GJK (Gilbert-Johnson-Keerthi), is proposed to accelerate 2D FDEM (Combined finite-discrete element method) simulations. AGS algorithm maintains computational efficiency comparable to traditional broad search methods based on uniform grid decomposition, while significantly reducing memory consumption by utilizing

Perfusion bioreactors involve the continuous flow of culture medium through the scaffold. While sophisticated experimental setups exist for measuring flow parameters, a deep understanding of the three-dimensional (3D) flow throughout a scaffold mounted in a bioreactor can be accomplished via computational methods. The flow in a bioreactor is characterized by low Reynold numbers and can be modeled as

In this paper, a meshless finite point method (FPM) is proposed to solve a class of parabolic differential equation of neutral delay. By using difference techniques and Taylor expansions in time, a second-order accurate time semi-discrete system is established for the neutral delay initial–boundary value problem. Then, by combining the moving least squares approximation and the collocation technique

In the Local Method of Fundamental Solutions (LMFS), the selection of parameters {Ri}i=1∗, representing the radii of circle-type source points of each local approximation domain is crucial for the accuracy and stability of the algorithm. Traditionally, all the Ri are set to be a same constant which can be determined through a trial-and-error process (TRP). This process is always inflexible and not

In the traditional method of fundamental solutions (MFS), the selection of the sources is the most crucial task. Despite numerous studies dedicated to addressing this challenge, it remains an open problem. By introducing the physics-informed neural networks to automatically determine the optimal distribution of source points, this paper proposes a novel adaptive method of fundamental solutions (AMFS)

Modelling the production dynamics of fractured shale reservoirs remains a complex task, particularly when characterizing the connectivity of matrix, hydraulic fractures, and natural fractures during production simulation. This study aims to predict the production of non-planar hydraulic fractures in deep fractured shale reservoirs. An integrated numerical model for hydraulic fracturing and development

The randomness in structural parameters of printed circuit heat exchangers (PCHEs) is unavoidable and can significantly impact shakedown limit and reliability. However, studies on the influence of random structural parameters are limited due to the expensive computation burden. Therefore, this paper aims to achieve efficient stochastic shakedown and reliability analyses of PCHEs with multiple random

Electromagnetic slot models are employed to efficiently simulate electromagnetic penetration through openings in an otherwise closed electromagnetic scatterer. Such models, which incorporate varying assumptions about the geometry of the openings, are typically coupled with electromagnetic surface integral equations that model electromagnetic scattering. In this paper, we introduce novel code-verification

This paper proposes the fatigue crack growth modelling of three-dimensional geometries with the eXtended Isogeometric Boundary Element Method (XIGABEM). The formulation combines the advantages of the dual Boundary Element Method (BEM), the isogeometric approach, and an enrichment strategy for surfaces containing the crack front. The dual BEM approach relies on a boundary-only mesh, eliminating a re-meshing

This study investigates the numerical solution of the Kuramoto–Tsuzuki equation in one, two and three dimensions. To effectively handle the equation’s nonlinear component, we employ a splitting technique, while the linear component is addressed using the Crank–Nicolson method for temporal discretization. Spatial discretization is achieved through the generalized finite difference method with a convergence

This paper extends the inclusion-based boundary element method (iBEM) to conduct elastodynamic analysis of chain-structured composites with aligned spherical inhomogeneities and predict the effective material properties depending on the frequency and specimen-particle size ratio (SPR). The iBEM algorithm utilizes boundary integral equations to handle the boundary conditions of the specimen. Using Eshelby’s

Various applications are related to the plane-wave scattering by an obstacle near the interface between two different kinds of isotropic and homogeneous media. The analysis of such a problem asks for an efficient numerical method. To this end, this study proposes a scattering matrix method for evaluating scattering fields by acoustically rigid scatterers with arbitrary shapes. The basic idea is to

A disaster is a severe event that occurs on a short period but has highly damaging and long-lasting effects on society. Disasters can be broadly categorized into natural and man-made events. Among natural disasters, floods are some of the most common disaster. As climate change accelerates, floods are expected to become more frequent and severe, highlighting the need for a deeper understanding of their

Numerical simulation is an important approach for chemical laser investigation. However, it is time-consuming and prone to numerical divergence because of the system's complexity and strong nonlinearity. This paper develops a deep learning encoding underlying physics method for modeling chemical oxygen-iodine lasers (COIL). Two classes of DeepONets are proposed to capture the nonlinear relationships

