Jaehong Lee

• Ph.D.
• Professor (Full) at Sejong University

Deep energy method (DEM) has shown its successes to solve several problems in solid mechanics recently. It is known that determining proper integration scheme to precisely calculate total potential energy (TPE) value is crucial to achieve high-quality training performance of DEM but it has not been discovered satisfactorily in previous related work...

Physics-informed neural networks (PINNs) usually confront significant difficulties to accurately solve partial differential equations (PDEs) due to many pathologies caused by gradient failures during training process. In this paper, a gradient disease regarding the ill-conditioned loss function of the PINN methodology is intensively investigated in...

The utilization of Physics-informed Neural Networks (PINNs) in deciphering inverse problems has gained significant attention in recent years. However, the PINN training process for inverse problems is notably restricted due to gradient failures provoked by magnitudes of partial differential equations (PDEs) parameters or source functions. To addres...

The study and manufacture of functionally graded (FG) shallow shells with the variable thickness are essential for the actual application of these types of structures. Previously, many researchers have developed different approaches to analyzing the mechanical behaviors of the FG structures, in which the thickness parameter has been assumed to be c...

In this work, an effective Damage-Informed Neural Network (DINN) is first developed to pinpoint the position and extent of structural damage. Instead of resolving the damage identification problem by conventional numerical methods, a Deep Neural Network (DNN) is employed to minimize the loss function which is designed by combining multiple damage l...

Exact boundary conditions (BCs) imposition technique is widely used in physics-informed neural networks (PINNs) for solving boundary value problems (BVPs). In this regard, the selection of trial function satisfying essential BCs becomes hard to determine when complex geometric domain or essential BCs are considered. To address this challenge, an un...

In this paper, a novel physics-informed neural networks (PINNs) called deep reduced-order least-square (ROLS) is proposed. The deep ROLS is a combination of reduced-order and least-square methods in the context of PINN methodology. The key idea of the deep ROLS is to convert a higher-order PDE to a system of lower-order PDEs by using primary and se...

Fuel cell hybrid electric vehicles (FCHEVs) have been recognized as a promising solution for green and sustainable transportation. Unfortunately, the low performance and high operational cost make current FCHEVs less attractive than their alternatives. In this paper, we address a new contribution to the optimal design for the FCHEV components’ para...

In this study, we propose a novel deep learning model named as the Finite-element-informed neural network (FEI-NN), inspired from finite element method (FEM) for parametric simulation of static problems in structural mechanics. The approach trains neural networks in the supervised manner, in which parametric variables of structures are considered a...

Conventional scan to building information modeling (BIM) automation mainly deals with geometry. However, one of its limitations is the time it takes and the costs in generating material. Therefore, this study proposes an automated scan-to-BIM method considering both the geometry and material of building objects. It recognizes the geometry from a po...

Functionally graded porous plates have been validated as remarkable lightweight structures with excellent mechanical characteristics and numerous applications. With inspiration from the high strength-to-volume ratio of triply periodic minimal surface (TPMS) structures, a new model of porous plates, which is called a functionally graded TPMS (FG-TPM...

Functionally graded porous plates have been validated as remarkable lightweight structures with excellent mechanical characteristics and numerous applications. With inspiration from the high strength-to-volume ratio of triply periodic minimal surface (TPMS) structures, a new model of porous plates, which is called a functionally graded TPMS (FG-TPM...

In this article, a density-driven unified multi-material topology optimization framework is suggested for functionally graded (FG) structures under static and dynamic responses. For this, two-dimensional solid structures and plate-like structures with/without variable thickness are investigated as design domains using multiple in-plane bi-direction...

Research on strengthening and retrofitting of concrete structures against explosive loading has recently received much attention. This paper proposes a new type of reinforcement for concrete panels to enhance their blast‐resistant capacity. The reinforcement structure is naturally optimized with continuous nonself‐intersecting surfaces, known as tr...

In the current study, we present an efficient and straightforward numerical framework for exploring the responses of functionally graded triply periodic minimal surface (FG-TPMS) microplates. FG-TPMS structures including Primitive (P), Gyroid (G), and I-graph and Wrapped Package-graph (IWP) exhibit numerous potential applications in engineering due...

We in this work present an efficient and straightforward computational model to discover transient responses of agglomerated graphene platelets (GPLs)–reinforced porous sandwich plates subjected to various dynamic loads. To this end, a generalized three-variable high-order shear deformation plate theory within the NURBS-based isogeometric analysis...

In this study, a physics-informed neural energy-force network (PINEFN) framework is first proposed to directly solve the optimum design of truss structures that structural analysis is completely removed from the implementation of the global optimization. Herein, a loss function is constructed to guide the training network based on the complementary...

