Optimal design of structures subjected to time history loading by swarm intelligence and an advanced metamodel

Gholizadeh, Saeed; Salajegheh, E.

doi:10.1016/j.cma.2009.04.010

Cited by 78 publications

(24 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They operate as black box, model-free, and adaptive tools to capture and learn significant structures in data. Their computing abilities have been proven in the fields of prediction and estimation, pattern recognition, and optimization [8][9][10][11]. They are suitable particularly for problems too complex to be modeled and solved by classical mathematics and traditional procedures.…”

Section: Introductionmentioning

confidence: 99%

Assessment of load carrying capacity of castellated steel beams by neural networks

Gholizadeh

Pirmoz

Attarnejad

2011

Journal of Constructional Steel Research

Self Cite

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Assessment of load carrying capacity of castellated steel beams by neural networks

Gholizadeh

Pirmoz

Attarnejad

2011

Journal of Constructional Steel Research

Self Cite

View full text Add to dashboard Cite

“…The best results are obtained by considering i = 2 and j = 0 in (22). The details of designing a wavelet neural network can also be found in Gholizadeh et al (2008) and Gholizadeh and Salajegheh (2009).…”

Section: Approximate Dynamic Analysis Using a Neural Network Modelmentioning

confidence: 97%

Shape optimal design of materially nonlinear arch dams including dam-water-foundation rock interaction using an improved PSO algorithm

Seyedpoor

Salajegheh

2011

Optim Eng

Self Cite

View full text Add to dashboard Cite

An efficient optimization procedure is proposed to find the optimal shape of arch dams including dam-water-foundation rock interaction subject to earthquake. The arch dam is treated as a three-dimensional structure involving the material nonlinearity effects. For this purpose, the nonlinear behavior of the dam concrete is idealized as an elasto-plastic material using the Drucker-Prager model. In order to reduce the computational cost of optimization process, a wavelet back propagation (WBP) neural network is designed to approximate the dam response instead of directly evaluating it by a time-consuming finite element analysis (FEA). An improved particle swarm optimization (IPSO) is also presented. In test example, the computational merits of the proposed methodology for optimizing an existing arch dam are demonstrated.

show abstract

“…Use of approximations has been presented in several fields of engineering, such as structural optimization (Salajegheh 2000;Salajegheh and Salajegheh 2002;Gholizadeh and Salajegheh 2009) and structural reliability analysis (Mahadevan 1997;Grandhi and Wang 1998;Melchers and Ahammed 2004;Cheng et al 2008) to reduce the computational time.…”

Section: The Third Order Approximationmentioning

confidence: 99%

Reliability-based topology optimization of double layer grids using a two-stage optimization method

Mashayekhi

Salajegheh

et al. 2011

Struct Multidisc Optim

Self Cite

View full text Add to dashboard Cite

This paper presents a two-stage optimization method for reliability-based topology optimization (RBTO) of double layer grids that considers uncertainties in applied loads. The optimization is performed using a two-stage optimization by employing the method of moving asymptotes (MMA) and ant colony optimization (ACO), which is called MMA-ACO method. For implementation of MMA-ACO, the structural stiffness is maximized using MMA, first. Then, the results of MMA are used to enhance ACO through the following four modifications: (I) finding the structural importance rate of elements or joints and using this to achieve a better topology, (II) determining the number of compressive and tensile element types, (III) changing the lower limit of available cross-sectional areas for the elements of each group and (IV) modifying the generation of random stable structures. In reliability analysis, multiple criteria i.e. stiffness and eigenvalue are considered where the probability of failure in each mode is calculated by Monte Carlo simulation (MCS). To reduce the computational time, the eigenvalues are evaluated using the third order approximation (TOA). Through numerical examples, reliability-based topology designs of typical double layer grids are obtained by ACO and MMA-ACO methods. The numerical results reveal the computational advantages and effectiveness of the proposed MMA-ACO method for the RBTO of double layer grids. Also, the importance of considering uncertainties is then demonstrated by comparing the results obtained by those of other failure probabilities.

show abstract

Optimal design of structures subjected to time history loading by swarm intelligence and an advanced metamodel

Cited by 78 publications

References 30 publications

Assessment of load carrying capacity of castellated steel beams by neural networks

Assessment of load carrying capacity of castellated steel beams by neural networks

Shape optimal design of materially nonlinear arch dams including dam-water-foundation rock interaction using an improved PSO algorithm

Reliability-based topology optimization of double layer grids using a two-stage optimization method

Contact Info

Product

Resources

About