We present a computationally efficient Python algorithm based on the Boundary Element Method (BEM) for frictionless linear elastic axisymmetric contact of coated solids. The algorithm solves indentation problems using conical, spherical, and cylindrical flat indenters, with results also reported for flat punch indentation on a soft-coated substrate. To validate BEM, we implement Finite Element Method

This paper presents a novel application of compactly supported radial basis functions (CSRBFs) within a local meshfree framework to solve two-dimensional coupled partial differential equations, including the Burgers’ equation (2D-CVBE) and the Saint Venant system (2D-SVS), also known as the shallow water equations. By integrating CSRBFs with the method of lines (CSRBF-MOL), this approach provides a

Accurately simulating acoustic wave propagation is crucial for seismic exploration and acoustic imaging. Traditional numerical methods often struggle to balance accuracy and computational efficiency, particularly when applied to heterogeneous media. The multiquadric radial basis function (MQRBF)-FD method offers flexibility in handling irregular geometries but encounters difficulties in selecting optimal

When a structure moves uniformly at high-speed, the structural-acoustic coupling significant alters the acoustic field distribution compared to conditions without coupling. We propose a hybrid numerical method combining the finite element method (FEM) for structural vibration and the convective boundary element method (BEM) for sound propagation in uniform flow to predict the acoustic field of a uniformly

The behaviour of fractured rocks under quasi-dynamic loads significantly influences the stability of rock engineering projects under dynamic disturbances. To account for strain rate effects, new rate-dependent contact models were proposed in this study. Then, numerical models of fractured rocks were generated for quasi-dynamic simulations under uniaxial compression, aiming to investigate the impacts

Traditional laboratory methods for determining rock internal friction angles are costly, time-intensive, and limited by core sample quality, yet few studies address this in oil and gas drilling contexts. This research introduces a groundbreaking machine learning framework to predict offshore downhole internal friction angles, leveraging data from the East China Sea’s Xihu Sag. Using four algorithms

Tumor treating fields (TTFields) is a promising non-invasive cancer treatment that uses alternating electric fields to disrupt tumor cell division. Despite its potential, there is a significant lack of precise and reliable methods for evaluating the efficacy of TTFields in clinical settings. The aim of this study is to develop and validate a new method for real-time assessment of the efficacy of TTFields

This study develops a two-dimensional time-domain boundary element method to address the acoustic coupling in vortex-sound interaction phenomena, specifically for geometries with impedance boundary conditions. To ensure compatibility with the two-dimensional time-domain boundary integral equation, time and spatial basis functions were used to discretize the improved time-domain admittance boundary

Stepped beams are crucial in various structural engineering applications. This investigation aims to explore linear and nonlinear vibrational behaviors of multi-stepped beams made of functionally graded triply periodic minimal surface materials with various patterns of graphene platelet (GPL) reinforcements through the thickness. The first order shear deformable theory coupled with von Kármán strains

It is foremost to investigate group piles dynamic response for large nuclear island structure considering high-precision soil structure interaction (SSI). However, the existing group piles effect obtained using static stiffness cannot reflect to the frequency dependence, and the spatial coupling characteristics of far-field artificial boundary limits the efficient and fine impedance function computation

This paper investigates the performance analysis of asphalt pavement on fractional viscoelastic saturated subgrade subjected to moving loads. Firstly, the thermoviscoelastic constitutive equation of asphalt pavement is derived by using the fractional viscoelastic Zener model, time-temperature superposition principle (TTSP) and Williams-Landel-Ferry (WLF) equation. Subsequently, the dynamic governing

The discrete element method (DEM) is a widely used approach for studying the behavior of particles in industrial equipment, including rotary drums. Although DEM is highly accurate and efficient, it suffers from the computational cost in simulations. The primary objective of this research is to reduce the computational costs of DEM by introducing a novel machine learning (ML) approach based on a deep

The precise prediction of landslide displacement is crucial for effective geological disaster prevention and management. Existing models predominantly focus on temporal prediction, often neglecting the intricate spatiotemporal deformation characteristics of landslides. To address this gap, this study proposed a micro-macro spatiotemporal multi-graph network model (MM-STMGN) to analyze landslide deformation

Simulating the behavior of moored floating structures in real-world ocean waves presents significant challenges due to the inherent nonlinearities in both the wave environment and the dynamic response of the structure. This study introduces a novel three-dimensional (3D) time-domain solver, HOS-FNL, designed to accurately capture the complex interactions among wave components, the floating structure