In this work, a direct physics-informed neural network (DPINN) is first proposed to analyze the stability of truss structures that incremental-iterative algorithm is completely removed from the implementation process. Instead of resolving of nonlinear equations as in conventional numerical methods, a neural network (NN) is employed to minimize the...

In this paper, a robust deep neural network (DNN)-based parameterization framework is proposed to directly solve the optimum design for geometrically nonlinear trusses subject to displacement constraints. The core idea is to integrate DNN into Bayesian optimization (BO) to find the best optimum structural weight. Herein, the design variables of the...

Surrogate modeling techniques are widely employed in solving constrained expensive black-box optimization problems. Therein, Kriging is among the most popular surrogates in which the trend function is considered as a constant mean. However, it also encounters several challenges related to capturing the overall trend with a relatively limited number...

Thin cylindrical shells are widespread in structural engineering, such as civil engineering structures, oil rigs, oil pipes, rocket hull and aircraft fuselages. With the development of materials science, the behavior of the cylindrical shell structures made of advanced materials has attracted many scientists. This paper proposed an analytical appro...

Because the proportion between the compressive strength of high‐performance concrete (HPC) and its composition is highly nonlinear, more advanced regression methods are demanded to obtain better results. Super learner models, which are based on several ensemble methods including random forest regression (RFR), an adaptive boosting (AdaBoost), gradi...

This paper proposes an effective one-dimensional convolutional gated recurrent unit neural network (1D-CGRU) by combining a one-dimensional convolutional neural network (1D-CNN) and a gated recurrent unit neural network (GRU) for real-time structural damage detection (SDD) based on time-series vibration signals measured from a large number of accel...

Porous structures with controllable mechanical and hydrodynamic characteristics are prospective candidates for coastal engineering applications. In this paper, a novel emerged porous breakwater based on triply periodic minimal surface (TPMS) cellular structure is proposed. Mechanical behaviour of TPMS structures is analyzed by conducting uniaxial c...

Analytical paradigms have limited conventional form-finding methods of tensegrities; therefore, an innovative approach is urgently needed. This paper proposes a new form-finding method based on state-of-the-art deep learning techniques. One of the statical paradigms, a force density method, is substituted for trained deep neural networks to obtain...

Isotropic ultra-thin shells or membranes, as well as cable–membrane structures, cannot resist loads at the initial state and always require a form-finding process to reach the steady state. After this stage, they can work in a pure membrane state and quickly experience large deflection behavior, even with a small amplitude of load. This paper aims...

In this paper, an efficient deep unsupervised learning (DUL)-based framework is proposed to directly perform the design optimization of truss structures under multiple constraints for the first time. Herein, the members’ cross-sectional areas are parameterized using a deep neural network (DNN) with the middle spatial coordinates of truss elements a...

This study proposes an adaptive 3-stage hybrid teaching-based differential evolution (ATDE) algorithm to deal with sizing and layout frequency-constrained truss designs more efficiently. The optimization process is divided into 3 stages, and suitable mutation formulae are applied adaptively in each stage. A novel operator inspired by the teaching p...

A straightforward and effective scheme for adaptive initialization is proposed and coupled with the Linearly reduced population size Success History based Adaptive Differential Evolution (LSHADE) for solving constrained optimization problems. The novel contributions are in the initialization phase: (i) exploiting the information of problem dimensio...

In this study, a robust and simple unsupervised neural network (NN) framework is proposed to perform the geometrically nonlinear analysis of inelastic truss structures. The core idea is to employ the NN to directly estimate nonlinear structural responses without utilizing any time-consuming incremental-iterative algorithms as those done in standard...

Daylight analysis is essential in building design to ensure indoor environment quality, including health and thermal comfort vis-à-vis energy. It is a repeating and time-consuming process of design options. Several studies conducted machine learning models to accurately predict daylight performance in particular design situations. Therefore, develo...

In recent years, the tensegrity structures have been studied and applied extensively in the engineering field because of their unique topology, shape, and stability. An effective force density-informed neural network (FDINN) approach for performing a robust force finding procedure is constructed in this paper by utilizing a fully connected neural n...

A two-way beam string structure is composed of upper beam and two different cables, namely, sagging and arch-shaped cables. It is designed for structural members under bi-directional loads because the maximum stress and displacement can dramatically reduced. In this study, a parametric study for this structure is presented to provide optimal design...

We in this paper propose an efficient and vigorous approach based on flexible polygonal meshes for solving stress-constrained topology optimization problems involving both compressible and nearly incompressible materials. The core idea is to employ a polygonal composite finite element technique to deal with volumetric locking phenomena in nearly in...

Nowadays, there are a lot of iterative algorithms which have been proposed for nonlinear problems of solid mechanics. The existing biggest drawback of iterative algorithms is the requirement of numerous iterations and computation to solve these problems. This can be found clearly when the large or complex problems with thousands or millions of degr...

This study presents vibration and buckling optimization of thin-walled functionally graded (FG) beams with bi-symmetric I-shape and channel-section. Material properties are assumed to vary through-the-contour direction by a non-monotonic function. A piece-wise cubic Hermite interpolation is used to estimate the volume fractions of the constituent p...

In this paper, we explore the advantages of heuristic mechanisms and devise a new optimization framework named Sequential Motion Optimization (SMO) to strengthen gradientbased methods. The key idea of SMO is inspired from a movement mechanism in a recent metaheuristic method called Balancing Composite Motion Optimization (BCMO). Specifically, SMO e...

In this article, we explore a three-dimensional solid isogeometric analysis (3D-IGA) approach based on a nonlocal elasticity theory to investigate size effects on natural frequency and critical buckling load for multi-directional functionally graded (FG) nanoshells. The multi-directional FG material uses a power law rule with three power exponent i...

This article aims to introduce a multigrid preconditioned conjugate gradient (MPCG)-oriented topology optimization (TO) methodology using multiple bi-directional functionally graded (BFG) models for the first time. For that purpose, the MPCG paradigm is integrated into the TO procedure to more effectively and quickly resolve linear algebraic system...

As initial endeavors, this paper presents an in-depth study to investigate the influence of nanoscale parameters on bending and free vibration responses of functionally graded carbon nanotube-reinforced composite (FG-CNTRC) nanoshells with double curvature. Carbon nanotubes (CNTs) are considered as reinforcements that are distributed across the she...

Design optimization of geometrically nonlinear structures is well known as a computationally expensive problem by using incremental-iterative solution techniques. To handle the problem effectively the optimization algorithm needs to ensure that the trade-off between the computational time and the quality of the solution is found. In this study, a d...

Recent advances in chip and sensor technology allow a large amount of data to be collected for serving structural damage detection (SDD). However, how to efficiently utilize and transform these complex sensing data into useful engineering information has remained many challenges. One of the major challenges in SDD using sensing data is how to effec...

The main goal of this research paper is to present the modeling and analysis of bi-directional functionally graded (BDFG) nanobeams within the framework of the Timoshenko beam theory and nonlocal strain gradient theory. According to the DBFG material model, the material properties of the nanobeams are simultaneously distributed in two different dir...

This article introduces a simple and effective adaptive surrogate model to structural reliability analysis using deep neural network (DNN). In this paradigm, initial design of experiments (DoEs) are randomly selected from a given Monte Carlo Simulation (MCS) population to build the global approximate model of performance function (PF). More importa...

In the paper, an analysis of thin-walled functionally graded straight and curved beams for general non-uniform polygonal cross-sections has been introduced for vibration problems. Higher order beam theory that has fully taken into account major deformations, e.g. in-plane distortion, out-of-plane warping, is adopted by means of beam frame modal app...

The purpose of this study is to present a quasi-three-dimensional (quasi-3D) shear deformation theory for static bending and free vibration analyses of porous sandwich functionally graded (FG) plates with graphene nanoplatelets (GPLs) reinforcement. In addition, we propose a novel sandwich plate model with various outstanding features in terms of s...

Due to complexities from the interaction between steel tube and concrete filling of concrete-filled steel tubular (CFST) columns, their strengths are very complicated, which is a highly nonlinear relation with material strengths and geometry. Categorical gradient Boosting (CatBoost), which is advanced boosting machine, is presented to solve the pro...

The operations of metaheuristic optimization algorithms depend heavily on the setting of control parameters. Therefore the addition of adaptive control parameter has been widely studied and shown to enhance the problem flexibility and overall performance of the algorithms. This paper proposes Q-learning Differential Evolution (qlDE) algorithm, an a...

This paper proposes an intelligent multi-objective optimization approach using the deep feedforward neural network (DNN) integrated with the speed-constrained multi-objective particle swarm optimization (SMPSO) to give the so-called DNN-SMPSO algorithm for solving multi-objective optimization problems of two-dimensional functionally graded (2D-FG)...

This paper presents a novel combination of Generative Adversarial Networks (GANs) and Clustering Analysis (CA) for topology optimization. Based on the results from the topology analysis, new data are generated by the GANs and Deep Convolutional GANs (DCGANs). K-means Clustering Analysis is employed to select optimized valid data with the minimum co...

The buckling and lateral buckling of thin-walled functionally graded (FG) open-section beams with various types of material distributions are studied. The approach is based on assumption that the volume fraction of particles varies through the contour direction according to a power law. The governing buckling equation and a finite element method ha...

Application of nano/micro structures has become popular in a wide range of advanced engineering systems in recent years. For a better insight, this paper presents an intensive numerical study on the static and dynamic responses of smart functionally graded microplates with graphene platelets (GPLs) reinforcement under concurrently both mechanical a...