Precise and efficient assisted diagnosis of fatty liver disease in coal miners is directly related to the development of occupational health prevention and control efforts in the coal mining industry. We proposed a cascade reduction strategy based on neighbourhood component analysis (NCA) joined with expectation maximization and principal component analysis (EM-PCA) to address the shortcomings of traditional

The hysteretic response of reinforced concrete (RC) columns is essential for understanding the seismic capacity of RC buildings. Traditional methods for estimating this response often rely on experimental tests or numerical simulations, which are labor-intensive, costly, and sometimes unstable. This study presents HysGAN-RC, a conditional generative adversarial network model developed to predict the

Laminated multiphase composite plates reinforced with carbon nanotubes (CNTs) and carbon fibers in an epoxy matrix offer excellent mechanical performance for lightweight, high-strength applications. This study focuses on their buckling behavior under in-plane loads by developing a soft computing framework that couples isogeometric analysis (IGA) with Murakami’s zigzag theory for layerwise displacement

Real-world systems frequently encounter data loss caused by external interference or channel congestion. Such unreliable transmission can significantly impact system dynamics. To mitigate its effects on Boolean control networks (BCNs), this paper investigates the asymptotic feedback set stabilization of BCNs with missing data. Firstly, an augmented system is constructed to handle the data loss. Subsequently

Hybrid-dimensional models are widely used in large-scale engineering machinery. In this paper, a hybrid-dimensional modeling method for the vibration of embedding 1D structures into 3D solids under rotating scenarios is developed. Based on the Nitsche method, a weak coupling strategy is first proposed to improve a rotation-free 1D beam, enhancing its prediction capability for complex geometries. Then

Efficient and accurate simulation of the motion response of floating wind turbine (FOWT) is critical for their design and operation. This study employed the vortex lattice method (VLM) to investigate and validate the aerodynamic performance of FOWT. By integrating the VLM with a potential flow hydrodynamic model, a coupled simulation framework was developed to comprehensively analyze floating platform

To address the challenges of electrostatic field calculation for dynamic sources in complex terrains, this study proposes a computational strategy combining multi-level conformal mapping (CM) and the method of image (MI). By coordinating fractional linear transformations with the Cauchy integral theorem, the actual terrain boundary was converted into a standard half-plane, establishing a mathematical

The environmental vibration problem induced by metro operation can be simplified as a semi-infinite domain multi-boundary wave problem. With the rapid development of metro networks, the vibration problems have an increasingly significant impact on adjacent living and working environments. Therefore, the demand for high-precision environmental vibration analysis is becoming more and more urgent. Finite

The parameters calibration of the original fracture constitutive model for the joint element in the finite-discrete element method (FDEM) is very complex. To simplify the parameter calibration procedure, we firstly propose a linear fracture constitutive model for the two-dimensional finite-discrete element method (FDEM). Based on the simplified constitutive model for the joint element, the proposed

Inspired by the dynamics of blood flow around clots, emboli, and drug capsules in blood vessels, this study introduces a hydrodynamic model describing the steady, pressure-driven flow of a viscous, incompressible fluid past multiple equally sized circular cylinders within a rectangular microchannel. To create a permeable environment, the microchannel is embedded with a uniform, isotropic porous medium

To improve the accuracy and computational efficiency of the CDEM for deep coal mine roadway excavation modeling, this study proposes a heterogeneous CPU/GPGPU-accelerated solver that integrates a mixed continuous–discontinuous media algorithm. The solver employs an explicit time integration method combined with a modular approach for 3D tetrahedral solid finite elements and fracturable penalty springs

Physics-driven particle relaxation, driven by either constant background pressure or the kernel gradient correction (KGC) matrix, has been proposed to generate isotropic and body-fitted particle distributions for complex geometries while ensuring zero-order consistency in smoothed particle hydrodynamics (SPH). However, this relaxation process often encounters challenges, such as a low decay rate of

This study introduces a novel spring element model for efficient simulation of nonlinear seepage in porous media. The model discretizes the simulation domain into tetrahedral elements and constructs orthogonal Three-dimensional permeability networks within each element, establishing a quantitative relationship between pipe flow and nodal pressure differences. By developing a mathematical model linking

The transverse free vibration analysis of composite intelligent plates constituted by the functionally graded substrate and full size surface-attached piezoelectric laminae is conducted by means of the scaled boundary finite element method (SBFEM) in association with the precise integration algorithm (PIA). It is needful to point out that material coefficients of the functionally graded host layer

As a promising imaging technique, electrical impedance tomography (EIT) is used to reflect the conductivity distribution variation of human tissues. Different from the lung EIT, the application of the craniocerebral EIT is challenging. This is attributed to the fact that the skull with high resistivity greatly restricts the injected current from flowing into the brain tissue. Consequently, the measured

We present PINNs-MPF framework, an application of Physics-Informed Neural Networks (PINNs) to handle Multi-Phase-Field (MPF) simulations of microstructure evolution. A combination of optimization techniques within PINNs and in direct relation to MPF method are extended and adapted. The numerical resolution is realized through a multi-variable time-series problem by using fully discrete resolution.

The traditional boundary element method (BEM) often faces challenges in efficiently solving inhomogeneous problems, particularly in thin-walled geometries, due to the need for domain discretization and the handling of nearly singular integrals. In this study, we propose an efficient hybrid algorithm that combines the BEM with physics-informed neural networks (PINNs) to solve inhomogeneous potential

Numerical simulation of slope instability remains a critical challenge in geotechnical engineering, particularly for large deformations and long-term seepage. The traditional finite element method (FEM) is prone to mesh distortion in large-deformation modeling, while the material point method (MPM) is less efficient for small deformations associated with long-term seepage. To overcome these limitations

This research introduces a dual reciprocity boundary element method (BEM) designed to analyze the transient scattering of vertically travelling incident P-SV waves. By using static fundamental solutions and appropriate predictor operations, the domain inertia integrals from the equilibrium equation were transformed into boundary integral equations. The computable format of the integral equations was

In this work, the ZZ-BD recovered stress field is first used to enhance the data transferred from the global to the local scale models in the Generalized Finite Element Method with Global–Local enrichments (GFEMgl). The recovered stress field is constructed by solving a block-diagonal system of equations resulting from an L2 approximate function projection associated with the singular stress field

The problem of radiation diffusion is extremely challenging due to the complex physical processes and nonlinear characteristics of the equation involved. In this paper, we propose a class of high-precision meshless methods for 3D nonlinear radiation diffusion equations applicable to spherical and cylindrical walls. Firstly, when the energy density is linearly related to temperature, we use a full-implicit

In this study, a new virtual material point peridynamic model (abbreviated as VMPPD) is proposed to capture the fracture behavior of composite laminates with arbitrary fiber orientation. The unique feature is that virtual material points serve as intermediate variables to achieve load transfer in a regularized discrete grid. As a result, a PD model for describing the reinforcement characteristics of

The paper introduces a novel methodology based on a generalized formulation and higher-order-theories for the fully-coupled multifield analysis of laminated curved structures subjected to thermal, magnetic, and mechanical loads. The formulation follows the Equivalent Single Layer approach, taking into account a generalized through-the-thickness expansion of displacement field components, scalar magnetic

Artificial Neural Networks (ANNs) have revolutionized machine learning by enabling systems to learn from data and generalize to new, unseen examples. As biologically inspired models, ANNs consist of interconnected neurons organized in layers, mimicking the human brain’s functioning. Their ability to model complex, nonlinear processes makes them powerful tools in various domains. In this study, the

Rock fractures significantly diminish shear strength and stability of rock masses. Understanding the shear behavior of fractured rock and associated energy release is essential for disaster prediction in rock engineering. This study investigates the shear behavior and damage evolution of intact and fractured rock samples through the analysis of acoustic emission (AE) characteristics. We conduct a series

Traditional model for composite laminae based on bond-based peridynamics (BB-PD) involves only two material parameters, which is insufficient to fully describe the complicated engineering properties of composite laminae. This limitation results in constrained Poisson's ratio and shear modulus in the PD model. In this study, a novel fracture model for composite laminae is proposed based on BB-PD, which

The generalized nth-order perturbation method for the quantitative uncertainty analysis in half-space acoustic problems proposed in this study is based on the isogeometric boundary element method, where the acoustic wave frequency is defined as a stochastic variable. We derive the Taylor series expansion and the kernel function formulation of the acoustic boundary integral equation for the half-space

Numerical solutions of initial value problems (IVPs) for stiff differential equations via explicit methods such as Euler’s method, trapezoidal method and Runge–Kutta methods suffer from stability issues and demand unacceptably small time steps. Backward differentiation formulas (BDF), a class of implicit methods, have been successfully used for resolving stiff IVPs. Classical BDF methods are derived

Fracture initiation in solids fundamentally arises from pre-existing discontinuities, such as crack networks and void distributions, which are ubiquitously observed in engineering structures. This paper presents an innovative unsupervised learning framework, termed Kolmogorov–Arnold representation theorem enhanced peridynamic-informed neural network (PD-KINN), designed to address challenges in elastic