In this study, we have explored the structural damage detection of truss structures using the state-of-the-art deep learning techniques. The surrogate models, deep neural networks, are used to train the knowledge of the patterns in the response of the undamaged and the damaged structures. The limited sensors are then used to collect the response fr...

The paper adequately presents an analysis of thin-walled functionally graded straight and curved beams for general non-uniform polygonal cross-sections. In order to mathematically model a complex beam which property information in both material distribution and geometric continuity need to be collected from multiple patches through blade thickness...

For the first time, an investigation on the shape and material optimization for buckling behavior of functionally graded (FG) toroidal shells using differential evolution (DE) algorithm is presented in this paper. For buckling analysis, an analytical approach is used to derive governing equations, then combining with the Galerkin procedure to obtai...

An investigation of free vibration of a thin-walled beams with functionally graded materials (FGMs) is presented. The mechanical properties of thin-walled beam are assumed to vary along the contour direction of the thin-walled cross section. Governing differential equations are derived by means of Hamilton's principle. A finite element model is dev...

The postbuckling and geometrically nonlinear behaviors of imperfect functionally graded carbon nanotube-reinforced composite (FG-CNTRC) shells under axial compression are investigated in this paper. For the first time, a new type of instability named “snap-backward” with the presence of three limit points on the equilibrium path is proposed. A nove...

Different from large deflection analyses of plates and shells, for analysis of an isotropic membrane structure a form finding procedure is first performed to find the new geometry of membrane. With this new geometry, large deflection analysis is conducted and the membrane works in a pure membrane state. In the conventionally numerical approaches fo...

This paper concerns a new fabrication method and experimental studies for tensegrity systems. Numerous studies have observed fabrications of the tensegrity systems, however, full-scale tests under load control are rarely reported. In this work, we first develop a form-finding method to draw the equilibrium status with the corresponding force densit...

A new methodology for making design decisions of structures using multi-material optimum topology information is presented. Multi-material analysis contributes significant applications to enhance the bearing capacity and performance of structures. A method that chooses an appropriate material combination satisfying design stiffness requirement econ...

In this work, the shell formulation for postbuckling analysis of functionally graded carbon nanotube-reinforced composite shells based on isogeometric analysis and first-order shear deformation shell theory (FSDT) is proposed. The nonlinearity of shells is formed in the Total Lagrangian approach considering the von Karman assumption. The nonlinear...

The paper is aimed at enhancing computational performance for optimizing the material distribution of tri-directional functionally graded (FG) plates. We exploit advantages of using a non-uniform rational B-spline (NURBS) basis function for describing material distribution varying through all three directions of functionally graded (FG) plates. Two...

In this study, we numerically investigate static and free vibration responses of functionally graded (FG) porous plates with graphene platelets (GPLs) reinforcement using an efficient polygonal finite element method (PFEM). While the bending strain field is approximated through quadratic serendipity shape functions, the shear strain field is calcul...

Effectiveness of several currently popular topology optimization methods is closely related to the number of design variables consisted of discretized finite elements. Since the number of design variables is proportional to the number of finite element meshes, a very fine discretization needs more computational cost to carry out a finite element an...

The fatigue crack growth analysis of an interfacial cracked structure plays an essential role in the design process as well as the safety assessment for various engineering fields in real life. This paper proposes a novel and effective computational approach based on polygonal meshes for crack growth simulation of interfacial crack problems. Polygo...

Structural damage assessment is a challenging problem of study due to lack of information in data measurement and the difficulty of extracting noisy features from the structural responses. Therefore, this paper proposes an effective deep feedforward neural networks (DFNN) method for damage identification of truss structures based on noisy incomplet...

This study presents applications of the multivariate adaptive regression splines (MARS) method for predicting the ultimate loading carrying capacity (Nu) of rectangular concrete-filled steel tubular (CFST) columns subjected to eccentric loading. A database containing 141 experimental data was collected from available literature to develop the MARS...

A recently developed adaptive hybrid evolutionary firefly algorithm (AHEFA) as a cross-breed of differential evolution (DE) approach and firefly algorithm (FA) is utilized to address inverse optimization problems in two-stage damage detection of truss structures. In the first step, the most potentially damaged elements are recognized utilizing a mo...

A novel and effective artificial neural network (ANN)-differential evolution (DE) approach as an integration of ANN into DE is first introduced to the material distribution optimization of bidirectional functionally graded (BFG) beams under free vibration. In this methodology, ANN is utilized as an analyzer to predict responses of BFG beams instead...

This paper aims at forecasting the crack propagation in risk assessment of engineering structures based on time series algorithms named “long short-term memory” and “multi-layer neural network”. The core idea is how to predict precisely the accuracy of solution of crack growth in engineering fracture structures without requiring re-modeling and re-...